From 95650ddc9a7e5d394b2440525f5a28e66f64f270 Mon Sep 17 00:00:00 2001 From: Hossein Kavianihamedani Date: Wed, 15 Oct 2025 13:27:46 -0700 Subject: [PATCH] Adding SFT Notebook --- apps/sft/README.md | 531 + apps/sft/actor.py | 133 + apps/sft/interactive_config_notebook.ipynb | 10336 +++++++++++++++++++ apps/sft/spawn_actor.py | 139 + apps/sft/trainer_actor.py | 189 + apps/sft/utils.py | 187 + 6 files changed, 11515 insertions(+) create mode 100644 apps/sft/README.md create mode 100644 apps/sft/actor.py create mode 100644 apps/sft/interactive_config_notebook.ipynb create mode 100644 apps/sft/spawn_actor.py create mode 100644 apps/sft/trainer_actor.py create mode 100644 apps/sft/utils.py diff --git a/apps/sft/README.md b/apps/sft/README.md new file mode 100644 index 000000000..2b18d8b36 --- /dev/null +++ b/apps/sft/README.md @@ -0,0 +1,531 @@ +# SFT (Supervised Fine-Tuning) Training + +This directory contains code for supervised fine-tuning of large language models using PyTorch and the Monarch actor framework. + +## Quick Start + +### Option 1: Command Line (Production) + +```bash +# Run training with a config file +python -m forge.apps.sft.main --config forge/apps/sft/llama3_8b.yaml +``` + +### Option 2: Interactive Notebook (Experimentation) + +Use the Jupyter notebook for interactive configuration and testing: + +```bash +# Open the notebook in VS Code or JupyterLab +code forge/apps/sft/interactive_config_notebook.ipynb + +# Or start JupyterLab +cd /home/hosseinkh/TorchForge/forge/apps/sft +jupyter lab +``` + +--- + +## Files Overview + +| File | Purpose | When to Use | +|------|---------|-------------| +| `main.py` | Main training script | Production training runs | +| `trainer_actor.py` | Training actor implementation | Core training logic | +| `spawn_actor.py` | Actor spawning utilities | Distributed setup | +| `utils.py` | Utility functions | Helper functions for data/training | +| `interactive_config_notebook.ipynb` | Interactive configuration | Quick experiments & learning | +| `llama3_8b.yaml` | Default config for Llama 3 8B | Production configuration | +| `qwen3_8b.yaml` | Config for Qwen 3 8B | Alternative model | + +--- + +## Interactive Notebook Guide + +The `interactive_config_notebook.ipynb` allows you to: + +1. **Interactively build configurations** - Modify settings in real-time +2. **Visualize configurations** - See YAML output before saving +3. **Test configurations** - Quickly iterate on experiments +4. **Save to YAML** - Export your configuration for production runs + +### Notebook Structure + +``` +Step 1: Setup Environment + └─ Import libraries, set working directory + +Step 2: Configure Model and Process Settings + └─ Model type, number of GPUs/processes + +Step 3: Configure Optimizer and LR Scheduler + └─ Learning rate, warmup steps + +Step 4: Configure Training Settings + └─ Batch size, sequence length, training steps + +Step 5: Configure Checkpoint and Activation Checkpointing + └─ Where to save, how often to save + +Step 6: Configure Communication and Parallelism Settings + └─ FSDP, tensor parallelism, etc. + +Step 7: Combine All Configurations + └─ Merge into complete config + +Step 8: Save to YAML File + └─ Export for use with main.py + +Step 9: Optional - Run Training + └─ Launch training from notebook +``` + +### How to Use the Notebook + +1. **Open the notebook:** + ```bash + code forge/apps/sft/interactive_config_notebook.ipynb + ``` + +2. **Run cells sequentially** (Shift+Enter) from top to bottom + +3. **Modify parameters** in each step according to your needs: + - **Model path**: Point to your model weights + - **Training steps**: How long to train + - **Batch size**: Adjust for your GPU memory + - **Learning rate**: Tune for your task + - **Checkpoint folder**: Where to save checkpoints + +4. **View the configuration** in Step 7 to see the complete YAML + +5. **Save to YAML** in Step 8 to export your config + +6. **Run training**: + - Option A: Use the notebook (Step 9) + - Option B: Use command line with your saved config + +--- + +## Configuration Files + +### YAML Structure + +```yaml +comm: + trace_buf_size: 0 + +model: + name: llama3 + flavor: 8B + hf_assets_path: /path/to/model + +processes: + procs: 8 # Number of processes (usually = number of GPUs) + with_gpus: true + +optimizer: + name: AdamW + lr: 1e-5 + eps: 1e-8 + +lr_scheduler: + warmup_steps: 200 + +training: + local_batch_size: 1 + seq_len: 2048 + max_norm: 1.0 + steps: 1000 + compile: false + dataset: c4 + +parallelism: + data_parallel_replicate_degree: 1 + data_parallel_shard_degree: -1 # -1 = use all GPUs for FSDP + tensor_parallel_degree: 1 + pipeline_parallel_degree: 1 + context_parallel_degree: 1 + expert_parallel_degree: 1 + disable_loss_parallel: false + +checkpoint: + enable: true + folder: /path/to/checkpoints + initial_load_path: /path/to/model + initial_load_in_hf: true + last_save_in_hf: true + interval: 500 + async_mode: disabled + +activation_checkpoint: + mode: selective + selective_ac_option: op +``` + +### Key Parameters to Adjust + +#### For Quick Testing: +```yaml +training: + steps: 10 # Just 10 steps + dataset: c4_test # Tiny test dataset + +processes: + procs: 1 # Single GPU +``` + +#### For Production Training: +```yaml +training: + steps: 10000 # Full training run + dataset: c4 # Full C4 dataset + +processes: + procs: 8 # All 8 GPUs +``` + +#### For Memory-Constrained GPUs: +```yaml +training: + local_batch_size: 1 # Smallest batch size + seq_len: 1024 # Shorter sequences + +activation_checkpoint: + mode: selective # Enable activation checkpointing +``` + +--- + +## Running Training + +### Single Node (8 GPUs) + +```bash +python -m forge.apps.sft.main --config forge/apps/sft/llama3_8b.yaml +``` + +### Multi-Node (32 GPUs across 4 nodes) + +1. **Update config:** + ```yaml + processes: + procs: 32 # 4 nodes × 8 GPUs + with_gpus: true + ``` + +2. **Submit to cluster:** + ```bash + sbatch --nodes=4 --gpus-per-node=8 \ + python -m forge.apps.sft.main --config forge/apps/sft/llama3_8b.yaml + ``` + +--- + +## Datasets + +### Available Datasets + +| Dataset | Size | Use Case | Config Value | +|---------|------|----------|--------------| +| `c4` | ~750 GB | Production training | `dataset: c4` | +| `c4_test` | ~Few MB | Quick testing | `dataset: c4_test` | +| `c4_validation` | ~30 GB | Validation | `dataset: c4_validation` | + +### Using Custom Datasets + +Modify `utils.py` or `trainer_actor.py` to add your custom dataset loading logic. + +--- + +## Monitoring Training + +### Logs + +Training logs show: +- Loss per step +- Learning rate +- Checkpoint saves +- GPU memory usage + +Example output: +``` +[Trainer-0/8] 2025-10-14 13:20:00 INFO 1 / 1000|Loss: 3.245 +[Trainer-0/8] 2025-10-14 13:20:05 INFO 2 / 1000|Loss: 3.189 +[Trainer-0/8] 2025-10-14 13:20:10 INFO 3 / 1000|Loss: 3.134 +``` + +### Checkpoints + +Checkpoints are saved to `checkpoint.folder` every `checkpoint.interval` steps: +``` +/path/to/checkpoints/ +├── step_500/ +│ ├── model.pt +│ └── optimizer.pt +├── step_1000/ +│ ├── model.pt +│ └── optimizer.pt +``` + +--- + +## Architecture + +### Actor-Based Distributed Training + +``` +Orchestrator (main.py) + │ + ├─ spawn_actor.run_actor() + │ │ + │ └─ TrainerActor × 8 (one per GPU) + │ │ + │ ├─ setup() → Load data, model, optimizer + │ ├─ train() → Training loop + │ └─ cleanup() → Save final checkpoint +``` + +### Key Components + +#### 1. TrainerActor (`trainer_actor.py`) +- Main training class +- Inherits from `ForgeActor` and `ForgeEngine` +- Handles: + - Data loading + - Model training + - Checkpointing + - Distributed coordination + +#### 2. SpawnActor (`spawn_actor.py`) +- Utility for spawning actors +- Handles: + - Actor configuration + - Distributed setup + - Actor lifecycle management + +#### 3. Utils (`utils.py`) +- Helper functions for: + - Data loading + - Tokenization + - Metrics logging + +--- + +## Parallelism Strategies + +### FSDP (Fully Sharded Data Parallelism) +- **Default**: `data_parallel_shard_degree: -1` +- Shards model parameters across all GPUs +- Reduces memory per GPU +- Recommended for large models + +### Tensor Parallelism +- **Config**: `tensor_parallel_degree: N` +- Splits individual layers across N GPUs +- Useful for very large models that don't fit on single GPU + +### Pipeline Parallelism +- **Config**: `pipeline_parallel_degree: N` +- Splits model into N stages +- Each stage on different GPU +- Good for very deep models + +### Example Configurations + +#### Small Model (7B), 8 GPUs: +```yaml +parallelism: + data_parallel_shard_degree: 8 # FSDP across all 8 GPUs + tensor_parallel_degree: 1 + pipeline_parallel_degree: 1 +``` + +#### Large Model (70B), 8 GPUs: +```yaml +parallelism: + data_parallel_shard_degree: 4 # FSDP across 4 GPUs + tensor_parallel_degree: 2 # TP across 2 GPUs + pipeline_parallel_degree: 1 +``` + +--- + +## Troubleshooting + +### Issue: Out of Memory (OOM) + +**Solutions:** +1. Reduce batch size: + ```yaml + training: + local_batch_size: 1 + ``` + +2. Reduce sequence length: + ```yaml + training: + seq_len: 1024 # or even 512 + ``` + +3. Enable activation checkpointing: + ```yaml + activation_checkpoint: + mode: selective + ``` + +4. Increase FSDP sharding: + ```yaml + parallelism: + data_parallel_shard_degree: -1 # Use all GPUs + ``` + +### Issue: Training is Slow + +**Check:** +1. Are you using all GPUs? (`processes.procs`) +2. Is dataset loading slow? (try `c4_test` for quick test) +3. Is compile enabled? (can be slow on first run) + +### Issue: Loss is NaN + +**Solutions:** +1. Reduce learning rate: + ```yaml + optimizer: + lr: 1e-6 # Smaller LR + ``` + +2. Increase warmup: + ```yaml + lr_scheduler: + warmup_steps: 500 + ``` + +3. Enable gradient clipping: + ```yaml + training: + max_norm: 1.0 # Already enabled by default + ``` + +### Issue: Can't Import `forge.apps.sft` + +**Solution:** +Make sure you're running from the repo root: +```bash +cd /home/hosseinkh/TorchForge/forge +python -m forge.apps.sft.main --config forge/apps/sft/llama3_8b.yaml +``` + +--- + +## Comparison with GRPO + +| Feature | SFT | GRPO | +|---------|-----|------| +| **Training Type** | Supervised learning | Reinforcement learning | +| **Number of Actors** | 1 type (Trainer) | 7 types (Policy, Trainer, Buffer, etc.) | +| **Complexity** | Simple | Complex | +| **Use Case** | Pre-training, instruction tuning | RL fine-tuning, RLHF | +| **Data** | (input, output) pairs | Prompts + rewards | +| **Architecture** | Single actor | Multi-actor pipeline | + +--- + +## Best Practices + +### 1. Start Small +- Use `c4_test` dataset first +- Run for 10 steps to verify setup +- Then scale up + +### 2. Monitor Memory +- Check GPU memory usage +- Adjust batch size and sequence length accordingly +- Use activation checkpointing if needed + +### 3. Save Regularly +- Set reasonable `checkpoint.interval` (e.g., 500) +- Save initial checkpoint to test loading + +### 4. Use Version Control +- Commit your config files +- Track changes to training parameters +- Document experiments + +### 5. Test Configurations +- Use the interactive notebook first +- Validate YAML before production runs +- Run quick tests (10 steps) before long runs + +--- + +## Additional Resources + +### Documentation Files + +See the `apps/sft_v2/` directory for additional documentation: +- `EVALUATION_GUIDE.md` - How to add evaluation +- `C4_DATASET_EXPLAINED.md` - Dataset details +- `ENDPOINT_DECORATOR_EXPLAINED.md` - Understanding `@endpoint` +- `MULTI_NODE_EXPLAINED.md` - Multi-node training guide +- `GRPO_VS_SFT_COMPARISON.md` - SFT vs GRPO architecture + +### Related Code + +- `forge/src/forge/controller/` - ForgeActor base class +- `forge/src/forge/data/` - Data loading utilities +- `forge/apps/grpo/` - GRPO (RL) training for comparison + +--- + +## Quick Reference + +### Start Training +```bash +python -m forge.apps.sft.main --config forge/apps/sft/llama3_8b.yaml +``` + +### Test Configuration +```bash +# Use notebook +code forge/apps/sft/interactive_config_notebook.ipynb + +# Or quick test with CLI +python -m forge.apps.sft.main --config forge/apps/sft/llama3_8b.yaml \ + --training.steps=10 \ + --training.dataset=c4_test +``` + +### Resume from Checkpoint +```yaml +# In config: +checkpoint: + enable: true + initial_load_path: /path/to/checkpoint/step_500/ +``` + +### Multi-Node Training +```yaml +# In config: +processes: + procs: 32 # 4 nodes × 8 GPUs +``` + +--- + +## Summary + +**SFT provides simple, scalable supervised fine-tuning** with: +- ✅ Interactive notebook for configuration +- ✅ Single-command training launch +- ✅ Multi-node support out of the box +- ✅ FSDP/TP/PP parallelism options +- ✅ Automatic checkpointing +- ✅ Production-ready architecture + +**Get started in 3 steps:** +1. Open `interactive_config_notebook.ipynb` +2. Configure your settings +3. Run `python -m forge.apps.sft.main --config your_config.yaml` + +Happy training! 🚀 diff --git a/apps/sft/actor.py b/apps/sft/actor.py new file mode 100644 index 000000000..8607a39c4 --- /dev/null +++ b/apps/sft/actor.py @@ -0,0 +1,133 @@ +# Copyright (c) Meta Platforms, Inc. and affiliates. +# All rights reserved. +# +# This source code is licensed under the BSD-style license found in the +# LICENSE file in the root directory of this source tree. + +""" +Abstract Actor class for training/inference actors in Forge. + +This provides a base class that can be extended for different types of actors +(e.g., Trainer, Evaluator, Inferencer, etc.) +""" + +import logging +import math +import os +from abc import ABC, abstractmethod +from typing import Any, Optional + +import torch +from forge.controller import ForgeActor +from monarch.actor import current_rank, current_size +from omegaconf import DictConfig, OmegaConf +from torch import nn +from torchtitan.components.loss import LossFunction +from torchtitan.components.lr_scheduler import LRSchedulersContainer +from torchtitan.components.optimizer import OptimizersContainer +from torchtitan.distributed import ParallelDims +from torchtitan.experiments.forge.engine import ForgeEngine +from torchtitan.experiments.forge.job_config import ForgeJobConfig + +Checkpointer = Any +Dataloader = Any +MetricLogger = Any +Profiler = Any +Tokenizer = Any + +logger = logging.getLogger(__name__) +logger.setLevel(logging.INFO) + + +class BaseForgeActor(ForgeActor, ForgeEngine, ABC): + """ + Abstract base class for Forge actors. + + This class handles common initialization, distributed setup, and provides + abstract methods that must be implemented by concrete actor classes. + """ + + job_config: ForgeJobConfig + parallel_dims: ParallelDims + model: list[nn.Module] + loss_fn: Optional[LossFunction] + optimizer: Optional[OptimizersContainer] + lr_scheduler: Optional[LRSchedulersContainer] + checkpointer: Optional[Checkpointer] + tokenizer: Optional[Tokenizer] + metric_logger: Optional[MetricLogger] + profiler: Optional[Profiler] + device: torch.device + + def __init__(self, config: DictConfig): + """ + Initialize the base actor with configuration. + + Args: + config: Configuration dictionary containing job settings + """ + job_config = ForgeJobConfig().to_dict() + job_config = OmegaConf.merge(job_config, config) + + self.current_step = 0 + self.metric_logger = None + self.gradient_accumulation_steps = 1 + self._rank = current_rank().rank + self._size = math.prod(current_size().values()) + + self._init_dist() + super().__init__(job_config) + + def _init_dist(self): + """ + Initialize torch distributed environment. + + Sets up environment variables required for distributed training + in the Monarch actor framework. + """ + env = { + "RANK": str(self._rank), + "LOCAL_RANK": str(self._rank), + "LOCAL_WORLD_SIZE": str(self._size), + "GROUP_RANK": str(self._size), + "GROUP_WORLD_SIZE": str(self._size), + "ROLE_RANK": str(self._rank), + "ROLE_WORLD_SIZE": str(self._size), + "ROLE_NAME": "rank", + "WORLD_SIZE": str(self._size), + "PYTORCH_CUDA_ALLOC_CONF": "expandable_segments:True", + } + os.environ.update(env) + logger.info(f"Initialized distributed environment: {env}") + + @abstractmethod + async def setup(self): + """ + Setup the actor (load data, checkpoint, etc.). + + This method must be implemented by concrete actor classes. + """ + pass + + @abstractmethod + async def run(self): + """ + Main execution logic for the actor. + + This method must be implemented by concrete actor classes. + """ + pass + + @abstractmethod + async def cleanup(self): + """ + Cleanup resources (close checkpointer, logger, etc.). + + This method must be implemented by concrete actor classes. + """ + pass + + @abstractmethod + def __repr__(self) -> str: + """String representation of the actor.""" + pass diff --git a/apps/sft/interactive_config_notebook.ipynb b/apps/sft/interactive_config_notebook.ipynb new file mode 100644 index 000000000..7ac800757 --- /dev/null +++ b/apps/sft/interactive_config_notebook.ipynb @@ -0,0 +1,10336 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# SFT Training - Interactive Configuration Notebook\n", + "\n", + "This notebook allows you to configure and run SFT training **without any YAML files**!\n", + "\n", + "## Benefits\n", + "\n", + "✅ No external YAML files needed \n", + "✅ Interactive configuration in separate cells \n", + "✅ Easy to modify and experiment \n", + "✅ All configuration visible in notebook \n", + "✅ Quick templates for common scenarios" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Step 1: Import Dependencies" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "output": { + "id": 1438699627218568, + "loadingStatus": "loaded" + } + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "✓ Working directory set to: /home/hosseinkh/TorchForge/forge\n", + "✓ Added /home/hosseinkh/TorchForge/forge to sys.path\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/hosseinkh/.conda/envs/forge/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n", + " from .autonotebook import tqdm as notebook_tqdm\n" + ] + } + ], + "source": [ + "import sys\n", + "import os\n", + "from pathlib import Path\n", + "\n", + "# Set working directory to forge root\n", + "repo_root = Path(\"/home/hosseinkh/TorchForge/forge\")\n", + "os.chdir(repo_root)\n", + "print(f\"✓ Working directory set to: {os.getcwd()}\")\n", + "if str(repo_root) not in sys.path:\n", + " sys.path.insert(0, str(repo_root))\n", + " print(f\"✓ Added {repo_root} to sys.path\")\n", + "\n", + "import asyncio\n", + "import logging\n", + "from omegaconf import OmegaConf, DictConfig\n", + "\n", + "from apps.sft.trainer_actor import TrainerActor\n", + "from apps.sft.spawn_actor import SpawnActor, run_actor" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Step 2: Configure Model and Process Settings\n", + "\n", + "Define your model configuration and how many processes to use." + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": { + "output": { + "id": 779738548196921, + "loadingStatus": "loaded" + } + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Model Configuration:\n", + "name: llama3\n", + "flavor: 8B\n", + "hf_assets_path: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/\n", + "\n", + "\n", + "Process Configuration:\n", + "procs: 8\n", + "with_gpus: true\n", + "\n" + ] + } + ], + "source": [ + "# Model Configuration\n", + "model_config = {\n", + " \"name\": \"llama3\",\n", + " \"flavor\": \"8B\",\n", + " \"hf_assets_path\": \"/home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/\"\n", + "}\n", + "\n", + "# Process Configuration\n", + "processes_config = {\n", + " \"procs\": 8, # Number of processes\n", + " \"with_gpus\": True # Use GPUs\n", + "}\n", + "\n", + "print(\"Model Configuration:\")\n", + "print(OmegaConf.to_yaml(OmegaConf.create(model_config)))\n", + "print(\"\\nProcess Configuration:\")\n", + "print(OmegaConf.to_yaml(OmegaConf.create(processes_config)))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Step 3: Configure Optimizer and LR Scheduler" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": { + "output": { + "id": 837311532606040, + "loadingStatus": "loaded" + } + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Optimizer Configuration:\n", + "name: AdamW\n", + "lr: 1.0e-05\n", + "eps: 1.0e-08\n", + "\n", + "\n", + "LR Scheduler Configuration:\n", + "warmup_steps: 200\n", + "\n" + ] + } + ], + "source": [ + "# Optimizer Configuration\n", + "optimizer_config = {\n", + " \"name\": \"AdamW\",\n", + " \"lr\": 1e-5, # Learning rate\n", + " \"eps\": 1e-8\n", + "}\n", + "\n", + "# Learning Rate Scheduler Configuration\n", + "lr_scheduler_config = {\n", + " \"warmup_steps\": 200 # Number of warmup steps\n", + "}\n", + "\n", + "print(\"Optimizer Configuration:\")\n", + "print(OmegaConf.to_yaml(OmegaConf.create(optimizer_config)))\n", + "print(\"\\nLR Scheduler Configuration:\")\n", + "print(OmegaConf.to_yaml(OmegaConf.create(lr_scheduler_config)))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Step 4: Configure Training Settings\n", + "\n", + "**Key parameters to adjust for your experiment:**" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": { + "output": { + "id": 1331479275018407, + "loadingStatus": "loaded" + } + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Training Configuration:\n", + "local_batch_size: 1\n", + "seq_len: 2048\n", + "max_norm: 1.0\n", + "steps: 1000\n", + "compile: false\n", + "dataset: c4\n", + "\n" + ] + } + ], + "source": [ + "training_config = {\n", + " \"local_batch_size\": 1, # Batch size per GPU\n", + " \"seq_len\": 2048, # Sequence length\n", + " \"max_norm\": 1.0, # Gradient clipping\n", + " \"steps\": 1000, # Total training steps\n", + " \"compile\": False, # PyTorch compilation\n", + " \"dataset\": \"c4\" # Dataset name\n", + "}\n", + "\n", + "print(\"Training Configuration:\")\n", + "print(OmegaConf.to_yaml(OmegaConf.create(training_config)))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Step 5: Configure Parallelism Settings" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": { + "output": { + "id": 1346478426919699, + "loadingStatus": "loaded" + } + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Parallelism Configuration:\n", + "data_parallel_replicate_degree: 1\n", + "data_parallel_shard_degree: -1\n", + "tensor_parallel_degree: 1\n", + "pipeline_parallel_degree: 1\n", + "context_parallel_degree: 1\n", + "expert_parallel_degree: 1\n", + "disable_loss_parallel: false\n", + "\n" + ] + } + ], + "source": [ + "parallelism_config = {\n", + " \"data_parallel_replicate_degree\": 1,\n", + " \"data_parallel_shard_degree\": -1, # -1 means use all available GPUs for FSDP\n", + " \"tensor_parallel_degree\": 1,\n", + " \"pipeline_parallel_degree\": 1,\n", + " \"context_parallel_degree\": 1,\n", + " \"expert_parallel_degree\": 1,\n", + " \"disable_loss_parallel\": False\n", + "}\n", + "\n", + "print(\"Parallelism Configuration:\")\n", + "print(OmegaConf.to_yaml(OmegaConf.create(parallelism_config)))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Step 6: Configure Checkpoint and Activation Checkpointing" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": { + "output": { + "id": 1594338181936740, + "loadingStatus": "loaded" + } + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Checkpoint Configuration:\n", + "enable: true\n", + "folder: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/saved_checkpoints\n", + "initial_load_path: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/\n", + "initial_load_in_hf: true\n", + "last_save_in_hf: true\n", + "interval: 500\n", + "async_mode: disabled\n", + "\n", + "\n", + "Activation Checkpoint Configuration:\n", + "mode: selective\n", + "selective_ac_option: op\n", + "\n" + ] + } + ], + "source": [ + "# Checkpoint Configuration\n", + "checkpoint_config = {\n", + " \"enable\": True,\n", + " \"folder\": \"/home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/saved_checkpoints\",\n", + " \"initial_load_path\": \"/home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/\",\n", + " \"initial_load_in_hf\": True,\n", + " \"last_save_in_hf\": True,\n", + " \"interval\": 500, # Save every N steps\n", + " \"async_mode\": \"disabled\"\n", + "}\n", + "\n", + "# Activation Checkpoint Configuration\n", + "activation_checkpoint_config = {\n", + " \"mode\": \"selective\",\n", + " \"selective_ac_option\": \"op\"\n", + "}\n", + "\n", + "print(\"Checkpoint Configuration:\")\n", + "print(OmegaConf.to_yaml(OmegaConf.create(checkpoint_config)))\n", + "print(\"\\nActivation Checkpoint Configuration:\")\n", + "print(OmegaConf.to_yaml(OmegaConf.create(activation_checkpoint_config)))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Step 7: Configure Communication Settings" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": { + "output": { + "id": 1115922440689149, + "loadingStatus": "loaded" + } + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Communication Configuration:\n", + "trace_buf_size: 0\n", + "\n" + ] + } + ], + "source": [ + "# Communication Configuration\n", + "comm_config = {\n", + " \"trace_buf_size\": 0\n", + "}\n", + "\n", + "print(\"Communication Configuration:\")\n", + "print(OmegaConf.to_yaml(OmegaConf.create(comm_config)))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Step 8: Combine All Configurations\n", + "\n", + "Now let's merge everything into a complete configuration!" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": { + "output": { + "id": 890825846616212, + "loadingStatus": "loaded" + } + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "================================================================================\n", + "COMPLETE CONFIGURATION\n", + "================================================================================\n", + "comm:\n", + " trace_buf_size: 0\n", + "model:\n", + " name: llama3\n", + " flavor: 8B\n", + " hf_assets_path: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/\n", + "processes:\n", + " procs: 8\n", + " with_gpus: true\n", + "optimizer:\n", + " name: AdamW\n", + " lr: 1.0e-05\n", + " eps: 1.0e-08\n", + "lr_scheduler:\n", + " warmup_steps: 200\n", + "training:\n", + " local_batch_size: 1\n", + " seq_len: 2048\n", + " max_norm: 1.0\n", + " steps: 1000\n", + " compile: false\n", + " dataset: c4\n", + "parallelism:\n", + " data_parallel_replicate_degree: 1\n", + " data_parallel_shard_degree: -1\n", + " tensor_parallel_degree: 1\n", + " pipeline_parallel_degree: 1\n", + " context_parallel_degree: 1\n", + " expert_parallel_degree: 1\n", + " disable_loss_parallel: false\n", + "checkpoint:\n", + " enable: true\n", + " folder: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/saved_checkpoints\n", + " initial_load_path: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/\n", + " initial_load_in_hf: true\n", + " last_save_in_hf: true\n", + " interval: 500\n", + " async_mode: disabled\n", + "activation_checkpoint:\n", + " mode: selective\n", + " selective_ac_option: op\n", + "\n", + "================================================================================\n" + ] + } + ], + "source": [ + "# Combine all configs\n", + "complete_config = {\n", + " \"comm\": comm_config,\n", + " \"model\": model_config,\n", + " \"processes\": processes_config,\n", + " \"optimizer\": optimizer_config,\n", + " \"lr_scheduler\": lr_scheduler_config,\n", + " \"training\": training_config,\n", + " \"parallelism\": parallelism_config,\n", + " \"checkpoint\": checkpoint_config,\n", + " \"activation_checkpoint\": activation_checkpoint_config\n", + "}\n", + "\n", + "# Create OmegaConf DictConfig\n", + "cfg = OmegaConf.create(complete_config)\n", + "\n", + "print(\"=\" * 80)\n", + "print(\"COMPLETE CONFIGURATION\")\n", + "print(\"=\" * 80)\n", + "print(OmegaConf.to_yaml(cfg))\n", + "print(\"=\" * 80)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Step 9: Run Training\n", + "\n", + "### Option A: Automatic Lifecycle Management (Recommended)\n", + "\n", + "Use `run_actor()` for automatic setup, training, and cleanup:" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# Run training with automatic lifecycle management\n", + "await run_actor(TrainerActor, cfg)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Alternative: Manual Lifecycle Control\n", + "\n", + "For more control, manage each phase separately.\n", + "\n", + "### Create and Spawn the Actor" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": { + "output": { + "id": 813567704706905, + "loadingStatus": "loaded" + } + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "Launcher not provided, remote allocations will not work.\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:23:41 INFO\u001b[0m Building 1-D device mesh with ['dp_shard'], [8]\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:23:41 INFO\u001b[0m Building 1-D device mesh with ['dp_shard'], [8]\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:23:41 INFO\u001b[0m [GC] Initial GC collection took 0.00 seconds\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:23:41 INFO\u001b[0m [GC] Initial GC collection took 0.00 seconds\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:23:41 INFO\u001b[0m Building 1-D device mesh with ['dp_shard'], [8]\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:23:41 INFO\u001b[0m Building 1-D device mesh with ['dp_shard'], [8]\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:23:41 INFO\u001b[0m [GC] Initial GC collection took 0.00 seconds\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:23:41 INFO\u001b[0m [GC] Initial GC collection took 0.00 seconds\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:23:41 INFO\u001b[0m Building 1-D device mesh with ['dp_shard'], [8]\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:23:41 INFO\u001b[0m [GC] Initial GC collection took 0.00 seconds\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:23:41 INFO\u001b[0m Building 1-D device mesh with ['dp_shard'], [8]\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:23:41 INFO\u001b[0m [GC] Initial GC collection took 0.00 seconds\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:23:42 INFO\u001b[0m Building 1-D device mesh with ['dp_shard'], [8]\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:23:42 INFO\u001b[0m [GC] Initial GC collection took 0.00 seconds\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:23:42 INFO\u001b[0m Building 1-D device mesh with ['dp_shard'], [8]\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:23:42 INFO\u001b[0m [GC] Initial GC collection took 0.00 seconds\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:23:47 INFO\u001b[0m Applied selective activation checkpointing to the model\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:23:47 INFO\u001b[0m Applied selective activation checkpointing to the model\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:23:47 INFO\u001b[0m Applied selective activation checkpointing to the model\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:23:47 INFO\u001b[0m Applied selective activation checkpointing to the model\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:23:47 INFO\u001b[0m Applied selective activation checkpointing to the model\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:23:47 INFO\u001b[0m Applied selective activation checkpointing to the model\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:23:47 INFO\u001b[0m Applied selective activation checkpointing to the model\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:23:47 INFO\u001b[0m Applied selective activation checkpointing to the model\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:23:47 INFO\u001b[0m Applied FSDP to the model\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:23:47 INFO\u001b[0m Applied FSDP to the model\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:23:47 INFO\u001b[0m Applied FSDP to the model\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:23:47 INFO\u001b[0m Applied FSDP to the model\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:23:47 INFO\u001b[0m Applied FSDP to the model\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:23:47 INFO\u001b[0m Applied FSDP to the model\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:23:47 INFO\u001b[0m Applied FSDP to the model\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:23:47 INFO\u001b[0m Applied FSDP to the model\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:23:48 INFO\u001b[0m Checkpointing active. Checkpoints will be loaded from and saved to /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/saved_checkpoints\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:23:48 INFO\u001b[0m Mixed precision training is handled by fully_shard\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:23:48 INFO\u001b[0m Setting up trainer actor...\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:23:48 INFO\u001b[0m Loading tokenizer from: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/tokenizer.json\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:23:48 INFO\u001b[0m Loading SFT dataset from: yahma/alpaca-cleaned, split: train\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:23:48 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: eba76a2e-e78d-48cc-85aa-e80d750c2ad6)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:23:48 WARNING\u001b[0m Retrying in 1s [Retry 1/5].\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:23:48 INFO\u001b[0m Checkpointing active. Checkpoints will be loaded from and saved to /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/saved_checkpoints\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:23:48 INFO\u001b[0m Mixed precision training is handled by fully_shard\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:23:48 INFO\u001b[0m Setting up trainer actor...\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:23:48 INFO\u001b[0m Loading tokenizer from: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/tokenizer.json\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[0] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: eba76a2e-e78d-48cc-85aa-e80d750c2ad6)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[0] Retrying in 1s [Retry 1/5].\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:23:48 INFO\u001b[0m Checkpointing active. Checkpoints will be loaded from and saved to /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/saved_checkpoints\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:23:48 INFO\u001b[0m Mixed precision training is handled by fully_shard\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:23:48 INFO\u001b[0m Setting up trainer actor...\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:23:48 INFO\u001b[0m Loading tokenizer from: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/tokenizer.json\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:23:48 INFO\u001b[0m Checkpointing active. Checkpoints will be loaded from and saved to /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/saved_checkpoints\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:23:48 INFO\u001b[0m Mixed precision training is handled by fully_shard\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:23:48 INFO\u001b[0m Checkpointing active. Checkpoints will be loaded from and saved to /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/saved_checkpoints\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:23:48 INFO\u001b[0m Mixed precision training is handled by fully_shard\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:23:48 INFO\u001b[0m Setting up trainer actor...\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:23:48 INFO\u001b[0m Loading tokenizer from: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/tokenizer.json\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:23:48 INFO\u001b[0m Setting up trainer actor...\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:23:48 INFO\u001b[0m Loading tokenizer from: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/tokenizer.json\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:23:48 INFO\u001b[0m Checkpointing active. Checkpoints will be loaded from and saved to /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/saved_checkpoints\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:23:48 INFO\u001b[0m Mixed precision training is handled by fully_shard\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:23:48 INFO\u001b[0m Setting up trainer actor...\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:23:48 INFO\u001b[0m Loading tokenizer from: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/tokenizer.json\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:23:48 INFO\u001b[0m Checkpointing active. Checkpoints will be loaded from and saved to /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/saved_checkpoints\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:23:48 INFO\u001b[0m Mixed precision training is handled by fully_shard\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:23:48 INFO\u001b[0m Setting up trainer actor...\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:23:48 INFO\u001b[0m Loading tokenizer from: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/tokenizer.json\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:23:48 INFO\u001b[0m Checkpointing active. Checkpoints will be loaded from and saved to /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/saved_checkpoints\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:23:48 INFO\u001b[0m Mixed precision training is handled by fully_shard\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:23:48 INFO\u001b[0m Setting up trainer actor...\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:23:48 INFO\u001b[0m Loading tokenizer from: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/tokenizer.json\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:23:48 INFO\u001b[0m Loading SFT dataset from: yahma/alpaca-cleaned, split: train\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:23:48 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 6e440fff-4493-47b6-8f86-c81ab5959618)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:23:48 WARNING\u001b[0m Retrying in 1s [Retry 1/5].\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:23:48 INFO\u001b[0m Loading SFT dataset from: yahma/alpaca-cleaned, split: train\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:23:48 INFO\u001b[0m Loading SFT dataset from: yahma/alpaca-cleaned, split: train\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:23:48 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: c21f381a-004e-40eb-91b2-feb2a511871a)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:23:48 WARNING\u001b[0m Retrying in 1s [Retry 1/5].\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:23:48 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 41bc6047-8598-4c88-be6b-fd7317301eab)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:23:48 WARNING\u001b[0m Retrying in 1s [Retry 1/5].\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:23:48 INFO\u001b[0m Loading SFT dataset from: yahma/alpaca-cleaned, split: train\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:23:48 INFO\u001b[0m Loading SFT dataset from: yahma/alpaca-cleaned, split: train\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:23:48 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: edffb55d-7d7d-4e03-b788-5533613059ee)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:23:48 WARNING\u001b[0m Retrying in 1s [Retry 1/5].\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:23:48 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 2d6cd455-7141-47a6-9082-e48e7eba9f2a)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:23:48 WARNING\u001b[0m Retrying in 1s [Retry 1/5].\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:23:48 INFO\u001b[0m Loading SFT dataset from: yahma/alpaca-cleaned, split: train\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:23:48 INFO\u001b[0m Loading SFT dataset from: yahma/alpaca-cleaned, split: train\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:23:48 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 9ed8f60c-9c36-4c93-8c93-32d93b0a6b49)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:23:48 WARNING\u001b[0m Retrying in 1s [Retry 1/5].\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:23:48 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 18af54b1-0afb-4701-8d3e-353c70880617)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:23:48 WARNING\u001b[0m Retrying in 1s [Retry 1/5].\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[6] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 6e440fff-4493-47b6-8f86-c81ab5959618)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[6] Retrying in 1s [Retry 1/5].\n", + "[3] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: c21f381a-004e-40eb-91b2-feb2a511871a)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[3] Retrying in 1s [Retry 1/5].\n", + "[4] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 41bc6047-8598-4c88-be6b-fd7317301eab)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[4] Retrying in 1s [Retry 1/5].\n", + "[7] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: edffb55d-7d7d-4e03-b788-5533613059ee)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[7] Retrying in 1s [Retry 1/5].\n", + "[5] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 2d6cd455-7141-47a6-9082-e48e7eba9f2a)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[5] Retrying in 1s [Retry 1/5].\n", + "[1] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 9ed8f60c-9c36-4c93-8c93-32d93b0a6b49)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[1] Retrying in 1s [Retry 1/5].\n", + "[2] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 18af54b1-0afb-4701-8d3e-353c70880617)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[2] Retrying in 1s [Retry 1/5].\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[0] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: df9e4f0b-5090-4fa3-a6f3-cf27f88269ac)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[0] Retrying in 2s [Retry 2/5].\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:23:49 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: df9e4f0b-5090-4fa3-a6f3-cf27f88269ac)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:23:49 WARNING\u001b[0m Retrying in 2s [Retry 2/5].\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[6] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 9d2a7186-28d7-4655-937a-aa2a3bdf3fe3)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[6] Retrying in 2s [Retry 2/5].\n", + "[3] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 209a4ad1-3098-4571-8c1e-fc0250ceb63f)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[3] Retrying in 2s [Retry 2/5].\n", + "[4] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: f874834e-7f18-41df-93cb-66739cacbbbc)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[4] Retrying in 2s [Retry 2/5].\n", + "[7] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 61cc04cf-cc37-4ce5-8066-e3721a5bd50e)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[7] Retrying in 2s [Retry 2/5].\n", + "[5] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 093b89a8-0c8c-4c27-b851-8d303398fdf2)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[5] Retrying in 2s [Retry 2/5].\n", + "[1] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 3f4e4872-4c46-4955-a34b-085d02e25952)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[1] Retrying in 2s [Retry 2/5].\n", + "[2] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: ba6b72c3-4bd6-4a26-9191-f7a428c69696)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[2] Retrying in 2s [Retry 2/5].\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:23:49 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 9d2a7186-28d7-4655-937a-aa2a3bdf3fe3)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:23:49 WARNING\u001b[0m Retrying in 2s [Retry 2/5].\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:23:49 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 209a4ad1-3098-4571-8c1e-fc0250ceb63f)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:23:49 WARNING\u001b[0m Retrying in 2s [Retry 2/5].\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:23:49 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: f874834e-7f18-41df-93cb-66739cacbbbc)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:23:49 WARNING\u001b[0m Retrying in 2s [Retry 2/5].\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:23:49 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 61cc04cf-cc37-4ce5-8066-e3721a5bd50e)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:23:49 WARNING\u001b[0m Retrying in 2s [Retry 2/5].\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:23:49 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 093b89a8-0c8c-4c27-b851-8d303398fdf2)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:23:49 WARNING\u001b[0m Retrying in 2s [Retry 2/5].\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:23:49 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 3f4e4872-4c46-4955-a34b-085d02e25952)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:23:49 WARNING\u001b[0m Retrying in 2s [Retry 2/5].\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:23:49 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: ba6b72c3-4bd6-4a26-9191-f7a428c69696)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:23:49 WARNING\u001b[0m Retrying in 2s [Retry 2/5].\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[0] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: b0d87ae8-44e9-49ec-b65b-5134f4608033)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[0] Retrying in 4s [Retry 3/5].\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:23:51 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: b0d87ae8-44e9-49ec-b65b-5134f4608033)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:23:51 WARNING\u001b[0m Retrying in 4s [Retry 3/5].\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[6] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: ae91b891-2fb8-4086-8d84-65adffdb3792)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[6] Retrying in 4s [Retry 3/5].\n", + "[3] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 85974e4a-0082-439f-b131-0e823d0d5d4b)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[3] Retrying in 4s [Retry 3/5].\n", + "[4] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 5deab86a-d38c-4785-9bc2-655bca15c461)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[4] Retrying in 4s [Retry 3/5].\n", + "[7] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 76f1fd4c-0fad-4026-8243-14533f67b820)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[7] Retrying in 4s [Retry 3/5].\n", + "[5] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 15e6d88b-59b6-44b5-ab55-9fbea201e180)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[5] Retrying in 4s [Retry 3/5].\n", + "[1] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: ab0d2c8c-d72b-4a0a-9979-8d964e09c854)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[1] Retrying in 4s [Retry 3/5].\n", + "[2] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 41a63c5b-09e2-486a-a036-b7cb91fb433e)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[2] Retrying in 4s [Retry 3/5].\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:23:51 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: ae91b891-2fb8-4086-8d84-65adffdb3792)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:23:51 WARNING\u001b[0m Retrying in 4s [Retry 3/5].\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:23:51 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 85974e4a-0082-439f-b131-0e823d0d5d4b)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:23:51 WARNING\u001b[0m Retrying in 4s [Retry 3/5].\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:23:51 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 5deab86a-d38c-4785-9bc2-655bca15c461)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:23:51 WARNING\u001b[0m Retrying in 4s [Retry 3/5].\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:23:51 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 76f1fd4c-0fad-4026-8243-14533f67b820)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:23:51 WARNING\u001b[0m Retrying in 4s [Retry 3/5].\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:23:51 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 15e6d88b-59b6-44b5-ab55-9fbea201e180)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:23:51 WARNING\u001b[0m Retrying in 4s [Retry 3/5].\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:23:51 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: ab0d2c8c-d72b-4a0a-9979-8d964e09c854)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:23:51 WARNING\u001b[0m Retrying in 4s [Retry 3/5].\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:23:51 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 41a63c5b-09e2-486a-a036-b7cb91fb433e)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:23:51 WARNING\u001b[0m Retrying in 4s [Retry 3/5].\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:23:55 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 5d0cfdbc-97d3-4c49-8469-a3124102e42e)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:23:55 WARNING\u001b[0m Retrying in 8s [Retry 4/5].\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[0] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 5d0cfdbc-97d3-4c49-8469-a3124102e42e)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[0] Retrying in 8s [Retry 4/5].\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:23:55 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 76d94b86-f93e-483a-b32c-ce8d63e41edd)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:23:55 WARNING\u001b[0m Retrying in 8s [Retry 4/5].\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:23:55 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: b96d9f58-1023-43ec-a3e2-417bf11ce56b)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:23:55 WARNING\u001b[0m Retrying in 8s [Retry 4/5].\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:23:55 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: d6bee3f4-4642-46da-a082-c08a701da491)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:23:55 WARNING\u001b[0m Retrying in 8s [Retry 4/5].\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:23:55 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: bb7a222b-7e55-48c3-9165-dd0daacdcf6e)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:23:55 WARNING\u001b[0m Retrying in 8s [Retry 4/5].\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:23:55 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 3dd29629-07e9-4095-b7d4-9b3f96acb2bd)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:23:55 WARNING\u001b[0m Retrying in 8s [Retry 4/5].\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:23:55 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 865d9aab-e086-4550-ba54-ef68e2fd1343)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:23:55 WARNING\u001b[0m Retrying in 8s [Retry 4/5].\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:23:55 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: e2c71598-619e-4ec1-a7ff-d7b67b87a810)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:23:55 WARNING\u001b[0m Retrying in 8s [Retry 4/5].\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[6] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 76d94b86-f93e-483a-b32c-ce8d63e41edd)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[6] Retrying in 8s [Retry 4/5].\n", + "[3] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: b96d9f58-1023-43ec-a3e2-417bf11ce56b)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[4] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: d6bee3f4-4642-46da-a082-c08a701da491)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[4] Retrying in 8s [Retry 4/5].\n", + "[3] Retrying in 8s [Retry 4/5].\n", + "[7] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: bb7a222b-7e55-48c3-9165-dd0daacdcf6e)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[7] Retrying in 8s [Retry 4/5].\n", + "[5] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 3dd29629-07e9-4095-b7d4-9b3f96acb2bd)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[5] Retrying in 8s [Retry 4/5].\n", + "[1] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 865d9aab-e086-4550-ba54-ef68e2fd1343)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[1] Retrying in 8s [Retry 4/5].\n", + "[2] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: e2c71598-619e-4ec1-a7ff-d7b67b87a810)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[2] Retrying in 8s [Retry 4/5].\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[0] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: bc7a77d0-9aa7-419b-8b95-1c68a51ec7cd)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[0] Retrying in 8s [Retry 5/5].\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:24:03 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: bc7a77d0-9aa7-419b-8b95-1c68a51ec7cd)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:24:03 WARNING\u001b[0m Retrying in 8s [Retry 5/5].\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[6] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 96e6c0be-ea93-4907-81b1-569b41268798)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[6] Retrying in 8s [Retry 5/5].\n", + "[4] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 8fa2cf10-66cd-4316-b096-e16fc28cb007)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[4] Retrying in 8s [Retry 5/5].\n", + "[3] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 64323fb3-1a58-4392-b2b3-93b92d5b9e36)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[3] Retrying in 8s [Retry 5/5].\n", + "[7] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 9194cf6a-571a-4b8a-acae-f9415de036ca)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[7] Retrying in 8s [Retry 5/5].\n", + "[5] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 6946fa1f-b34f-49e3-a8d3-90b3a7c83909)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[5] Retrying in 8s [Retry 5/5].\n", + "[2] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: be05fc99-0c5f-40a9-bcd0-f1ad3ec28a69)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[2] Retrying in 8s [Retry 5/5].\n", + "[1] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: a79f05aa-0ff4-4062-b701-b7a28ec17799)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[1] Retrying in 8s [Retry 5/5].\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:24:03 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 96e6c0be-ea93-4907-81b1-569b41268798)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:24:03 WARNING\u001b[0m Retrying in 8s [Retry 5/5].\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:24:03 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 8fa2cf10-66cd-4316-b096-e16fc28cb007)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:24:03 WARNING\u001b[0m Retrying in 8s [Retry 5/5].\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:24:03 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 64323fb3-1a58-4392-b2b3-93b92d5b9e36)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:24:03 WARNING\u001b[0m Retrying in 8s [Retry 5/5].\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:24:03 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 9194cf6a-571a-4b8a-acae-f9415de036ca)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:24:03 WARNING\u001b[0m Retrying in 8s [Retry 5/5].\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:24:03 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 6946fa1f-b34f-49e3-a8d3-90b3a7c83909)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:24:03 WARNING\u001b[0m Retrying in 8s [Retry 5/5].\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:24:03 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: be05fc99-0c5f-40a9-bcd0-f1ad3ec28a69)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:24:03 WARNING\u001b[0m Retrying in 8s [Retry 5/5].\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:24:03 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: a79f05aa-0ff4-4062-b701-b7a28ec17799)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:24:03 WARNING\u001b[0m Retrying in 8s [Retry 5/5].\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[0] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 9eb97d8d-ce27-473b-a87c-225b2624ae67)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[0] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: f0a18d65-989f-4a2b-972e-0b5f3d1bae35)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[0] Retrying in 1s [Retry 1/5].\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:24:11 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 9eb97d8d-ce27-473b-a87c-225b2624ae67)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:24:11 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: f0a18d65-989f-4a2b-972e-0b5f3d1bae35)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:24:11 WARNING\u001b[0m Retrying in 1s [Retry 1/5].\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[6] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: f404c99f-fb3c-4a91-9174-765dfab1447d)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[6] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 04bfc3bd-8c31-4761-9c45-f55696a44373)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[6] Retrying in 1s [Retry 1/5].\n", + "[4] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 9a8caafd-2e9e-4bdd-b414-8be25d5756fa)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[3] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 1dac8ea0-61e1-4362-bd0c-c5c27a01b0a2)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[4] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 7b09410b-3c5c-4263-b409-2d565b594288)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[4] Retrying in 1s [Retry 1/5].\n", + "[7] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 0f3ef442-1151-4b71-bfba-0af4eb79ff12)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[3] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: df1f1c7e-4c88-4aea-b4a2-0d4ce42a0b5f)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[3] Retrying in 1s [Retry 1/5].\n", + "[7] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 424806bf-2913-4372-99c9-5861fc988312)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[7] Retrying in 1s [Retry 1/5].\n", + "[5] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: b4218c4d-1c3c-47aa-b471-58be1b45914c)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[2] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: e1878e1e-bd4f-4b16-8296-528fcb31cf09)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[1] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 78abe56d-b7f3-4aad-b00d-ab1f0c7f91e8)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[5] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: c15489da-1d25-4133-a6d8-d5f231919eae)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[5] Retrying in 1s [Retry 1/5].\n", + "[2] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 40753c16-77d0-4b9b-afe5-d7e1ea1defaa)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[2] Retrying in 1s [Retry 1/5].\n", + "[1] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: fab7afc0-be85-4293-8e60-fd52db64df37)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[1] Retrying in 1s [Retry 1/5].\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:24:11 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: f404c99f-fb3c-4a91-9174-765dfab1447d)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:24:11 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 04bfc3bd-8c31-4761-9c45-f55696a44373)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:24:11 WARNING\u001b[0m Retrying in 1s [Retry 1/5].\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:24:11 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 9a8caafd-2e9e-4bdd-b414-8be25d5756fa)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:24:11 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 1dac8ea0-61e1-4362-bd0c-c5c27a01b0a2)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:24:11 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 7b09410b-3c5c-4263-b409-2d565b594288)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:24:11 WARNING\u001b[0m Retrying in 1s [Retry 1/5].\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:24:11 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 0f3ef442-1151-4b71-bfba-0af4eb79ff12)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:24:11 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: df1f1c7e-4c88-4aea-b4a2-0d4ce42a0b5f)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:24:11 WARNING\u001b[0m Retrying in 1s [Retry 1/5].\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:24:11 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 424806bf-2913-4372-99c9-5861fc988312)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:24:11 WARNING\u001b[0m Retrying in 1s [Retry 1/5].\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:24:11 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: b4218c4d-1c3c-47aa-b471-58be1b45914c)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:24:11 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: e1878e1e-bd4f-4b16-8296-528fcb31cf09)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:24:11 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 78abe56d-b7f3-4aad-b00d-ab1f0c7f91e8)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:24:12 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: c15489da-1d25-4133-a6d8-d5f231919eae)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:24:12 WARNING\u001b[0m Retrying in 1s [Retry 1/5].\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:24:12 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 40753c16-77d0-4b9b-afe5-d7e1ea1defaa)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:24:12 WARNING\u001b[0m Retrying in 1s [Retry 1/5].\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:24:12 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: fab7afc0-be85-4293-8e60-fd52db64df37)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:24:12 WARNING\u001b[0m Retrying in 1s [Retry 1/5].\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[0] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: b5bcc0bc-86ec-4e1a-b03c-809248c83186)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[0] Retrying in 2s [Retry 2/5].\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:24:12 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: b5bcc0bc-86ec-4e1a-b03c-809248c83186)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:24:12 WARNING\u001b[0m Retrying in 2s [Retry 2/5].\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[6] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 58ad501a-a11f-4f13-a93e-23a6cd7a4153)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[6] Retrying in 2s [Retry 2/5].\n", + "[4] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 79388dfe-d545-459d-92bc-2ac43550b01d)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[4] Retrying in 2s [Retry 2/5].\n", + "[3] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 17689a66-403b-48ae-9fd7-f985b4864413)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[3] Retrying in 2s [Retry 2/5].\n", + "[7] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: e228c017-819b-454c-916c-7fe6afd50d6b)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[7] Retrying in 2s [Retry 2/5].\n", + "[5] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 0c4254d9-5692-4b6b-b7f8-be193b7d5e10)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[5] Retrying in 2s [Retry 2/5].\n", + "[2] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: dff930ed-a36b-4fa5-aba4-2d7f8f33559b)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[2] Retrying in 2s [Retry 2/5].\n", + "[1] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 61412471-3f59-4184-bf80-5eaa4399a722)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[1] Retrying in 2s [Retry 2/5].\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:24:12 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 58ad501a-a11f-4f13-a93e-23a6cd7a4153)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:24:12 WARNING\u001b[0m Retrying in 2s [Retry 2/5].\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:24:12 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 79388dfe-d545-459d-92bc-2ac43550b01d)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:24:12 WARNING\u001b[0m Retrying in 2s [Retry 2/5].\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:24:12 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 17689a66-403b-48ae-9fd7-f985b4864413)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:24:12 WARNING\u001b[0m Retrying in 2s [Retry 2/5].\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:24:12 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: e228c017-819b-454c-916c-7fe6afd50d6b)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:24:12 WARNING\u001b[0m Retrying in 2s [Retry 2/5].\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:24:13 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: dff930ed-a36b-4fa5-aba4-2d7f8f33559b)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:24:13 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 0c4254d9-5692-4b6b-b7f8-be193b7d5e10)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:24:13 WARNING\u001b[0m Retrying in 2s [Retry 2/5].\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:24:13 WARNING\u001b[0m Retrying in 2s [Retry 2/5].\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:24:13 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 61412471-3f59-4184-bf80-5eaa4399a722)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:24:13 WARNING\u001b[0m Retrying in 2s [Retry 2/5].\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[0] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 27cff387-a160-4378-87b7-ff9025ac4454)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[0] Retrying in 4s [Retry 3/5].\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:24:14 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 27cff387-a160-4378-87b7-ff9025ac4454)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:24:14 WARNING\u001b[0m Retrying in 4s [Retry 3/5].\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[6] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 0d3c3990-de47-4355-9bf2-c738747f9360)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[6] Retrying in 4s [Retry 3/5].\n", + "[4] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 4bbd8e17-3a62-4d3f-a650-a5ddc9d684b8)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[4] Retrying in 4s [Retry 3/5].\n", + "[3] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 887734f7-9720-4e51-acb8-7172193cce74)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[3] Retrying in 4s [Retry 3/5].\n", + "[7] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 41355287-3565-4f7d-897f-ca7000aa4691)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[7] Retrying in 4s [Retry 3/5].\n", + "[5] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: f2c39634-e8f8-4ea0-b319-3f64e0e7a467)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[2] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 1eb1a269-e0a0-4e15-b44c-9f27cb14e384)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[5] Retrying in 4s [Retry 3/5].\n", + "[2] Retrying in 4s [Retry 3/5].\n", + "[1] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 25fe07e9-f1d2-4973-9371-139e57a1790b)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[1] Retrying in 4s [Retry 3/5].\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:24:14 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 0d3c3990-de47-4355-9bf2-c738747f9360)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:24:14 WARNING\u001b[0m Retrying in 4s [Retry 3/5].\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:24:14 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 4bbd8e17-3a62-4d3f-a650-a5ddc9d684b8)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:24:14 WARNING\u001b[0m Retrying in 4s [Retry 3/5].\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:24:14 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 887734f7-9720-4e51-acb8-7172193cce74)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:24:14 WARNING\u001b[0m Retrying in 4s [Retry 3/5].\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:24:14 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 41355287-3565-4f7d-897f-ca7000aa4691)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:24:14 WARNING\u001b[0m Retrying in 4s [Retry 3/5].\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:24:15 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: f2c39634-e8f8-4ea0-b319-3f64e0e7a467)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:24:15 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 1eb1a269-e0a0-4e15-b44c-9f27cb14e384)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:24:15 WARNING\u001b[0m Retrying in 4s [Retry 3/5].\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:24:15 WARNING\u001b[0m Retrying in 4s [Retry 3/5].\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:24:15 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 25fe07e9-f1d2-4973-9371-139e57a1790b)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:24:15 WARNING\u001b[0m Retrying in 4s [Retry 3/5].\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[0] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 5096989b-0c0f-4973-85c1-f9a3a06347bc)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[0] Retrying in 8s [Retry 4/5].\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:24:18 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 5096989b-0c0f-4973-85c1-f9a3a06347bc)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:24:18 WARNING\u001b[0m Retrying in 8s [Retry 4/5].\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[6] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: cc62c981-e421-4ea7-9e2a-2892f536c47b)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[6] Retrying in 8s [Retry 4/5].\n", + "[4] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 2e8ffc61-25c6-44c0-bd27-e3fb38569517)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[4] Retrying in 8s [Retry 4/5].\n", + "[3] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 69b31204-2274-45a0-9f3a-58e68b452940)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[3] Retrying in 8s [Retry 4/5].\n", + "[7] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 8f7b01f1-65de-4eac-835d-000a38b47a99)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[7] Retrying in 8s [Retry 4/5].\n", + "[5] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: f1007b8c-09ab-40e1-9932-14836cca35f6)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[5] Retrying in 8s [Retry 4/5].\n", + "[2] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: e4bc2777-ee64-41d2-9b63-655d7cad647a)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[2] Retrying in 8s [Retry 4/5].\n", + "[1] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 396fc594-c3b9-47e8-bc1a-9c0e727002ad)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[1] Retrying in 8s [Retry 4/5].\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:24:18 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: cc62c981-e421-4ea7-9e2a-2892f536c47b)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:24:18 WARNING\u001b[0m Retrying in 8s [Retry 4/5].\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:24:18 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 2e8ffc61-25c6-44c0-bd27-e3fb38569517)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:24:18 WARNING\u001b[0m Retrying in 8s [Retry 4/5].\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:24:19 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 69b31204-2274-45a0-9f3a-58e68b452940)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:24:19 WARNING\u001b[0m Retrying in 8s [Retry 4/5].\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:24:19 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 8f7b01f1-65de-4eac-835d-000a38b47a99)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:24:19 WARNING\u001b[0m Retrying in 8s [Retry 4/5].\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:24:19 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: f1007b8c-09ab-40e1-9932-14836cca35f6)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:24:19 WARNING\u001b[0m Retrying in 8s [Retry 4/5].\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:24:19 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: e4bc2777-ee64-41d2-9b63-655d7cad647a)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:24:19 WARNING\u001b[0m Retrying in 8s [Retry 4/5].\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:24:19 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 396fc594-c3b9-47e8-bc1a-9c0e727002ad)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:24:19 WARNING\u001b[0m Retrying in 8s [Retry 4/5].\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[0] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 5d8c4e31-6394-4d7e-85d2-ea61788672b3)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[0] Retrying in 8s [Retry 5/5].\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:24:26 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 5d8c4e31-6394-4d7e-85d2-ea61788672b3)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:24:26 WARNING\u001b[0m Retrying in 8s [Retry 5/5].\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[6] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 1c1af391-81d4-4496-90b9-1a719e334b5e)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[6] Retrying in 8s [Retry 5/5].\n", + "[4] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 177525aa-65a5-40e2-9221-5e898de7a7aa)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[4] Retrying in 8s [Retry 5/5].\n", + "[3] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: b417c5c5-98c4-490e-996a-44b8d0e7ddca)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[3] Retrying in 8s [Retry 5/5].\n", + "[7] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: a844eaf8-c582-4bf8-bdc9-0ee0a83e224c)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[7] Retrying in 8s [Retry 5/5].\n", + "[5] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 73210ecf-4251-4530-a59a-6abf02f0bb3d)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[5] Retrying in 8s [Retry 5/5].\n", + "[2] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: c4a7749a-07f8-4343-80b5-779717b40839)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[2] Retrying in 8s [Retry 5/5].\n", + "[1] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 648d8b5d-16e1-4c7d-b6d8-a92729422997)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[1] Retrying in 8s [Retry 5/5].\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:24:26 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 1c1af391-81d4-4496-90b9-1a719e334b5e)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:24:26 WARNING\u001b[0m Retrying in 8s [Retry 5/5].\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:24:27 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 177525aa-65a5-40e2-9221-5e898de7a7aa)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:24:27 WARNING\u001b[0m Retrying in 8s [Retry 5/5].\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:24:27 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: b417c5c5-98c4-490e-996a-44b8d0e7ddca)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:24:27 WARNING\u001b[0m Retrying in 8s [Retry 5/5].\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:24:27 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: a844eaf8-c582-4bf8-bdc9-0ee0a83e224c)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:24:27 WARNING\u001b[0m Retrying in 8s [Retry 5/5].\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:24:27 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 73210ecf-4251-4530-a59a-6abf02f0bb3d)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:24:27 WARNING\u001b[0m Retrying in 8s [Retry 5/5].\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:24:27 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: c4a7749a-07f8-4343-80b5-779717b40839)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:24:27 WARNING\u001b[0m Retrying in 8s [Retry 5/5].\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:24:27 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 648d8b5d-16e1-4c7d-b6d8-a92729422997)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:24:27 WARNING\u001b[0m Retrying in 8s [Retry 5/5].\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[0] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: b3037391-e500-4f87-936a-9f75ec08cd5b)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[0] Using the latest cached version of the dataset since yahma/alpaca-cleaned couldn't be found on the Hugging Face Hub\n", + "[0] Found the latest cached dataset configuration 'default' at /home/hosseinkh/.cache/huggingface/datasets/yahma___alpaca-cleaned/default/0.0.0/12567cabf869d7c92e573c7c783905fc160e9639 (last modified on Tue Sep 16 13:36:00 2025).\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:24:34 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: b3037391-e500-4f87-936a-9f75ec08cd5b)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:24:34 WARNING\u001b[0m Using the latest cached version of the dataset since yahma/alpaca-cleaned couldn't be found on the Hugging Face Hub\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:24:34 WARNING\u001b[0m Found the latest cached dataset configuration 'default' at /home/hosseinkh/.cache/huggingface/datasets/yahma___alpaca-cleaned/default/0.0.0/12567cabf869d7c92e573c7c783905fc160e9639 (last modified on Tue Sep 16 13:36:00 2025).\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:24:34 INFO\u001b[0m Created dataloader with batch_size=1, target_tokens=2048\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:24:34 INFO\u001b[0m Loading checkpoint...\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:24:34 INFO\u001b[0m loading from HF safetensors from --checkpoint.initial_load_path: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:24:34 INFO\u001b[0m Loading the checkpoint from /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/.\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:24:35 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 9afd0cdd-f626-4773-8849-1b92ba3ec5a5)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:24:35 WARNING\u001b[0m Using the latest cached version of the dataset since yahma/alpaca-cleaned couldn't be found on the Hugging Face Hub\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:24:35 WARNING\u001b[0m Found the latest cached dataset configuration 'default' at /home/hosseinkh/.cache/huggingface/datasets/yahma___alpaca-cleaned/default/0.0.0/12567cabf869d7c92e573c7c783905fc160e9639 (last modified on Tue Sep 16 13:36:00 2025).\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:24:35 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 4447e501-7be2-43f4-ad1e-eeb5853bc643)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:24:35 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 85090fe5-531f-423a-ba23-bb6b1a662b73)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:24:35 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 9fca1b84-1eaf-4828-b73b-69aed61b1857)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:24:35 WARNING\u001b[0m Using the latest cached version of the dataset since yahma/alpaca-cleaned couldn't be found on the Hugging Face Hub\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:24:35 WARNING\u001b[0m Using the latest cached version of the dataset since yahma/alpaca-cleaned couldn't be found on the Hugging Face Hub\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:24:35 WARNING\u001b[0m Found the latest cached dataset configuration 'default' at /home/hosseinkh/.cache/huggingface/datasets/yahma___alpaca-cleaned/default/0.0.0/12567cabf869d7c92e573c7c783905fc160e9639 (last modified on Tue Sep 16 13:36:00 2025).\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:24:35 WARNING\u001b[0m Found the latest cached dataset configuration 'default' at /home/hosseinkh/.cache/huggingface/datasets/yahma___alpaca-cleaned/default/0.0.0/12567cabf869d7c92e573c7c783905fc160e9639 (last modified on Tue Sep 16 13:36:00 2025).\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:24:35 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 99d27955-32eb-417b-99c5-3415808c1e7f)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:24:35 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 4e3fbfe5-2905-4061-8f54-6658679f754b)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:24:35 WARNING\u001b[0m Using the latest cached version of the dataset since yahma/alpaca-cleaned couldn't be found on the Hugging Face Hub\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:24:35 WARNING\u001b[0m Found the latest cached dataset configuration 'default' at /home/hosseinkh/.cache/huggingface/datasets/yahma___alpaca-cleaned/default/0.0.0/12567cabf869d7c92e573c7c783905fc160e9639 (last modified on Tue Sep 16 13:36:00 2025).\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:24:35 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 9e3657ad-a664-4a23-b0e9-423f8ed1ff27)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:24:35 WARNING\u001b[0m Using the latest cached version of the dataset since yahma/alpaca-cleaned couldn't be found on the Hugging Face Hub\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:24:35 WARNING\u001b[0m Found the latest cached dataset configuration 'default' at /home/hosseinkh/.cache/huggingface/datasets/yahma___alpaca-cleaned/default/0.0.0/12567cabf869d7c92e573c7c783905fc160e9639 (last modified on Tue Sep 16 13:36:00 2025).\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:24:35 WARNING\u001b[0m Using the latest cached version of the dataset since yahma/alpaca-cleaned couldn't be found on the Hugging Face Hub\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:24:35 WARNING\u001b[0m Found the latest cached dataset configuration 'default' at /home/hosseinkh/.cache/huggingface/datasets/yahma___alpaca-cleaned/default/0.0.0/12567cabf869d7c92e573c7c783905fc160e9639 (last modified on Tue Sep 16 13:36:00 2025).\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:24:35 WARNING\u001b[0m Using the latest cached version of the dataset since yahma/alpaca-cleaned couldn't be found on the Hugging Face Hub\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:24:35 WARNING\u001b[0m Found the latest cached dataset configuration 'default' at /home/hosseinkh/.cache/huggingface/datasets/yahma___alpaca-cleaned/default/0.0.0/12567cabf869d7c92e573c7c783905fc160e9639 (last modified on Tue Sep 16 13:36:00 2025).\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[6] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 9afd0cdd-f626-4773-8849-1b92ba3ec5a5)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[6] Using the latest cached version of the dataset since yahma/alpaca-cleaned couldn't be found on the Hugging Face Hub\n", + "[6] Found the latest cached dataset configuration 'default' at /home/hosseinkh/.cache/huggingface/datasets/yahma___alpaca-cleaned/default/0.0.0/12567cabf869d7c92e573c7c783905fc160e9639 (last modified on Tue Sep 16 13:36:00 2025).\n", + "[4] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 4447e501-7be2-43f4-ad1e-eeb5853bc643)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[3] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 85090fe5-531f-423a-ba23-bb6b1a662b73)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[7] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 9fca1b84-1eaf-4828-b73b-69aed61b1857)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[3] Using the latest cached version of the dataset since yahma/alpaca-cleaned couldn't be found on the Hugging Face Hub\n", + "[4] Using the latest cached version of the dataset since yahma/alpaca-cleaned couldn't be found on the Hugging Face Hub\n", + "[3] Found the latest cached dataset configuration 'default' at /home/hosseinkh/.cache/huggingface/datasets/yahma___alpaca-cleaned/default/0.0.0/12567cabf869d7c92e573c7c783905fc160e9639 (last modified on Tue Sep 16 13:36:00 2025).\n", + "[4] Found the latest cached dataset configuration 'default' at /home/hosseinkh/.cache/huggingface/datasets/yahma___alpaca-cleaned/default/0.0.0/12567cabf869d7c92e573c7c783905fc160e9639 (last modified on Tue Sep 16 13:36:00 2025).\n", + "[2] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 99d27955-32eb-417b-99c5-3415808c1e7f)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[5] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 4e3fbfe5-2905-4061-8f54-6658679f754b)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[7] Using the latest cached version of the dataset since yahma/alpaca-cleaned couldn't be found on the Hugging Face Hub\n", + "[7] Found the latest cached dataset configuration 'default' at /home/hosseinkh/.cache/huggingface/datasets/yahma___alpaca-cleaned/default/0.0.0/12567cabf869d7c92e573c7c783905fc160e9639 (last modified on Tue Sep 16 13:36:00 2025).\n", + "[1] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 9e3657ad-a664-4a23-b0e9-423f8ed1ff27)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[2] Using the latest cached version of the dataset since yahma/alpaca-cleaned couldn't be found on the Hugging Face Hub\n", + "[2] Found the latest cached dataset configuration 'default' at /home/hosseinkh/.cache/huggingface/datasets/yahma___alpaca-cleaned/default/0.0.0/12567cabf869d7c92e573c7c783905fc160e9639 (last modified on Tue Sep 16 13:36:00 2025).\n", + "[5] Using the latest cached version of the dataset since yahma/alpaca-cleaned couldn't be found on the Hugging Face Hub\n", + "[5] Found the latest cached dataset configuration 'default' at /home/hosseinkh/.cache/huggingface/datasets/yahma___alpaca-cleaned/default/0.0.0/12567cabf869d7c92e573c7c783905fc160e9639 (last modified on Tue Sep 16 13:36:00 2025).\n", + "[1] Using the latest cached version of the dataset since yahma/alpaca-cleaned couldn't be found on the Hugging Face Hub\n", + "[1] Found the latest cached dataset configuration 'default' at /home/hosseinkh/.cache/huggingface/datasets/yahma___alpaca-cleaned/default/0.0.0/12567cabf869d7c92e573c7c783905fc160e9639 (last modified on Tue Sep 16 13:36:00 2025).\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:24:35 INFO\u001b[0m Created dataloader with batch_size=1, target_tokens=2048\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:24:35 INFO\u001b[0m Loading checkpoint...\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:24:35 INFO\u001b[0m loading from HF safetensors from --checkpoint.initial_load_path: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:24:35 INFO\u001b[0m Loading the checkpoint from /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/.\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:24:35 INFO\u001b[0m Created dataloader with batch_size=1, target_tokens=2048\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:24:35 INFO\u001b[0m Loading checkpoint...\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:24:35 INFO\u001b[0m loading from HF safetensors from --checkpoint.initial_load_path: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:24:35 INFO\u001b[0m Loading the checkpoint from /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/.\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:24:35 INFO\u001b[0m Created dataloader with batch_size=1, target_tokens=2048\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:24:35 INFO\u001b[0m Loading checkpoint...\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:24:35 INFO\u001b[0m loading from HF safetensors from --checkpoint.initial_load_path: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:24:35 INFO\u001b[0m Loading the checkpoint from /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/.\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:24:35 INFO\u001b[0m Created dataloader with batch_size=1, target_tokens=2048\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:24:35 INFO\u001b[0m Loading checkpoint...\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:24:35 INFO\u001b[0m loading from HF safetensors from --checkpoint.initial_load_path: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:24:35 INFO\u001b[0m Loading the checkpoint from /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/.\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:24:35 INFO\u001b[0m Created dataloader with batch_size=1, target_tokens=2048\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:24:35 INFO\u001b[0m Loading checkpoint...\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:24:35 INFO\u001b[0m loading from HF safetensors from --checkpoint.initial_load_path: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:24:35 INFO\u001b[0m Loading the checkpoint from /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/.\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:24:35 INFO\u001b[0m Created dataloader with batch_size=1, target_tokens=2048\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:24:35 INFO\u001b[0m Loading checkpoint...\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:24:35 INFO\u001b[0m loading from HF safetensors from --checkpoint.initial_load_path: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:24:35 INFO\u001b[0m Loading the checkpoint from /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/.\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:24:35 INFO\u001b[0m Created dataloader with batch_size=1, target_tokens=2048\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:24:35 INFO\u001b[0m Loading checkpoint...\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:24:35 INFO\u001b[0m loading from HF safetensors from --checkpoint.initial_load_path: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:24:35 INFO\u001b[0m Loading the checkpoint from /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/.\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:25:15 INFO\u001b[0m [GC] GC collection for checkpoint loading. took 0.10 seconds\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:25:15 INFO\u001b[0m Finished loading the checkpoint in 39.81 seconds.\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:25:15 INFO\u001b[0m Trainer setup complete.\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:25:15 INFO\u001b[0m [GC] GC collection for checkpoint loading. took 0.10 seconds\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:25:15 INFO\u001b[0m Finished loading the checkpoint in 39.72 seconds.\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:25:15 INFO\u001b[0m Trainer setup complete.\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:25:15 INFO\u001b[0m [GC] GC collection for checkpoint loading. took 0.11 seconds\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:25:15 INFO\u001b[0m Finished loading the checkpoint in 40.36 seconds.\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:25:15 INFO\u001b[0m [GC] GC collection for checkpoint loading. took 0.11 seconds\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:25:15 INFO\u001b[0m Finished loading the checkpoint in 39.75 seconds.\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:25:15 INFO\u001b[0m Trainer setup complete.\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:25:15 INFO\u001b[0m Trainer setup complete.\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:25:15 INFO\u001b[0m [GC] GC collection for checkpoint loading. took 0.12 seconds\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:25:15 INFO\u001b[0m Finished loading the checkpoint in 39.72 seconds.\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:25:15 INFO\u001b[0m Trainer setup complete.\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:25:15 INFO\u001b[0m [GC] GC collection for checkpoint loading. took 0.13 seconds\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:25:15 INFO\u001b[0m Finished loading the checkpoint in 39.77 seconds.\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:25:15 INFO\u001b[0m Trainer setup complete.\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:25:15 INFO\u001b[0m [GC] GC collection for checkpoint loading. took 0.14 seconds\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:25:15 INFO\u001b[0m Finished loading the checkpoint in 39.83 seconds.\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:25:15 INFO\u001b[0m Trainer setup complete.\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:25:15 INFO\u001b[0m [GC] GC collection for checkpoint loading. took 0.13 seconds\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:25:15 INFO\u001b[0m Finished loading the checkpoint in 39.75 seconds.\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:25:15 INFO\u001b[0m Trainer setup complete.\n", + "✓ Actor spawned: ActorMesh(class=, shape={procs=8}), inner=)\n" + ] + } + ], + "source": [ + "# Create the spawner\n", + "spawner = SpawnActor(TrainerActor, cfg)\n", + "\n", + "# Spawn the actor\n", + "actor = await spawner.spawn()\n", + "print(f\"✓ Actor spawned: {actor}\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Setup the Actor" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": { + "output": { + "id": 693658349895675, + "loadingStatus": "loaded" + } + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:27:30 INFO\u001b[0m Setting up trainer actor...\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:27:30 INFO\u001b[0m Setting up trainer actor...\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:27:30 INFO\u001b[0m Setting up trainer actor...\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:27:30 INFO\u001b[0m Loading tokenizer from: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/tokenizer.json\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:27:30 INFO\u001b[0m Setting up trainer actor...\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:27:30 INFO\u001b[0m Setting up trainer actor...\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:27:30 INFO\u001b[0m Setting up trainer actor...\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:27:30 INFO\u001b[0m Loading tokenizer from: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/tokenizer.json\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:27:30 INFO\u001b[0m Loading tokenizer from: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/tokenizer.json\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:27:30 INFO\u001b[0m Loading tokenizer from: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/tokenizer.json\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:27:30 INFO\u001b[0m Setting up trainer actor...\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:27:30 INFO\u001b[0m Setting up trainer actor...\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:27:30 INFO\u001b[0m Loading tokenizer from: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/tokenizer.json\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:27:30 INFO\u001b[0m Loading tokenizer from: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/tokenizer.json\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:27:30 INFO\u001b[0m Loading tokenizer from: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/tokenizer.json\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:27:30 INFO\u001b[0m Loading tokenizer from: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/tokenizer.json\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:27:30 INFO\u001b[0m Loading SFT dataset from: yahma/alpaca-cleaned, split: train\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:27:30 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: c787119f-193d-4492-a59f-74262d4fd927)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:27:30 WARNING\u001b[0m Retrying in 1s [Retry 1/5].\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:27:30 INFO\u001b[0m Loading SFT dataset from: yahma/alpaca-cleaned, split: train\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:27:30 INFO\u001b[0m Loading SFT dataset from: yahma/alpaca-cleaned, split: train\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:27:30 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: ce05a969-6d99-40cf-a062-376f45f5db41)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:27:30 WARNING\u001b[0m Retrying in 1s [Retry 1/5].\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:27:30 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: ea962dc0-2676-454e-b82f-da6dfed2ac77)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:27:30 WARNING\u001b[0m Retrying in 1s [Retry 1/5].\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:27:30 INFO\u001b[0m Loading SFT dataset from: yahma/alpaca-cleaned, split: train\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:27:30 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 372cd4c1-cb1d-4330-a1f2-1bae50dac4e5)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:27:30 WARNING\u001b[0m Retrying in 1s [Retry 1/5].\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:27:30 INFO\u001b[0m Loading SFT dataset from: yahma/alpaca-cleaned, split: train\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:27:30 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: ed34cca9-ffb2-49cb-855f-40413f1d1630)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:27:30 WARNING\u001b[0m Retrying in 1s [Retry 1/5].\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:27:30 INFO\u001b[0m Loading SFT dataset from: yahma/alpaca-cleaned, split: train\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:27:30 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: f94785e5-a55e-4de8-9557-958836113d9e)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:27:30 WARNING\u001b[0m Retrying in 1s [Retry 1/5].\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:27:30 INFO\u001b[0m Loading SFT dataset from: yahma/alpaca-cleaned, split: train\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:27:30 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: f0f6a361-7fff-4c4a-aac2-e9c2d3215842)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:27:30 WARNING\u001b[0m Retrying in 1s [Retry 1/5].\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:27:30 INFO\u001b[0m Loading SFT dataset from: yahma/alpaca-cleaned, split: train\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:27:30 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: b5992586-ca0b-43d9-8a71-8a23f92bee97)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:27:30 WARNING\u001b[0m Retrying in 1s [Retry 1/5].\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[1] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: c787119f-193d-4492-a59f-74262d4fd927)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[1] Retrying in 1s [Retry 1/5].\n", + "[5] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: ce05a969-6d99-40cf-a062-376f45f5db41)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[5] Retrying in 1s [Retry 1/5].\n", + "[2] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: ea962dc0-2676-454e-b82f-da6dfed2ac77)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[2] Retrying in 1s [Retry 1/5].\n", + "[0] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 372cd4c1-cb1d-4330-a1f2-1bae50dac4e5)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[0] Retrying in 1s [Retry 1/5].\n", + "[6] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: ed34cca9-ffb2-49cb-855f-40413f1d1630)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[6] Retrying in 1s [Retry 1/5].\n", + "[3] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: f94785e5-a55e-4de8-9557-958836113d9e)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[3] Retrying in 1s [Retry 1/5].\n", + "[4] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: f0f6a361-7fff-4c4a-aac2-e9c2d3215842)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[4] Retrying in 1s [Retry 1/5].\n", + "[7] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: b5992586-ca0b-43d9-8a71-8a23f92bee97)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[7] Retrying in 1s [Retry 1/5].\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[1] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 4a76e392-8845-441c-a5de-0c267702d484)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[1] Retrying in 2s [Retry 2/5].\n", + "[2] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 26f237b3-0a26-4908-b296-81971ff782f2)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[2] Retrying in 2s [Retry 2/5].\n", + "[5] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 9a757a97-023f-4514-8311-0092c378e221)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[5] Retrying in 2s [Retry 2/5].\n", + "[0] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 1f438164-60b4-4949-873b-5b97b4cd8a9c)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[0] Retrying in 2s [Retry 2/5].\n", + "[6] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 53aa3ed7-6acd-4111-983c-276a2697e320)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[6] Retrying in 2s [Retry 2/5].\n", + "[3] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 4158e554-ee7c-4781-866f-619af9f6a593)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[3] Retrying in 2s [Retry 2/5].\n", + "[4] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 094a2622-6572-4219-bf44-82e0e148694a)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[4] Retrying in 2s [Retry 2/5].\n", + "[7] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 6267555e-58a7-4b5c-b7e7-08c628502eee)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[7] Retrying in 2s [Retry 2/5].\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:27:31 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 4a76e392-8845-441c-a5de-0c267702d484)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:27:31 WARNING\u001b[0m Retrying in 2s [Retry 2/5].\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:27:31 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 26f237b3-0a26-4908-b296-81971ff782f2)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:27:31 WARNING\u001b[0m Retrying in 2s [Retry 2/5].\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:27:31 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 9a757a97-023f-4514-8311-0092c378e221)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:27:31 WARNING\u001b[0m Retrying in 2s [Retry 2/5].\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:27:31 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 1f438164-60b4-4949-873b-5b97b4cd8a9c)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:27:31 WARNING\u001b[0m Retrying in 2s [Retry 2/5].\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:27:31 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 53aa3ed7-6acd-4111-983c-276a2697e320)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:27:31 WARNING\u001b[0m Retrying in 2s [Retry 2/5].\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:27:31 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 4158e554-ee7c-4781-866f-619af9f6a593)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:27:31 WARNING\u001b[0m Retrying in 2s [Retry 2/5].\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:27:31 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 094a2622-6572-4219-bf44-82e0e148694a)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:27:31 WARNING\u001b[0m Retrying in 2s [Retry 2/5].\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:27:31 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 6267555e-58a7-4b5c-b7e7-08c628502eee)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:27:31 WARNING\u001b[0m Retrying in 2s [Retry 2/5].\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:27:33 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: b090eb1f-38a6-446c-b29f-89272644459a)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:27:33 WARNING\u001b[0m Retrying in 4s [Retry 3/5].\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:27:33 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 4100690f-9d62-46f8-9b4b-9170a3d633cb)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:27:33 WARNING\u001b[0m Retrying in 4s [Retry 3/5].\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:27:33 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 2c584472-4aa9-4e49-bada-20bbe9e26c0a)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:27:33 WARNING\u001b[0m Retrying in 4s [Retry 3/5].\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:27:33 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: a77f6b4a-43dd-4c95-85b0-3c8e6d2cc1f1)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:27:33 WARNING\u001b[0m Retrying in 4s [Retry 3/5].\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:27:33 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 844c0336-98fb-4d27-bf87-4268779cbe33)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:27:33 WARNING\u001b[0m Retrying in 4s [Retry 3/5].\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:27:33 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 4f9a6d94-627c-4cfd-b963-8dd22d3c26af)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:27:33 WARNING\u001b[0m Retrying in 4s [Retry 3/5].\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:27:33 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: df3b3203-2ccf-4fed-961e-97e0a889df7e)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:27:33 WARNING\u001b[0m Retrying in 4s [Retry 3/5].\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:27:33 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: d172aaa5-7b1f-48cb-b53b-5308167112a1)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:27:33 WARNING\u001b[0m Retrying in 4s [Retry 3/5].\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[1] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: b090eb1f-38a6-446c-b29f-89272644459a)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[1] Retrying in 4s [Retry 3/5].\n", + "[2] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 4100690f-9d62-46f8-9b4b-9170a3d633cb)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[2] Retrying in 4s [Retry 3/5].\n", + "[5] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 2c584472-4aa9-4e49-bada-20bbe9e26c0a)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[5] Retrying in 4s [Retry 3/5].\n", + "[0] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: a77f6b4a-43dd-4c95-85b0-3c8e6d2cc1f1)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[0] Retrying in 4s [Retry 3/5].\n", + "[6] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 844c0336-98fb-4d27-bf87-4268779cbe33)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[6] Retrying in 4s [Retry 3/5].\n", + "[3] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 4f9a6d94-627c-4cfd-b963-8dd22d3c26af)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[3] Retrying in 4s [Retry 3/5].\n", + "[4] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: df3b3203-2ccf-4fed-961e-97e0a889df7e)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[4] Retrying in 4s [Retry 3/5].\n", + "[7] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: d172aaa5-7b1f-48cb-b53b-5308167112a1)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[7] Retrying in 4s [Retry 3/5].\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[1] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 4ffb7b11-22c8-4063-8fed-a57de5de8403)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[1] Retrying in 8s [Retry 4/5].\n", + "[5] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 1a01406a-736c-4bb5-80f4-c9860c11fc52)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[5] Retrying in 8s [Retry 4/5].\n", + "[2] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: f9b5e30f-5e37-4046-8e14-a68ee124c7be)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[2] Retrying in 8s [Retry 4/5].\n", + "[0] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 2719da25-5dcc-449b-a3ff-586ec0c65212)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[0] Retrying in 8s [Retry 4/5].\n", + "[6] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 025035bf-910e-400b-82ad-e655f8401b44)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[6] Retrying in 8s [Retry 4/5].\n", + "[3] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 72d844e6-44bc-4c3e-8932-ae616f6a5695)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[3] Retrying in 8s [Retry 4/5].\n", + "[4] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: b139f7ed-1ba1-46ee-8258-cc6f3020a2fd)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[4] Retrying in 8s [Retry 4/5].\n", + "[7] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 5262b0af-72fb-4c28-8f26-f113d6e7f2c8)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[7] Retrying in 8s [Retry 4/5].\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:27:37 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 4ffb7b11-22c8-4063-8fed-a57de5de8403)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:27:37 WARNING\u001b[0m Retrying in 8s [Retry 4/5].\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:27:37 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 1a01406a-736c-4bb5-80f4-c9860c11fc52)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:27:37 WARNING\u001b[0m Retrying in 8s [Retry 4/5].\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:27:37 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: f9b5e30f-5e37-4046-8e14-a68ee124c7be)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:27:37 WARNING\u001b[0m Retrying in 8s [Retry 4/5].\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:27:37 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 2719da25-5dcc-449b-a3ff-586ec0c65212)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:27:37 WARNING\u001b[0m Retrying in 8s [Retry 4/5].\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:27:37 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 025035bf-910e-400b-82ad-e655f8401b44)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:27:37 WARNING\u001b[0m Retrying in 8s [Retry 4/5].\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:27:37 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 72d844e6-44bc-4c3e-8932-ae616f6a5695)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:27:37 WARNING\u001b[0m Retrying in 8s [Retry 4/5].\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:27:37 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: b139f7ed-1ba1-46ee-8258-cc6f3020a2fd)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:27:37 WARNING\u001b[0m Retrying in 8s [Retry 4/5].\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:27:37 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 5262b0af-72fb-4c28-8f26-f113d6e7f2c8)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:27:37 WARNING\u001b[0m Retrying in 8s [Retry 4/5].\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[1] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: b5faa79c-ac4d-4bdb-ad28-00f8145c2369)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[1] Retrying in 8s [Retry 5/5].\n", + "[5] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: edad0c82-286f-4ad4-b03a-6af0b88a188a)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[5] Retrying in 8s [Retry 5/5].\n", + "[2] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 43eadf3a-82a7-4cb3-bd8e-6b19e7873748)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[2] Retrying in 8s [Retry 5/5].\n", + "[0] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: f1906533-966e-4715-bd6e-03bfcd057376)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[0] Retrying in 8s [Retry 5/5].\n", + "[6] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 04692a10-4765-438d-834d-13847772a7c1)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[6] Retrying in 8s [Retry 5/5].\n", + "[3] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: e26628b7-ecd5-485b-842a-894891160c1e)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[3] Retrying in 8s [Retry 5/5].\n", + "[4] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 994ef2e3-f583-46a8-b85a-dd1174ce727d)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[4] Retrying in 8s [Retry 5/5].\n", + "[7] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: d33a9d08-ab4a-4d71-bed2-41b8859325fb)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[7] Retrying in 8s [Retry 5/5].\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:27:45 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: b5faa79c-ac4d-4bdb-ad28-00f8145c2369)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:27:45 WARNING\u001b[0m Retrying in 8s [Retry 5/5].\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:27:45 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: edad0c82-286f-4ad4-b03a-6af0b88a188a)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:27:45 WARNING\u001b[0m Retrying in 8s [Retry 5/5].\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:27:45 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 43eadf3a-82a7-4cb3-bd8e-6b19e7873748)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:27:45 WARNING\u001b[0m Retrying in 8s [Retry 5/5].\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:27:45 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: f1906533-966e-4715-bd6e-03bfcd057376)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:27:45 WARNING\u001b[0m Retrying in 8s [Retry 5/5].\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:27:45 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 04692a10-4765-438d-834d-13847772a7c1)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:27:45 WARNING\u001b[0m Retrying in 8s [Retry 5/5].\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:27:45 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: e26628b7-ecd5-485b-842a-894891160c1e)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:27:45 WARNING\u001b[0m Retrying in 8s [Retry 5/5].\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:27:45 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 994ef2e3-f583-46a8-b85a-dd1174ce727d)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:27:45 WARNING\u001b[0m Retrying in 8s [Retry 5/5].\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:27:45 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: d33a9d08-ab4a-4d71-bed2-41b8859325fb)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:27:45 WARNING\u001b[0m Retrying in 8s [Retry 5/5].\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[1] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: ad3691b3-9589-4a22-9af7-935f439b572d)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[1] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: a22aaf4c-20e3-4f62-9d6f-f1bd1fd4fe89)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[1] Retrying in 1s [Retry 1/5].\n", + "[5] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: b77fe281-f6a4-43a2-9007-89558406aaed)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[2] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: a219110e-4774-4134-b74b-d6b23e63c00a)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[0] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 6f7638cc-d9a2-4b30-b507-f665ab64560e)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[5] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 8d2a10bd-fcf7-4c2a-a9b0-08597b8a5086)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[5] Retrying in 1s [Retry 1/5].\n", + "[2] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 09b0b22c-b405-43ed-99ca-06f75d429d17)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[2] Retrying in 1s [Retry 1/5].\n", + "[0] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: a45c4e57-e77c-4c9f-9ac1-400d73b6a1b5)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[0] Retrying in 1s [Retry 1/5].\n", + "[6] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: a8723092-8d7f-4f55-9467-c860baef5316)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[6] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 6b5d399e-562c-40e4-8471-6ec3e599e992)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[6] Retrying in 1s [Retry 1/5].\n", + "[3] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 88f07208-a8fd-44d9-af98-b8eb48e1023c)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[3] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 00a5d448-76f3-4fca-890f-a8cb332b8ff3)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[3] Retrying in 1s [Retry 1/5].\n", + "[4] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 38fe9537-f7e5-461d-a8e4-191fadea9202)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[4] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 9246e56c-4b35-4c4c-9efd-2423158c1d1d)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[4] Retrying in 1s [Retry 1/5].\n", + "[7] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: f45704e6-b1bf-4a56-b47f-4fdf6bb4eaa2)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[7] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 04dd6294-b004-4f89-9964-b089e732bfe1)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[7] Retrying in 1s [Retry 1/5].\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:27:53 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: ad3691b3-9589-4a22-9af7-935f439b572d)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:27:53 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: a22aaf4c-20e3-4f62-9d6f-f1bd1fd4fe89)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:27:53 WARNING\u001b[0m Retrying in 1s [Retry 1/5].\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:27:53 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: b77fe281-f6a4-43a2-9007-89558406aaed)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:27:53 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: a219110e-4774-4134-b74b-d6b23e63c00a)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:27:53 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 6f7638cc-d9a2-4b30-b507-f665ab64560e)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:27:53 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 8d2a10bd-fcf7-4c2a-a9b0-08597b8a5086)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:27:53 WARNING\u001b[0m Retrying in 1s [Retry 1/5].\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:27:53 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 09b0b22c-b405-43ed-99ca-06f75d429d17)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:27:53 WARNING\u001b[0m Retrying in 1s [Retry 1/5].\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:27:53 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: a45c4e57-e77c-4c9f-9ac1-400d73b6a1b5)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:27:53 WARNING\u001b[0m Retrying in 1s [Retry 1/5].\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:27:53 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: a8723092-8d7f-4f55-9467-c860baef5316)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:27:53 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 6b5d399e-562c-40e4-8471-6ec3e599e992)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:27:53 WARNING\u001b[0m Retrying in 1s [Retry 1/5].\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:27:53 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 88f07208-a8fd-44d9-af98-b8eb48e1023c)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:27:53 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 00a5d448-76f3-4fca-890f-a8cb332b8ff3)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:27:53 WARNING\u001b[0m Retrying in 1s [Retry 1/5].\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:27:53 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 38fe9537-f7e5-461d-a8e4-191fadea9202)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:27:53 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 9246e56c-4b35-4c4c-9efd-2423158c1d1d)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:27:53 WARNING\u001b[0m Retrying in 1s [Retry 1/5].\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:27:53 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/main/README.md (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: f45704e6-b1bf-4a56-b47f-4fdf6bb4eaa2)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/main/README.md\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:27:53 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 04dd6294-b004-4f89-9964-b089e732bfe1)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:27:53 WARNING\u001b[0m Retrying in 1s [Retry 1/5].\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[1] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 1701f2ef-13b3-4a89-a092-24fa134e9ccd)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[1] Retrying in 2s [Retry 2/5].\n", + "[5] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: e43e3099-3e2e-48e1-83ae-12fa2a314c05)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[5] Retrying in 2s [Retry 2/5].\n", + "[2] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: f1202e87-332d-4d96-ab0d-0472503fc4d3)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[2] Retrying in 2s [Retry 2/5].\n", + "[0] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 648c6d72-99c6-4d09-bfc4-2df906147f05)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[0] Retrying in 2s [Retry 2/5].\n", + "[6] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 600f7bde-c964-471c-8ce4-f30a752bc448)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[6] Retrying in 2s [Retry 2/5].\n", + "[3] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 74ea0fd7-c9a7-4ff6-8452-5c31ef974ba1)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[3] Retrying in 2s [Retry 2/5].\n", + "[4] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 86b710e1-8085-4846-adab-8bd26d30e664)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[4] Retrying in 2s [Retry 2/5].\n", + "[7] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 3f87c33f-59fb-45cc-b081-996ef227184a)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[7] Retrying in 2s [Retry 2/5].\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:27:54 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 1701f2ef-13b3-4a89-a092-24fa134e9ccd)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:27:54 WARNING\u001b[0m Retrying in 2s [Retry 2/5].\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:27:54 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: e43e3099-3e2e-48e1-83ae-12fa2a314c05)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:27:54 WARNING\u001b[0m Retrying in 2s [Retry 2/5].\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:27:54 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: f1202e87-332d-4d96-ab0d-0472503fc4d3)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:27:54 WARNING\u001b[0m Retrying in 2s [Retry 2/5].\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:27:54 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 648c6d72-99c6-4d09-bfc4-2df906147f05)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:27:54 WARNING\u001b[0m Retrying in 2s [Retry 2/5].\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:27:54 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 600f7bde-c964-471c-8ce4-f30a752bc448)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:27:54 WARNING\u001b[0m Retrying in 2s [Retry 2/5].\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:27:54 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 74ea0fd7-c9a7-4ff6-8452-5c31ef974ba1)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:27:54 WARNING\u001b[0m Retrying in 2s [Retry 2/5].\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:27:54 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 86b710e1-8085-4846-adab-8bd26d30e664)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:27:54 WARNING\u001b[0m Retrying in 2s [Retry 2/5].\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:27:54 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 3f87c33f-59fb-45cc-b081-996ef227184a)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:27:54 WARNING\u001b[0m Retrying in 2s [Retry 2/5].\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[1] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: c13ac332-6dbd-4e73-86a3-46ae24eb21d9)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[1] Retrying in 4s [Retry 3/5].\n", + "[5] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 2576a894-a550-4ddb-b74b-09c9495e2959)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[5] Retrying in 4s [Retry 3/5].\n", + "[2] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: f8b87a5e-e549-452f-aa36-806658b336f3)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[2] Retrying in 4s [Retry 3/5].\n", + "[0] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 0c69ca34-5695-4a9c-93d9-4c1f052e6b86)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[0] Retrying in 4s [Retry 3/5].\n", + "[6] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 6697ac3a-1d89-4e62-976e-b33feab54766)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[6] Retrying in 4s [Retry 3/5].\n", + "[3] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 6bd9497f-7e04-41fe-a699-caf4b6d986f3)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[3] Retrying in 4s [Retry 3/5].\n", + "[4] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 754ba06b-1c4c-4d38-8833-f2cf99732828)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[4] Retrying in 4s [Retry 3/5].\n", + "[7] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: fefb278b-7f36-40fb-a277-1dabe7cdb900)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[7] Retrying in 4s [Retry 3/5].\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:27:56 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: c13ac332-6dbd-4e73-86a3-46ae24eb21d9)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:27:56 WARNING\u001b[0m Retrying in 4s [Retry 3/5].\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:27:56 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 2576a894-a550-4ddb-b74b-09c9495e2959)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:27:56 WARNING\u001b[0m Retrying in 4s [Retry 3/5].\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:27:56 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: f8b87a5e-e549-452f-aa36-806658b336f3)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:27:56 WARNING\u001b[0m Retrying in 4s [Retry 3/5].\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:27:56 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 0c69ca34-5695-4a9c-93d9-4c1f052e6b86)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:27:56 WARNING\u001b[0m Retrying in 4s [Retry 3/5].\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:27:56 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 6697ac3a-1d89-4e62-976e-b33feab54766)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:27:56 WARNING\u001b[0m Retrying in 4s [Retry 3/5].\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:27:56 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 6bd9497f-7e04-41fe-a699-caf4b6d986f3)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:27:56 WARNING\u001b[0m Retrying in 4s [Retry 3/5].\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:27:56 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 754ba06b-1c4c-4d38-8833-f2cf99732828)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:27:56 WARNING\u001b[0m Retrying in 4s [Retry 3/5].\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:27:56 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: fefb278b-7f36-40fb-a277-1dabe7cdb900)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:27:56 WARNING\u001b[0m Retrying in 4s [Retry 3/5].\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[1] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: a25898a5-4f76-4a4a-aaec-81ed92aa3bc2)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[1] Retrying in 8s [Retry 4/5].\n", + "[2] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 5c0bf0d0-aab8-4ad2-9a6a-a5ed3b5373e7)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[2] Retrying in 8s [Retry 4/5].\n", + "[5] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: ef5f1bde-da3d-45be-961f-0484ba0aa999)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[5] Retrying in 8s [Retry 4/5].\n", + "[0] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: e6d140c3-3e2b-4196-944c-223a2e87f81d)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[0] Retrying in 8s [Retry 4/5].\n", + "[6] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: df48fda4-bfdc-4963-a0c5-d8a33827f07e)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[6] Retrying in 8s [Retry 4/5].\n", + "[3] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 57aa9802-8587-4476-b1c8-540f40d925fa)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[3] Retrying in 8s [Retry 4/5].\n", + "[4] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: c78615cc-a573-489a-b38b-17f90761e734)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[4] Retrying in 8s [Retry 4/5].\n", + "[7] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: fdd980f6-4d21-464c-ac2e-5a129ff6fc5e)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[7] Retrying in 8s [Retry 4/5].\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:28:00 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: a25898a5-4f76-4a4a-aaec-81ed92aa3bc2)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:28:00 WARNING\u001b[0m Retrying in 8s [Retry 4/5].\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:28:00 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 5c0bf0d0-aab8-4ad2-9a6a-a5ed3b5373e7)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:28:00 WARNING\u001b[0m Retrying in 8s [Retry 4/5].\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:28:00 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: ef5f1bde-da3d-45be-961f-0484ba0aa999)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:28:00 WARNING\u001b[0m Retrying in 8s [Retry 4/5].\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:28:00 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: e6d140c3-3e2b-4196-944c-223a2e87f81d)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:28:00 WARNING\u001b[0m Retrying in 8s [Retry 4/5].\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:28:00 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: df48fda4-bfdc-4963-a0c5-d8a33827f07e)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:28:00 WARNING\u001b[0m Retrying in 8s [Retry 4/5].\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:28:00 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 57aa9802-8587-4476-b1c8-540f40d925fa)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:28:00 WARNING\u001b[0m Retrying in 8s [Retry 4/5].\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:28:00 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: c78615cc-a573-489a-b38b-17f90761e734)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:28:00 WARNING\u001b[0m Retrying in 8s [Retry 4/5].\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:28:00 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: fdd980f6-4d21-464c-ac2e-5a129ff6fc5e)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:28:00 WARNING\u001b[0m Retrying in 8s [Retry 4/5].\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[1] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: a18b9e4c-6932-465b-87b1-e12986ceac8b)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[1] Retrying in 8s [Retry 5/5].\n", + "[2] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 760c4910-a61a-436c-9b7a-bbd594c2aabd)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[2] Retrying in 8s [Retry 5/5].\n", + "[5] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 8ec89e2d-9dd9-4d3b-9275-3910fd811b34)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[5] Retrying in 8s [Retry 5/5].\n", + "[0] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: cfb48d12-ed85-45f9-91bc-80e34ffca17c)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[0] Retrying in 8s [Retry 5/5].\n", + "[6] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 45c06612-dba8-4fd5-866c-433605a8b460)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[6] Retrying in 8s [Retry 5/5].\n", + "[3] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 37c243f3-950e-499a-b023-343d1fe5221a)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[3] Retrying in 8s [Retry 5/5].\n", + "[4] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: cd4d9dc4-43be-48d2-84e3-69bec7ec50f6)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[4] Retrying in 8s [Retry 5/5].\n", + "[7] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: be667810-eb20-430d-9fe5-1c9cae994608)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[7] Retrying in 8s [Retry 5/5].\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:28:08 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: a18b9e4c-6932-465b-87b1-e12986ceac8b)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:28:08 WARNING\u001b[0m Retrying in 8s [Retry 5/5].\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:28:08 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 760c4910-a61a-436c-9b7a-bbd594c2aabd)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:28:08 WARNING\u001b[0m Retrying in 8s [Retry 5/5].\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:28:08 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 8ec89e2d-9dd9-4d3b-9275-3910fd811b34)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:28:08 WARNING\u001b[0m Retrying in 8s [Retry 5/5].\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:28:08 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: cfb48d12-ed85-45f9-91bc-80e34ffca17c)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:28:08 WARNING\u001b[0m Retrying in 8s [Retry 5/5].\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:28:08 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 45c06612-dba8-4fd5-866c-433605a8b460)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:28:08 WARNING\u001b[0m Retrying in 8s [Retry 5/5].\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:28:08 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 37c243f3-950e-499a-b023-343d1fe5221a)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:28:08 WARNING\u001b[0m Retrying in 8s [Retry 5/5].\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:28:08 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: cd4d9dc4-43be-48d2-84e3-69bec7ec50f6)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:28:08 WARNING\u001b[0m Retrying in 8s [Retry 5/5].\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:28:08 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: be667810-eb20-430d-9fe5-1c9cae994608)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:28:08 WARNING\u001b[0m Retrying in 8s [Retry 5/5].\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[1] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 3c09fa02-335c-4acb-b126-06567a1bb16b)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[2] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: aae7637b-b790-4210-9c08-8f4a7a3f9343)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[5] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 5c63e4b6-99a3-46ed-8e43-ebdc836b8af0)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[1] Using the latest cached version of the dataset since yahma/alpaca-cleaned couldn't be found on the Hugging Face Hub\n", + "[1] Found the latest cached dataset configuration 'default' at /home/hosseinkh/.cache/huggingface/datasets/yahma___alpaca-cleaned/default/0.0.0/12567cabf869d7c92e573c7c783905fc160e9639 (last modified on Tue Sep 16 13:36:00 2025).\n", + "[0] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 8af0001b-4ca3-43ac-9eda-bcd4d6861b6c)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[2] Using the latest cached version of the dataset since yahma/alpaca-cleaned couldn't be found on the Hugging Face Hub\n", + "[2] Found the latest cached dataset configuration 'default' at /home/hosseinkh/.cache/huggingface/datasets/yahma___alpaca-cleaned/default/0.0.0/12567cabf869d7c92e573c7c783905fc160e9639 (last modified on Tue Sep 16 13:36:00 2025).\n", + "[5] Using the latest cached version of the dataset since yahma/alpaca-cleaned couldn't be found on the Hugging Face Hub\n", + "[5] Found the latest cached dataset configuration 'default' at /home/hosseinkh/.cache/huggingface/datasets/yahma___alpaca-cleaned/default/0.0.0/12567cabf869d7c92e573c7c783905fc160e9639 (last modified on Tue Sep 16 13:36:00 2025).\n", + "[0] Using the latest cached version of the dataset since yahma/alpaca-cleaned couldn't be found on the Hugging Face Hub\n", + "[0] Found the latest cached dataset configuration 'default' at /home/hosseinkh/.cache/huggingface/datasets/yahma___alpaca-cleaned/default/0.0.0/12567cabf869d7c92e573c7c783905fc160e9639 (last modified on Tue Sep 16 13:36:00 2025).\n", + "[6] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 12d2aacd-e7eb-4e78-a0bf-5fe6fa19f6e7)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[3] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 1e30ddae-841d-4863-947c-5cf882165234)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[6] Using the latest cached version of the dataset since yahma/alpaca-cleaned couldn't be found on the Hugging Face Hub\n", + "[6] Found the latest cached dataset configuration 'default' at /home/hosseinkh/.cache/huggingface/datasets/yahma___alpaca-cleaned/default/0.0.0/12567cabf869d7c92e573c7c783905fc160e9639 (last modified on Tue Sep 16 13:36:00 2025).\n", + "[4] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 512fa756-b919-45a7-9d58-40e859496f4b)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[3] Using the latest cached version of the dataset since yahma/alpaca-cleaned couldn't be found on the Hugging Face Hub\n", + "[3] Found the latest cached dataset configuration 'default' at /home/hosseinkh/.cache/huggingface/datasets/yahma___alpaca-cleaned/default/0.0.0/12567cabf869d7c92e573c7c783905fc160e9639 (last modified on Tue Sep 16 13:36:00 2025).\n", + "[4] Using the latest cached version of the dataset since yahma/alpaca-cleaned couldn't be found on the Hugging Face Hub\n", + "[4] Found the latest cached dataset configuration 'default' at /home/hosseinkh/.cache/huggingface/datasets/yahma___alpaca-cleaned/default/0.0.0/12567cabf869d7c92e573c7c783905fc160e9639 (last modified on Tue Sep 16 13:36:00 2025).\n", + "[7] '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: fb0c9ed8-dfe9-4d80-ab27-b575f5205a67)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[7] Using the latest cached version of the dataset since yahma/alpaca-cleaned couldn't be found on the Hugging Face Hub\n", + "[7] Found the latest cached dataset configuration 'default' at /home/hosseinkh/.cache/huggingface/datasets/yahma___alpaca-cleaned/default/0.0.0/12567cabf869d7c92e573c7c783905fc160e9639 (last modified on Tue Sep 16 13:36:00 2025).\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:28:16 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 3c09fa02-335c-4acb-b126-06567a1bb16b)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:28:16 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: aae7637b-b790-4210-9c08-8f4a7a3f9343)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:28:16 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 5c63e4b6-99a3-46ed-8e43-ebdc836b8af0)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:28:16 WARNING\u001b[0m Using the latest cached version of the dataset since yahma/alpaca-cleaned couldn't be found on the Hugging Face Hub\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:28:16 WARNING\u001b[0m Found the latest cached dataset configuration 'default' at /home/hosseinkh/.cache/huggingface/datasets/yahma___alpaca-cleaned/default/0.0.0/12567cabf869d7c92e573c7c783905fc160e9639 (last modified on Tue Sep 16 13:36:00 2025).\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:28:16 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 8af0001b-4ca3-43ac-9eda-bcd4d6861b6c)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:28:16 WARNING\u001b[0m Using the latest cached version of the dataset since yahma/alpaca-cleaned couldn't be found on the Hugging Face Hub\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:28:16 WARNING\u001b[0m Found the latest cached dataset configuration 'default' at /home/hosseinkh/.cache/huggingface/datasets/yahma___alpaca-cleaned/default/0.0.0/12567cabf869d7c92e573c7c783905fc160e9639 (last modified on Tue Sep 16 13:36:00 2025).\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:28:16 WARNING\u001b[0m Using the latest cached version of the dataset since yahma/alpaca-cleaned couldn't be found on the Hugging Face Hub\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:28:16 WARNING\u001b[0m Found the latest cached dataset configuration 'default' at /home/hosseinkh/.cache/huggingface/datasets/yahma___alpaca-cleaned/default/0.0.0/12567cabf869d7c92e573c7c783905fc160e9639 (last modified on Tue Sep 16 13:36:00 2025).\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:28:16 WARNING\u001b[0m Using the latest cached version of the dataset since yahma/alpaca-cleaned couldn't be found on the Hugging Face Hub\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:28:16 WARNING\u001b[0m Found the latest cached dataset configuration 'default' at /home/hosseinkh/.cache/huggingface/datasets/yahma___alpaca-cleaned/default/0.0.0/12567cabf869d7c92e573c7c783905fc160e9639 (last modified on Tue Sep 16 13:36:00 2025).\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:28:16 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 12d2aacd-e7eb-4e78-a0bf-5fe6fa19f6e7)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:28:16 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 1e30ddae-841d-4863-947c-5cf882165234)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:28:16 WARNING\u001b[0m Using the latest cached version of the dataset since yahma/alpaca-cleaned couldn't be found on the Hugging Face Hub\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:28:16 WARNING\u001b[0m Found the latest cached dataset configuration 'default' at /home/hosseinkh/.cache/huggingface/datasets/yahma___alpaca-cleaned/default/0.0.0/12567cabf869d7c92e573c7c783905fc160e9639 (last modified on Tue Sep 16 13:36:00 2025).\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:28:16 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: 512fa756-b919-45a7-9d58-40e859496f4b)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:28:16 WARNING\u001b[0m Using the latest cached version of the dataset since yahma/alpaca-cleaned couldn't be found on the Hugging Face Hub\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:28:16 WARNING\u001b[0m Found the latest cached dataset configuration 'default' at /home/hosseinkh/.cache/huggingface/datasets/yahma___alpaca-cleaned/default/0.0.0/12567cabf869d7c92e573c7c783905fc160e9639 (last modified on Tue Sep 16 13:36:00 2025).\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:28:16 WARNING\u001b[0m Using the latest cached version of the dataset since yahma/alpaca-cleaned couldn't be found on the Hugging Face Hub\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:28:16 WARNING\u001b[0m Found the latest cached dataset configuration 'default' at /home/hosseinkh/.cache/huggingface/datasets/yahma___alpaca-cleaned/default/0.0.0/12567cabf869d7c92e573c7c783905fc160e9639 (last modified on Tue Sep 16 13:36:00 2025).\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:28:16 WARNING\u001b[0m '(MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -2] Name or service not known)\"))'), '(Request ID: fb0c9ed8-dfe9-4d80-ab27-b575f5205a67)')' thrown while requesting HEAD https://huggingface.co/datasets/yahma/alpaca-cleaned/resolve/12567cabf869d7c92e573c7c783905fc160e9639/alpaca-cleaned.py\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:28:16 WARNING\u001b[0m Using the latest cached version of the dataset since yahma/alpaca-cleaned couldn't be found on the Hugging Face Hub\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:28:16 WARNING\u001b[0m Found the latest cached dataset configuration 'default' at /home/hosseinkh/.cache/huggingface/datasets/yahma___alpaca-cleaned/default/0.0.0/12567cabf869d7c92e573c7c783905fc160e9639 (last modified on Tue Sep 16 13:36:00 2025).\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:28:16 INFO\u001b[0m Created dataloader with batch_size=1, target_tokens=2048\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:28:16 INFO\u001b[0m Created dataloader with batch_size=1, target_tokens=2048\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:28:16 INFO\u001b[0m Loading checkpoint...\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:28:16 INFO\u001b[0m loading from HF safetensors from --checkpoint.initial_load_path: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:28:16 INFO\u001b[0m Loading the checkpoint from /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/.\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:28:16 INFO\u001b[0m Loading checkpoint...\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:28:16 INFO\u001b[0m loading from HF safetensors from --checkpoint.initial_load_path: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:28:16 INFO\u001b[0m Loading the checkpoint from /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/.\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:28:16 INFO\u001b[0m Created dataloader with batch_size=1, target_tokens=2048\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:28:16 INFO\u001b[0m Created dataloader with batch_size=1, target_tokens=2048\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:28:16 INFO\u001b[0m Loading checkpoint...\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:28:16 INFO\u001b[0m loading from HF safetensors from --checkpoint.initial_load_path: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:28:16 INFO\u001b[0m Loading the checkpoint from /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/.\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:28:16 INFO\u001b[0m Loading checkpoint...\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:28:16 INFO\u001b[0m loading from HF safetensors from --checkpoint.initial_load_path: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:28:16 INFO\u001b[0m Loading the checkpoint from /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/.\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:28:16 INFO\u001b[0m Created dataloader with batch_size=1, target_tokens=2048\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:28:16 INFO\u001b[0m Created dataloader with batch_size=1, target_tokens=2048\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:28:16 INFO\u001b[0m Loading checkpoint...\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:28:16 INFO\u001b[0m loading from HF safetensors from --checkpoint.initial_load_path: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:28:16 INFO\u001b[0m Loading the checkpoint from /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/.\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:28:16 INFO\u001b[0m Loading checkpoint...\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:28:16 INFO\u001b[0m loading from HF safetensors from --checkpoint.initial_load_path: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:28:16 INFO\u001b[0m Loading the checkpoint from /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/.\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:28:16 INFO\u001b[0m Created dataloader with batch_size=1, target_tokens=2048\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:28:16 INFO\u001b[0m Created dataloader with batch_size=1, target_tokens=2048\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:28:16 INFO\u001b[0m Loading checkpoint...\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:28:16 INFO\u001b[0m loading from HF safetensors from --checkpoint.initial_load_path: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:28:16 INFO\u001b[0m Loading checkpoint...\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:28:16 INFO\u001b[0m Loading the checkpoint from /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/.\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:28:16 INFO\u001b[0m loading from HF safetensors from --checkpoint.initial_load_path: /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:28:16 INFO\u001b[0m Loading the checkpoint from /home/hosseinkh/models/Meta-Llama-3.1-8B-Instruct/.\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:28:53 INFO\u001b[0m [GC] GC collection for checkpoint loading. took 0.01 seconds\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:28:53 INFO\u001b[0m Finished loading the checkpoint in 36.69 seconds.\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:28:53 INFO\u001b[0m Trainer setup complete.\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:28:53 INFO\u001b[0m [GC] GC collection for checkpoint loading. took 0.01 seconds\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:28:53 INFO\u001b[0m Finished loading the checkpoint in 36.70 seconds.\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:28:53 INFO\u001b[0m Trainer setup complete.\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:28:53 INFO\u001b[0m [GC] GC collection for checkpoint loading. took 0.01 seconds\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:28:53 INFO\u001b[0m Finished loading the checkpoint in 36.71 seconds.\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:28:53 INFO\u001b[0m Trainer setup complete.\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:28:53 INFO\u001b[0m [GC] GC collection for checkpoint loading. took 0.01 seconds\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:28:53 INFO\u001b[0m Finished loading the checkpoint in 36.66 seconds.\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:28:53 INFO\u001b[0m [GC] GC collection for checkpoint loading. took 0.01 seconds\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:28:53 INFO\u001b[0m Finished loading the checkpoint in 36.70 seconds.\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:28:53 INFO\u001b[0m Trainer setup complete.\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:28:53 INFO\u001b[0m Trainer setup complete.\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:28:53 INFO\u001b[0m [GC] GC collection for checkpoint loading. took 0.01 seconds\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:28:53 INFO\u001b[0m Finished loading the checkpoint in 36.66 seconds.\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:28:53 INFO\u001b[0m Trainer setup complete.\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:28:53 INFO\u001b[0m [GC] GC collection for checkpoint loading. took 0.01 seconds\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:28:53 INFO\u001b[0m Finished loading the checkpoint in 36.67 seconds.\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:28:53 INFO\u001b[0m Trainer setup complete.\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:28:53 INFO\u001b[0m [GC] GC collection for checkpoint loading. took 0.01 seconds\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:28:53 INFO\u001b[0m Finished loading the checkpoint in 36.68 seconds.\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:28:53 INFO\u001b[0m Trainer setup complete.\n", + "✓ Actor setup complete\n" + ] + } + ], + "source": [ + "# Setup (load data, checkpoints, etc.)\n", + "await spawner.setup()\n", + "print(\"✓ Actor setup complete\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Run Training" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": { + "output": { + "id": 4257826794454822, + "loadingStatus": "loaded" + } + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:31 INFO\u001b[0m Starting training loop...\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:31 INFO\u001b[0m Starting training loop...\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:31 INFO\u001b[0m Starting training loop...\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:31 INFO\u001b[0m Starting training loop...\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:31 INFO\u001b[0m Starting training loop...\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:31 INFO\u001b[0m Starting training loop...\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:31 INFO\u001b[0m Starting training loop...\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:31 INFO\u001b[0m Starting training loop...\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:34 INFO\u001b[0m Step 0/1000 | Loss: 1.3879\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:34 INFO\u001b[0m Step 0/1000 | Loss: 1.3575\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:34 INFO\u001b[0m Step 0/1000 | Loss: 1.4058\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:34 INFO\u001b[0m Step 0/1000 | Loss: 1.2134\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:34 INFO\u001b[0m Step 0/1000 | Loss: 1.2885\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:34 INFO\u001b[0m Step 0/1000 | Loss: 1.2271\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:34 INFO\u001b[0m Step 0/1000 | Loss: 1.2873\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:34 INFO\u001b[0m Step 0/1000 | Loss: 1.2584\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:35 INFO\u001b[0m Step 1/1000 | Loss: 1.3446\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:35 INFO\u001b[0m Step 1/1000 | Loss: 1.0995\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:35 INFO\u001b[0m Step 1/1000 | Loss: 1.4839\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:35 INFO\u001b[0m Step 1/1000 | Loss: 1.3154\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:35 INFO\u001b[0m Step 1/1000 | Loss: 1.3136\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:35 INFO\u001b[0m Step 1/1000 | Loss: 1.3836\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:35 INFO\u001b[0m Step 1/1000 | Loss: 1.2724\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:35 INFO\u001b[0m Step 1/1000 | Loss: 1.2416\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:35 INFO\u001b[0m Step 2/1000 | Loss: 1.3352\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:35 INFO\u001b[0m Step 2/1000 | Loss: 1.3216\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:35 INFO\u001b[0m Step 2/1000 | Loss: 1.2667\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:35 INFO\u001b[0m Step 2/1000 | Loss: 1.2524\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:35 INFO\u001b[0m Step 2/1000 | Loss: 1.2719\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:35 INFO\u001b[0m Step 2/1000 | Loss: 1.2459\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:35 INFO\u001b[0m Step 2/1000 | Loss: 1.4427\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:35 INFO\u001b[0m Step 2/1000 | Loss: 1.2750\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:36 INFO\u001b[0m Step 3/1000 | Loss: 1.4037\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:36 INFO\u001b[0m Step 3/1000 | Loss: 1.2964\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:36 INFO\u001b[0m Step 3/1000 | Loss: 1.3591\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:36 INFO\u001b[0m Step 3/1000 | Loss: 1.1986\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:36 INFO\u001b[0m Step 3/1000 | Loss: 1.2320\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:36 INFO\u001b[0m Step 3/1000 | Loss: 1.3460\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:36 INFO\u001b[0m Step 3/1000 | Loss: 1.2798\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:36 INFO\u001b[0m Step 3/1000 | Loss: 1.3310\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:36 INFO\u001b[0m Step 4/1000 | Loss: 1.2332\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:36 INFO\u001b[0m Step 4/1000 | Loss: 1.2515\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:36 INFO\u001b[0m Step 4/1000 | Loss: 1.2327\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:36 INFO\u001b[0m Step 4/1000 | Loss: 1.2820\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:36 INFO\u001b[0m Step 4/1000 | Loss: 1.2506\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:36 INFO\u001b[0m Step 4/1000 | Loss: 1.3129\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:36 INFO\u001b[0m Step 4/1000 | Loss: 1.4557\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:36 INFO\u001b[0m Step 4/1000 | Loss: 1.3472\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:37 INFO\u001b[0m Step 5/1000 | Loss: 1.2875\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:37 INFO\u001b[0m Step 5/1000 | Loss: 1.3100\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:37 INFO\u001b[0m Step 5/1000 | Loss: 1.3427\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:37 INFO\u001b[0m Step 5/1000 | Loss: 1.2775\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:37 INFO\u001b[0m Step 5/1000 | Loss: 1.3659\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:37 INFO\u001b[0m Step 5/1000 | Loss: 1.3104\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:37 INFO\u001b[0m Step 5/1000 | Loss: 1.2156\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:37 INFO\u001b[0m Step 5/1000 | Loss: 1.2944\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:37 INFO\u001b[0m Step 6/1000 | Loss: 1.1664\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:37 INFO\u001b[0m Step 6/1000 | Loss: 1.2141\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:37 INFO\u001b[0m Step 6/1000 | Loss: 1.4640\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:37 INFO\u001b[0m Step 6/1000 | Loss: 1.2914\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:37 INFO\u001b[0m Step 6/1000 | Loss: 1.2824\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:37 INFO\u001b[0m Step 6/1000 | Loss: 1.3397\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:37 INFO\u001b[0m Step 6/1000 | Loss: 1.2572\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:37 INFO\u001b[0m Step 6/1000 | Loss: 1.4064\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:37 INFO\u001b[0m Step 7/1000 | Loss: 1.1993\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:37 INFO\u001b[0m Step 7/1000 | Loss: 1.0969\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:37 INFO\u001b[0m Step 7/1000 | Loss: 1.3833\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:37 INFO\u001b[0m Step 7/1000 | Loss: 1.3213\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:37 INFO\u001b[0m Step 7/1000 | Loss: 1.2779\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:37 INFO\u001b[0m Step 7/1000 | Loss: 1.3592\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:37 INFO\u001b[0m Step 7/1000 | Loss: 1.2711\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:37 INFO\u001b[0m Step 7/1000 | Loss: 1.3853\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:38 INFO\u001b[0m Step 8/1000 | Loss: 1.1944\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:38 INFO\u001b[0m Step 8/1000 | Loss: 1.2725\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:38 INFO\u001b[0m Step 8/1000 | Loss: 1.2009\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:38 INFO\u001b[0m Step 8/1000 | Loss: 1.3001\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:38 INFO\u001b[0m Step 8/1000 | Loss: 1.1686\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:38 INFO\u001b[0m Step 8/1000 | Loss: 1.2479\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:38 INFO\u001b[0m Step 8/1000 | Loss: 1.1916\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:38 INFO\u001b[0m Step 8/1000 | Loss: 1.2491\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:38 INFO\u001b[0m Step 9/1000 | Loss: 1.0677\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:38 INFO\u001b[0m Step 9/1000 | Loss: 1.1576\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:38 INFO\u001b[0m Step 9/1000 | Loss: 1.1923\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:38 INFO\u001b[0m Step 9/1000 | Loss: 1.3268\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:38 INFO\u001b[0m Step 9/1000 | Loss: 1.2204\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:38 INFO\u001b[0m Step 9/1000 | Loss: 1.1739\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:38 INFO\u001b[0m Step 9/1000 | Loss: 1.1770\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:38 INFO\u001b[0m Step 9/1000 | Loss: 1.3698\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:39 INFO\u001b[0m Step 10/1000 | Loss: 1.2823\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:39 INFO\u001b[0m Step 10/1000 | Loss: 1.2541\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:39 INFO\u001b[0m Step 10/1000 | Loss: 1.4543\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:39 INFO\u001b[0m Step 10/1000 | Loss: 1.3076\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:39 INFO\u001b[0m Step 10/1000 | Loss: 1.1083\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:39 INFO\u001b[0m Step 10/1000 | Loss: 1.2355\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:39 INFO\u001b[0m Step 10/1000 | Loss: 1.3375\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:39 INFO\u001b[0m Step 10/1000 | Loss: 1.1846\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:39 INFO\u001b[0m Step 11/1000 | Loss: 1.1550\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:39 INFO\u001b[0m Step 11/1000 | Loss: 1.1147\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:39 INFO\u001b[0m Step 11/1000 | Loss: 1.2818\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:39 INFO\u001b[0m Step 11/1000 | Loss: 1.2095\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:39 INFO\u001b[0m Step 11/1000 | Loss: 1.2152\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:39 INFO\u001b[0m Step 11/1000 | Loss: 1.4114\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:39 INFO\u001b[0m Step 11/1000 | Loss: 1.2619\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:39 INFO\u001b[0m Step 11/1000 | Loss: 1.2515\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:39 INFO\u001b[0m Step 12/1000 | Loss: 1.2255\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:39 INFO\u001b[0m Step 12/1000 | Loss: 1.1185\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:39 INFO\u001b[0m Step 12/1000 | Loss: 1.2126\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:39 INFO\u001b[0m Step 12/1000 | Loss: 1.1079\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:39 INFO\u001b[0m Step 12/1000 | Loss: 1.0354\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:39 INFO\u001b[0m Step 12/1000 | Loss: 1.2343\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:39 INFO\u001b[0m Step 12/1000 | Loss: 1.0474\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:39 INFO\u001b[0m Step 12/1000 | Loss: 1.1924\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:40 INFO\u001b[0m Step 13/1000 | Loss: 1.0955\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:40 INFO\u001b[0m Step 13/1000 | Loss: 1.1039\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:40 INFO\u001b[0m Step 13/1000 | Loss: 1.2255\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:40 INFO\u001b[0m Step 13/1000 | Loss: 1.1671\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:40 INFO\u001b[0m Step 13/1000 | Loss: 1.0619\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:40 INFO\u001b[0m Step 13/1000 | Loss: 1.0631\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:40 INFO\u001b[0m Step 13/1000 | Loss: 0.9712\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:40 INFO\u001b[0m Step 13/1000 | Loss: 0.9890\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:40 INFO\u001b[0m Step 14/1000 | Loss: 1.0466\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:40 INFO\u001b[0m Step 14/1000 | Loss: 1.1425\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:40 INFO\u001b[0m Step 14/1000 | Loss: 0.9888\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:40 INFO\u001b[0m Step 14/1000 | Loss: 1.1653\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:40 INFO\u001b[0m Step 14/1000 | Loss: 1.2068\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:40 INFO\u001b[0m Step 14/1000 | Loss: 1.1679\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:40 INFO\u001b[0m Step 14/1000 | Loss: 1.0304\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:40 INFO\u001b[0m Step 14/1000 | Loss: 1.2282\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:41 INFO\u001b[0m Step 15/1000 | Loss: 1.0780\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:41 INFO\u001b[0m Step 15/1000 | Loss: 1.1283\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:41 INFO\u001b[0m Step 15/1000 | Loss: 0.9790\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:41 INFO\u001b[0m Step 15/1000 | Loss: 0.9983\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:41 INFO\u001b[0m Step 15/1000 | Loss: 0.8568\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:41 INFO\u001b[0m Step 15/1000 | Loss: 1.1002\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:41 INFO\u001b[0m Step 15/1000 | Loss: 1.0674\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:41 INFO\u001b[0m Step 15/1000 | Loss: 0.9851\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:41 INFO\u001b[0m Step 16/1000 | Loss: 1.0205\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:41 INFO\u001b[0m Step 16/1000 | Loss: 1.1271\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:41 INFO\u001b[0m Step 16/1000 | Loss: 0.9793\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:41 INFO\u001b[0m Step 16/1000 | Loss: 0.9302\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:41 INFO\u001b[0m Step 16/1000 | Loss: 0.9362\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:41 INFO\u001b[0m Step 16/1000 | Loss: 0.9824\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:41 INFO\u001b[0m Step 16/1000 | Loss: 1.0593\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:41 INFO\u001b[0m Step 16/1000 | Loss: 1.0598\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:41 INFO\u001b[0m Step 17/1000 | Loss: 1.0168\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:41 INFO\u001b[0m Step 17/1000 | Loss: 0.8759\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:41 INFO\u001b[0m Step 17/1000 | Loss: 0.9231\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:41 INFO\u001b[0m Step 17/1000 | Loss: 0.9712\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:41 INFO\u001b[0m Step 17/1000 | Loss: 0.9223\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:41 INFO\u001b[0m Step 17/1000 | Loss: 1.0533\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:41 INFO\u001b[0m Step 17/1000 | Loss: 1.1227\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:41 INFO\u001b[0m Step 17/1000 | Loss: 0.9577\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:42 INFO\u001b[0m Step 18/1000 | Loss: 0.8830\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:42 INFO\u001b[0m Step 18/1000 | Loss: 1.0052\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:42 INFO\u001b[0m Step 18/1000 | Loss: 0.9860\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:42 INFO\u001b[0m Step 18/1000 | Loss: 1.0314\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:42 INFO\u001b[0m Step 18/1000 | Loss: 1.2542\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:42 INFO\u001b[0m Step 18/1000 | Loss: 1.0459\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:42 INFO\u001b[0m Step 18/1000 | Loss: 1.1096\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:42 INFO\u001b[0m Step 18/1000 | Loss: 0.9876\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:42 INFO\u001b[0m Step 19/1000 | Loss: 1.2377\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:42 INFO\u001b[0m Step 19/1000 | Loss: 1.1060\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:42 INFO\u001b[0m Step 19/1000 | Loss: 0.9933\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:42 INFO\u001b[0m Step 19/1000 | Loss: 1.1389\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:42 INFO\u001b[0m Step 19/1000 | Loss: 1.0118\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:42 INFO\u001b[0m Step 19/1000 | Loss: 1.0373\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:42 INFO\u001b[0m Step 19/1000 | Loss: 1.3154\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:42 INFO\u001b[0m Step 19/1000 | Loss: 1.0951\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:43 INFO\u001b[0m Step 20/1000 | Loss: 1.1727\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:43 INFO\u001b[0m Step 20/1000 | Loss: 1.1881\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:43 INFO\u001b[0m Step 20/1000 | Loss: 0.9113\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:43 INFO\u001b[0m Step 20/1000 | Loss: 0.9492\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:43 INFO\u001b[0m Step 20/1000 | Loss: 1.0041\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:43 INFO\u001b[0m Step 20/1000 | Loss: 1.0685\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:43 INFO\u001b[0m Step 20/1000 | Loss: 0.9413\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:43 INFO\u001b[0m Step 20/1000 | Loss: 1.0472\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:43 INFO\u001b[0m Step 21/1000 | Loss: 0.9293\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:43 INFO\u001b[0m Step 21/1000 | Loss: 1.0554\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:43 INFO\u001b[0m Step 21/1000 | Loss: 1.0109\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:43 INFO\u001b[0m Step 21/1000 | Loss: 1.0653\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:43 INFO\u001b[0m Step 21/1000 | Loss: 1.1179\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:43 INFO\u001b[0m Step 21/1000 | Loss: 1.0619\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:43 INFO\u001b[0m Step 21/1000 | Loss: 0.9351\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:43 INFO\u001b[0m Step 21/1000 | Loss: 1.0244\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:44 INFO\u001b[0m Step 22/1000 | Loss: 0.9123\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:44 INFO\u001b[0m Step 22/1000 | Loss: 0.9655\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:44 INFO\u001b[0m Step 22/1000 | Loss: 0.8334\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:44 INFO\u001b[0m Step 22/1000 | Loss: 1.0536\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:44 INFO\u001b[0m Step 22/1000 | Loss: 1.1452\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:44 INFO\u001b[0m Step 22/1000 | Loss: 0.8310\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:44 INFO\u001b[0m Step 22/1000 | Loss: 1.1640\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:44 INFO\u001b[0m Step 22/1000 | Loss: 0.8248\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:44 INFO\u001b[0m Step 23/1000 | Loss: 0.9209\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:44 INFO\u001b[0m Step 23/1000 | Loss: 1.0363\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:44 INFO\u001b[0m Step 23/1000 | Loss: 0.9151\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:44 INFO\u001b[0m Step 23/1000 | Loss: 1.0912\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:44 INFO\u001b[0m Step 23/1000 | Loss: 0.9354\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:44 INFO\u001b[0m Step 23/1000 | Loss: 1.0719\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:44 INFO\u001b[0m Step 23/1000 | Loss: 0.9974\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:44 INFO\u001b[0m Step 23/1000 | Loss: 1.2039\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:44 INFO\u001b[0m Step 24/1000 | Loss: 0.9691\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:44 INFO\u001b[0m Step 24/1000 | Loss: 1.0877\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:44 INFO\u001b[0m Step 24/1000 | Loss: 0.9372\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:44 INFO\u001b[0m Step 24/1000 | Loss: 1.0526\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:44 INFO\u001b[0m Step 24/1000 | Loss: 1.0716\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:44 INFO\u001b[0m Step 24/1000 | Loss: 0.9824\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:44 INFO\u001b[0m Step 24/1000 | Loss: 1.1161\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:44 INFO\u001b[0m Step 24/1000 | Loss: 0.8817\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:45 INFO\u001b[0m Step 25/1000 | Loss: 1.0052\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:45 INFO\u001b[0m Step 25/1000 | Loss: 1.0522\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:45 INFO\u001b[0m Step 25/1000 | Loss: 1.0711\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:45 INFO\u001b[0m Step 25/1000 | Loss: 1.0175\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:45 INFO\u001b[0m Step 25/1000 | Loss: 1.0233\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:45 INFO\u001b[0m Step 25/1000 | Loss: 1.0758\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:45 INFO\u001b[0m Step 25/1000 | Loss: 1.0566\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:45 INFO\u001b[0m Step 25/1000 | Loss: 1.2796\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:45 INFO\u001b[0m Step 26/1000 | Loss: 1.1888\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:45 INFO\u001b[0m Step 26/1000 | Loss: 1.0739\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:45 INFO\u001b[0m Step 26/1000 | Loss: 0.7871\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:45 INFO\u001b[0m Step 26/1000 | Loss: 1.0993\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:45 INFO\u001b[0m Step 26/1000 | Loss: 1.0922\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:45 INFO\u001b[0m Step 26/1000 | Loss: 1.0475\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:45 INFO\u001b[0m Step 26/1000 | Loss: 1.0635\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:45 INFO\u001b[0m Step 26/1000 | Loss: 1.0938\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:46 INFO\u001b[0m Step 27/1000 | Loss: 1.2112\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:46 INFO\u001b[0m Step 27/1000 | Loss: 1.1058\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:46 INFO\u001b[0m Step 27/1000 | Loss: 1.1347\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:46 INFO\u001b[0m Step 27/1000 | Loss: 1.0164\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:46 INFO\u001b[0m Step 27/1000 | Loss: 1.1728\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:46 INFO\u001b[0m Step 27/1000 | Loss: 1.0719\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:46 INFO\u001b[0m Step 27/1000 | Loss: 1.0190\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:46 INFO\u001b[0m Step 27/1000 | Loss: 0.9814\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:46 INFO\u001b[0m Step 28/1000 | Loss: 0.9836\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:46 INFO\u001b[0m Step 28/1000 | Loss: 1.1672\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:46 INFO\u001b[0m Step 28/1000 | Loss: 1.0643\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:46 INFO\u001b[0m Step 28/1000 | Loss: 0.9921\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:46 INFO\u001b[0m Step 28/1000 | Loss: 0.9776\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:46 INFO\u001b[0m Step 28/1000 | Loss: 0.9766\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:46 INFO\u001b[0m Step 28/1000 | Loss: 1.1392\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:46 INFO\u001b[0m Step 28/1000 | Loss: 1.1273\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:46 INFO\u001b[0m Step 29/1000 | Loss: 1.0461\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:46 INFO\u001b[0m Step 29/1000 | Loss: 1.0377\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:46 INFO\u001b[0m Step 29/1000 | Loss: 1.0299\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:46 INFO\u001b[0m Step 29/1000 | Loss: 1.0565\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:46 INFO\u001b[0m Step 29/1000 | Loss: 1.1483\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:46 INFO\u001b[0m Step 29/1000 | Loss: 1.0361\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:46 INFO\u001b[0m Step 29/1000 | Loss: 1.0810\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:46 INFO\u001b[0m Step 29/1000 | Loss: 1.0343\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:47 INFO\u001b[0m Step 30/1000 | Loss: 1.0232\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:47 INFO\u001b[0m Step 30/1000 | Loss: 1.0951\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:47 INFO\u001b[0m Step 30/1000 | Loss: 1.0493\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:47 INFO\u001b[0m Step 30/1000 | Loss: 1.1696\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:47 INFO\u001b[0m Step 30/1000 | Loss: 1.1804\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:47 INFO\u001b[0m Step 30/1000 | Loss: 0.9973\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:47 INFO\u001b[0m Step 30/1000 | Loss: 1.0598\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:47 INFO\u001b[0m Step 30/1000 | Loss: 1.0113\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:47 INFO\u001b[0m Step 31/1000 | Loss: 0.8269\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:47 INFO\u001b[0m Step 31/1000 | Loss: 1.1943\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:47 INFO\u001b[0m Step 31/1000 | Loss: 0.9878\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:47 INFO\u001b[0m Step 31/1000 | Loss: 1.1139\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:47 INFO\u001b[0m Step 31/1000 | Loss: 0.9802\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:47 INFO\u001b[0m Step 31/1000 | Loss: 1.0880\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:47 INFO\u001b[0m Step 31/1000 | Loss: 1.1496\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:47 INFO\u001b[0m Step 31/1000 | Loss: 1.0311\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:48 INFO\u001b[0m Step 32/1000 | Loss: 1.0279\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:48 INFO\u001b[0m Step 32/1000 | Loss: 1.1203\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:48 INFO\u001b[0m Step 32/1000 | Loss: 0.9199\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:48 INFO\u001b[0m Step 32/1000 | Loss: 0.8204\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:48 INFO\u001b[0m Step 32/1000 | Loss: 1.0950\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:48 INFO\u001b[0m Step 32/1000 | Loss: 0.9940\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:48 INFO\u001b[0m Step 32/1000 | Loss: 1.0727\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:48 INFO\u001b[0m Step 32/1000 | Loss: 0.9001\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:48 INFO\u001b[0m Step 33/1000 | Loss: 0.9578\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:48 INFO\u001b[0m Step 33/1000 | Loss: 1.0042\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:48 INFO\u001b[0m Step 33/1000 | Loss: 1.0796\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:48 INFO\u001b[0m Step 33/1000 | Loss: 0.8216\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:48 INFO\u001b[0m Step 33/1000 | Loss: 1.0062\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:48 INFO\u001b[0m Step 33/1000 | Loss: 1.0705\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:48 INFO\u001b[0m Step 33/1000 | Loss: 1.0396\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:48 INFO\u001b[0m Step 33/1000 | Loss: 0.9633\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:48 INFO\u001b[0m Step 34/1000 | Loss: 1.0173\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:48 INFO\u001b[0m Step 34/1000 | Loss: 1.1093\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:48 INFO\u001b[0m Step 34/1000 | Loss: 1.0056\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:48 INFO\u001b[0m Step 34/1000 | Loss: 1.0483\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:48 INFO\u001b[0m Step 34/1000 | Loss: 0.8783\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:48 INFO\u001b[0m Step 34/1000 | Loss: 0.8599\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:48 INFO\u001b[0m Step 34/1000 | Loss: 0.9440\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:48 INFO\u001b[0m Step 34/1000 | Loss: 0.9157\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:49 INFO\u001b[0m Step 35/1000 | Loss: 1.0795\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:49 INFO\u001b[0m Step 35/1000 | Loss: 0.9118\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:49 INFO\u001b[0m Step 35/1000 | Loss: 0.8394\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:49 INFO\u001b[0m Step 35/1000 | Loss: 1.0624\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:49 INFO\u001b[0m Step 35/1000 | Loss: 1.0480\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:49 INFO\u001b[0m Step 35/1000 | Loss: 1.0256\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:49 INFO\u001b[0m Step 35/1000 | Loss: 0.9725\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:49 INFO\u001b[0m Step 35/1000 | Loss: 0.8708\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:49 INFO\u001b[0m Step 36/1000 | Loss: 0.8642\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:49 INFO\u001b[0m Step 36/1000 | Loss: 1.0509\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:49 INFO\u001b[0m Step 36/1000 | Loss: 1.1865\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:49 INFO\u001b[0m Step 36/1000 | Loss: 0.9585\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:49 INFO\u001b[0m Step 36/1000 | Loss: 1.0053\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:49 INFO\u001b[0m Step 36/1000 | Loss: 0.8375\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:49 INFO\u001b[0m Step 36/1000 | Loss: 1.0603\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:49 INFO\u001b[0m Step 36/1000 | Loss: 1.0344\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:50 INFO\u001b[0m Step 37/1000 | Loss: 0.9352\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:50 INFO\u001b[0m Step 37/1000 | Loss: 0.9870\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:50 INFO\u001b[0m Step 37/1000 | Loss: 1.0389\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:50 INFO\u001b[0m Step 37/1000 | Loss: 0.9088\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:50 INFO\u001b[0m Step 37/1000 | Loss: 1.0172\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:50 INFO\u001b[0m Step 37/1000 | Loss: 1.0411\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:50 INFO\u001b[0m Step 37/1000 | Loss: 1.1295\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:50 INFO\u001b[0m Step 37/1000 | Loss: 1.0284\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:50 INFO\u001b[0m Step 38/1000 | Loss: 1.0098\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:50 INFO\u001b[0m Step 38/1000 | Loss: 1.0331\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:50 INFO\u001b[0m Step 38/1000 | Loss: 1.1580\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:50 INFO\u001b[0m Step 38/1000 | Loss: 0.9686\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:50 INFO\u001b[0m Step 38/1000 | Loss: 0.8667\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:50 INFO\u001b[0m Step 38/1000 | Loss: 0.9341\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:50 INFO\u001b[0m Step 38/1000 | Loss: 1.0220\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:50 INFO\u001b[0m Step 38/1000 | Loss: 1.1191\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:50 INFO\u001b[0m Step 39/1000 | Loss: 1.1896\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:50 INFO\u001b[0m Step 39/1000 | Loss: 0.9896\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:50 INFO\u001b[0m Step 39/1000 | Loss: 0.9590\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:50 INFO\u001b[0m Step 39/1000 | Loss: 0.9088\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:50 INFO\u001b[0m Step 39/1000 | Loss: 1.1084\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:50 INFO\u001b[0m Step 39/1000 | Loss: 0.9694\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:50 INFO\u001b[0m Step 39/1000 | Loss: 1.0558\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:50 INFO\u001b[0m Step 39/1000 | Loss: 1.0482\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:51 INFO\u001b[0m Step 40/1000 | Loss: 1.0233\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:51 INFO\u001b[0m Step 40/1000 | Loss: 1.0089\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:51 INFO\u001b[0m Step 40/1000 | Loss: 1.1504\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:51 INFO\u001b[0m Step 40/1000 | Loss: 0.9628\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:51 INFO\u001b[0m Step 40/1000 | Loss: 0.8830\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:51 INFO\u001b[0m Step 40/1000 | Loss: 1.0415\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:51 INFO\u001b[0m Step 40/1000 | Loss: 0.9101\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:51 INFO\u001b[0m Step 40/1000 | Loss: 0.9917\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:51 INFO\u001b[0m Step 41/1000 | Loss: 0.9560\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:51 INFO\u001b[0m Step 41/1000 | Loss: 0.9171\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:51 INFO\u001b[0m Step 41/1000 | Loss: 1.0260\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:51 INFO\u001b[0m Step 41/1000 | Loss: 1.2426\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:51 INFO\u001b[0m Step 41/1000 | Loss: 0.9268\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:51 INFO\u001b[0m Step 41/1000 | Loss: 0.8361\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:51 INFO\u001b[0m Step 41/1000 | Loss: 1.1191\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:51 INFO\u001b[0m Step 41/1000 | Loss: 1.2142\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:52 INFO\u001b[0m Step 42/1000 | Loss: 1.0814\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:52 INFO\u001b[0m Step 42/1000 | Loss: 1.0190\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:52 INFO\u001b[0m Step 42/1000 | Loss: 1.0018\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:52 INFO\u001b[0m Step 42/1000 | Loss: 0.9990\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:52 INFO\u001b[0m Step 42/1000 | Loss: 1.0258\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:52 INFO\u001b[0m Step 42/1000 | Loss: 0.9887\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:52 INFO\u001b[0m Step 42/1000 | Loss: 0.8816\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:52 INFO\u001b[0m Step 42/1000 | Loss: 0.9094\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:52 INFO\u001b[0m Step 43/1000 | Loss: 1.0448\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:52 INFO\u001b[0m Step 43/1000 | Loss: 0.9791\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:52 INFO\u001b[0m Step 43/1000 | Loss: 0.9467\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:52 INFO\u001b[0m Step 43/1000 | Loss: 0.9517\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:52 INFO\u001b[0m Step 43/1000 | Loss: 0.9910\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:52 INFO\u001b[0m Step 43/1000 | Loss: 0.9631\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:52 INFO\u001b[0m Step 43/1000 | Loss: 1.0836\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:52 INFO\u001b[0m Step 43/1000 | Loss: 0.9254\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:52 INFO\u001b[0m Step 44/1000 | Loss: 0.9723\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:52 INFO\u001b[0m Step 44/1000 | Loss: 1.0876\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:52 INFO\u001b[0m Step 44/1000 | Loss: 1.0193\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:52 INFO\u001b[0m Step 44/1000 | Loss: 0.9749\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:52 INFO\u001b[0m Step 44/1000 | Loss: 0.8543\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:52 INFO\u001b[0m Step 44/1000 | Loss: 1.0620\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:52 INFO\u001b[0m Step 44/1000 | Loss: 1.0275\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:52 INFO\u001b[0m Step 44/1000 | Loss: 0.9462\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:53 INFO\u001b[0m Step 45/1000 | Loss: 0.9682\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:53 INFO\u001b[0m Step 45/1000 | Loss: 0.9482\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:53 INFO\u001b[0m Step 45/1000 | Loss: 1.1217\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:53 INFO\u001b[0m Step 45/1000 | Loss: 0.9227\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:53 INFO\u001b[0m Step 45/1000 | Loss: 1.0397\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:53 INFO\u001b[0m Step 45/1000 | Loss: 1.1239\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:53 INFO\u001b[0m Step 45/1000 | Loss: 0.9543\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:53 INFO\u001b[0m Step 45/1000 | Loss: 0.9594\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:57 INFO\u001b[0m Step 46/1000 | Loss: 0.9445\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:57 INFO\u001b[0m Step 46/1000 | Loss: 1.0512\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:57 INFO\u001b[0m Step 46/1000 | Loss: 0.8952\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:57 INFO\u001b[0m Step 46/1000 | Loss: 1.0039\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:57 INFO\u001b[0m Step 46/1000 | Loss: 0.9055\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:57 INFO\u001b[0m Step 46/1000 | Loss: 0.8527\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:57 INFO\u001b[0m Step 46/1000 | Loss: 1.1419\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:57 INFO\u001b[0m Step 46/1000 | Loss: 0.9760\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:29:59 INFO\u001b[0m Step 47/1000 | Loss: 0.9400\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:29:59 INFO\u001b[0m Step 47/1000 | Loss: 0.9331\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:29:59 INFO\u001b[0m Step 47/1000 | Loss: 0.8416\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:29:59 INFO\u001b[0m Step 47/1000 | Loss: 0.9053\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:29:59 INFO\u001b[0m Step 47/1000 | Loss: 0.8874\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:29:59 INFO\u001b[0m Step 47/1000 | Loss: 1.1209\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:29:59 INFO\u001b[0m Step 47/1000 | Loss: 0.7770\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:29:59 INFO\u001b[0m Step 47/1000 | Loss: 1.0493\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:00 INFO\u001b[0m Step 48/1000 | Loss: 1.0498\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:00 INFO\u001b[0m Step 48/1000 | Loss: 1.0481\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:00 INFO\u001b[0m Step 48/1000 | Loss: 1.0515\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:00 INFO\u001b[0m Step 48/1000 | Loss: 1.0068\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:00 INFO\u001b[0m Step 48/1000 | Loss: 0.9388\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:00 INFO\u001b[0m Step 48/1000 | Loss: 1.0956\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:00 INFO\u001b[0m Step 48/1000 | Loss: 1.2315\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:00 INFO\u001b[0m Step 48/1000 | Loss: 0.9992\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:02 INFO\u001b[0m Step 49/1000 | Loss: 1.1007\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:02 INFO\u001b[0m Step 49/1000 | Loss: 1.1678\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:02 INFO\u001b[0m Step 49/1000 | Loss: 1.0103\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:02 INFO\u001b[0m Step 49/1000 | Loss: 1.1387\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:02 INFO\u001b[0m Step 49/1000 | Loss: 1.1931\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:02 INFO\u001b[0m Step 49/1000 | Loss: 0.9916\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:02 INFO\u001b[0m Step 49/1000 | Loss: 1.0917\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:02 INFO\u001b[0m Step 49/1000 | Loss: 1.1419\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:03 INFO\u001b[0m Step 50/1000 | Loss: 1.0470\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:03 INFO\u001b[0m Step 50/1000 | Loss: 1.0311\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:03 INFO\u001b[0m Step 50/1000 | Loss: 0.9165\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:03 INFO\u001b[0m Step 50/1000 | Loss: 1.0287\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:03 INFO\u001b[0m Step 50/1000 | Loss: 1.0265\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:03 INFO\u001b[0m Step 50/1000 | Loss: 1.1687\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:03 INFO\u001b[0m Step 50/1000 | Loss: 1.0076\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:03 INFO\u001b[0m Step 50/1000 | Loss: 0.9719\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:04 INFO\u001b[0m Step 51/1000 | Loss: 1.0981\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:04 INFO\u001b[0m Step 51/1000 | Loss: 1.0375\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:04 INFO\u001b[0m Step 51/1000 | Loss: 0.8971\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:04 INFO\u001b[0m Step 51/1000 | Loss: 0.8202\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:04 INFO\u001b[0m Step 51/1000 | Loss: 1.1967\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:04 INFO\u001b[0m Step 51/1000 | Loss: 1.0116\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:04 INFO\u001b[0m Step 51/1000 | Loss: 1.0970\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:04 INFO\u001b[0m Step 51/1000 | Loss: 1.0448\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:05 INFO\u001b[0m Step 52/1000 | Loss: 1.0701\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:05 INFO\u001b[0m Step 52/1000 | Loss: 1.1670\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:05 INFO\u001b[0m Step 52/1000 | Loss: 0.9936\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:05 INFO\u001b[0m Step 52/1000 | Loss: 1.1187\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:05 INFO\u001b[0m Step 52/1000 | Loss: 1.0121\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:05 INFO\u001b[0m Step 52/1000 | Loss: 0.9685\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:05 INFO\u001b[0m Step 52/1000 | Loss: 1.0895\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:05 INFO\u001b[0m Step 52/1000 | Loss: 1.1017\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:07 INFO\u001b[0m Step 53/1000 | Loss: 1.1078\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:07 INFO\u001b[0m Step 53/1000 | Loss: 0.8239\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:07 INFO\u001b[0m Step 53/1000 | Loss: 1.0768\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:07 INFO\u001b[0m Step 53/1000 | Loss: 0.9070\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:07 INFO\u001b[0m Step 53/1000 | Loss: 0.8923\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:07 INFO\u001b[0m Step 53/1000 | Loss: 1.1030\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:07 INFO\u001b[0m Step 53/1000 | Loss: 0.9835\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:07 INFO\u001b[0m Step 53/1000 | Loss: 0.9724\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:08 INFO\u001b[0m Step 54/1000 | Loss: 0.9572\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:08 INFO\u001b[0m Step 54/1000 | Loss: 1.0448\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:08 INFO\u001b[0m Step 54/1000 | Loss: 1.1087\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:08 INFO\u001b[0m Step 54/1000 | Loss: 0.9813\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:08 INFO\u001b[0m Step 54/1000 | Loss: 1.0937\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:08 INFO\u001b[0m Step 54/1000 | Loss: 1.0167\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:08 INFO\u001b[0m Step 54/1000 | Loss: 0.9354\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:08 INFO\u001b[0m Step 54/1000 | Loss: 0.9827\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:10 INFO\u001b[0m Step 55/1000 | Loss: 1.0809\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:10 INFO\u001b[0m Step 55/1000 | Loss: 0.7487\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:10 INFO\u001b[0m Step 55/1000 | Loss: 1.0298\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:10 INFO\u001b[0m Step 55/1000 | Loss: 1.0203\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:10 INFO\u001b[0m Step 55/1000 | Loss: 0.9536\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:10 INFO\u001b[0m Step 55/1000 | Loss: 1.0290\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:10 INFO\u001b[0m Step 55/1000 | Loss: 1.0048\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:10 INFO\u001b[0m Step 55/1000 | Loss: 1.1168\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:11 INFO\u001b[0m Step 56/1000 | Loss: 0.9375\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:11 INFO\u001b[0m Step 56/1000 | Loss: 1.0186\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:11 INFO\u001b[0m Step 56/1000 | Loss: 1.0825\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:11 INFO\u001b[0m Step 56/1000 | Loss: 1.0466\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:11 INFO\u001b[0m Step 56/1000 | Loss: 0.9534\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:11 INFO\u001b[0m Step 56/1000 | Loss: 0.8788\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:11 INFO\u001b[0m Step 56/1000 | Loss: 0.9957\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:11 INFO\u001b[0m Step 56/1000 | Loss: 1.0098\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:13 INFO\u001b[0m Step 57/1000 | Loss: 0.9761\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:13 INFO\u001b[0m Step 57/1000 | Loss: 1.1847\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:13 INFO\u001b[0m Step 57/1000 | Loss: 1.2257\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:13 INFO\u001b[0m Step 57/1000 | Loss: 1.0285\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:13 INFO\u001b[0m Step 57/1000 | Loss: 0.9142\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:13 INFO\u001b[0m Step 57/1000 | Loss: 1.0717\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:13 INFO\u001b[0m Step 57/1000 | Loss: 0.9683\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:13 INFO\u001b[0m Step 57/1000 | Loss: 1.0905\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:14 INFO\u001b[0m Step 58/1000 | Loss: 1.1025\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:14 INFO\u001b[0m Step 58/1000 | Loss: 1.0335\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:14 INFO\u001b[0m Step 58/1000 | Loss: 1.0325\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:14 INFO\u001b[0m Step 58/1000 | Loss: 1.0167\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:14 INFO\u001b[0m Step 58/1000 | Loss: 1.0203\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:14 INFO\u001b[0m Step 58/1000 | Loss: 0.9829\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:14 INFO\u001b[0m Step 58/1000 | Loss: 1.0285\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:14 INFO\u001b[0m Step 58/1000 | Loss: 1.0330\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:14 INFO\u001b[0m Step 59/1000 | Loss: 1.0447\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:14 INFO\u001b[0m Step 59/1000 | Loss: 0.9965\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:14 INFO\u001b[0m Step 59/1000 | Loss: 0.8882\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:14 INFO\u001b[0m Step 59/1000 | Loss: 0.9593\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:14 INFO\u001b[0m Step 59/1000 | Loss: 1.0264\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:14 INFO\u001b[0m Step 59/1000 | Loss: 0.8997\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:14 INFO\u001b[0m Step 59/1000 | Loss: 1.0400\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:14 INFO\u001b[0m Step 59/1000 | Loss: 1.0282\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:14 INFO\u001b[0m Step 60/1000 | Loss: 0.8096\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:14 INFO\u001b[0m Step 60/1000 | Loss: 1.3307\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:14 INFO\u001b[0m Step 60/1000 | Loss: 0.9422\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:14 INFO\u001b[0m Step 60/1000 | Loss: 0.9740\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:14 INFO\u001b[0m Step 60/1000 | Loss: 1.0037\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:14 INFO\u001b[0m Step 60/1000 | Loss: 0.9892\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:14 INFO\u001b[0m Step 60/1000 | Loss: 0.9616\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:14 INFO\u001b[0m Step 60/1000 | Loss: 0.9210\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:15 INFO\u001b[0m Step 61/1000 | Loss: 0.9884\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:15 INFO\u001b[0m Step 61/1000 | Loss: 0.8824\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:15 INFO\u001b[0m Step 61/1000 | Loss: 0.9705\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:15 INFO\u001b[0m Step 61/1000 | Loss: 1.0535\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:15 INFO\u001b[0m Step 61/1000 | Loss: 1.0640\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:15 INFO\u001b[0m Step 61/1000 | Loss: 0.9976\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:15 INFO\u001b[0m Step 61/1000 | Loss: 1.1072\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:15 INFO\u001b[0m Step 61/1000 | Loss: 1.0550\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:15 INFO\u001b[0m Step 62/1000 | Loss: 0.9491\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:15 INFO\u001b[0m Step 62/1000 | Loss: 0.9713\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:15 INFO\u001b[0m Step 62/1000 | Loss: 1.0506\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:15 INFO\u001b[0m Step 62/1000 | Loss: 1.0437\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:15 INFO\u001b[0m Step 62/1000 | Loss: 1.0270\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:15 INFO\u001b[0m Step 62/1000 | Loss: 0.9185\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:15 INFO\u001b[0m Step 62/1000 | Loss: 0.9452\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:15 INFO\u001b[0m Step 62/1000 | Loss: 1.1129\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:16 INFO\u001b[0m Step 63/1000 | Loss: 0.9946\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:16 INFO\u001b[0m Step 63/1000 | Loss: 0.8790\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:16 INFO\u001b[0m Step 63/1000 | Loss: 0.8930\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:16 INFO\u001b[0m Step 63/1000 | Loss: 0.8602\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:16 INFO\u001b[0m Step 63/1000 | Loss: 0.7797\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:16 INFO\u001b[0m Step 63/1000 | Loss: 1.0123\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:16 INFO\u001b[0m Step 63/1000 | Loss: 1.0458\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:16 INFO\u001b[0m Step 63/1000 | Loss: 0.9944\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:16 INFO\u001b[0m Step 64/1000 | Loss: 0.9594\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:16 INFO\u001b[0m Step 64/1000 | Loss: 1.0161\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:16 INFO\u001b[0m Step 64/1000 | Loss: 0.9369\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:16 INFO\u001b[0m Step 64/1000 | Loss: 1.1053\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:16 INFO\u001b[0m Step 64/1000 | Loss: 0.9143\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:16 INFO\u001b[0m Step 64/1000 | Loss: 1.1343\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:16 INFO\u001b[0m Step 64/1000 | Loss: 1.0670\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:16 INFO\u001b[0m Step 64/1000 | Loss: 0.9924\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:16 INFO\u001b[0m Step 65/1000 | Loss: 0.7691\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:16 INFO\u001b[0m Step 65/1000 | Loss: 0.9632\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:16 INFO\u001b[0m Step 65/1000 | Loss: 1.0088\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:16 INFO\u001b[0m Step 65/1000 | Loss: 0.9502\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:16 INFO\u001b[0m Step 65/1000 | Loss: 0.9354\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:16 INFO\u001b[0m Step 65/1000 | Loss: 0.8622\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:16 INFO\u001b[0m Step 65/1000 | Loss: 1.0214\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:16 INFO\u001b[0m Step 65/1000 | Loss: 0.9543\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:17 INFO\u001b[0m Step 66/1000 | Loss: 1.0491\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:17 INFO\u001b[0m Step 66/1000 | Loss: 0.9517\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:17 INFO\u001b[0m Step 66/1000 | Loss: 0.8958\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:17 INFO\u001b[0m Step 66/1000 | Loss: 1.0436\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:17 INFO\u001b[0m Step 66/1000 | Loss: 0.9232\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:17 INFO\u001b[0m Step 66/1000 | Loss: 0.8964\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:17 INFO\u001b[0m Step 66/1000 | Loss: 1.1364\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:17 INFO\u001b[0m Step 66/1000 | Loss: 0.9983\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:17 INFO\u001b[0m Step 67/1000 | Loss: 1.1395\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:17 INFO\u001b[0m Step 67/1000 | Loss: 1.0419\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:17 INFO\u001b[0m Step 67/1000 | Loss: 0.9226\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:17 INFO\u001b[0m Step 67/1000 | Loss: 0.9779\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:17 INFO\u001b[0m Step 67/1000 | Loss: 0.8769\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:17 INFO\u001b[0m Step 67/1000 | Loss: 0.9660\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:17 INFO\u001b[0m Step 67/1000 | Loss: 0.9743\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:17 INFO\u001b[0m Step 67/1000 | Loss: 0.9257\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:18 INFO\u001b[0m Step 68/1000 | Loss: 1.0591\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:18 INFO\u001b[0m Step 68/1000 | Loss: 0.9655\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:18 INFO\u001b[0m Step 68/1000 | Loss: 0.8018\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:18 INFO\u001b[0m Step 68/1000 | Loss: 0.9737\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:18 INFO\u001b[0m Step 68/1000 | Loss: 1.0210\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:18 INFO\u001b[0m Step 68/1000 | Loss: 1.1171\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:18 INFO\u001b[0m Step 68/1000 | Loss: 0.9239\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:18 INFO\u001b[0m Step 68/1000 | Loss: 0.7785\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:18 INFO\u001b[0m Step 69/1000 | Loss: 0.9779\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:18 INFO\u001b[0m Step 69/1000 | Loss: 0.8503\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:18 INFO\u001b[0m Step 69/1000 | Loss: 0.9048\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:18 INFO\u001b[0m Step 69/1000 | Loss: 1.1071\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:18 INFO\u001b[0m Step 69/1000 | Loss: 0.8989\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:18 INFO\u001b[0m Step 69/1000 | Loss: 1.2273\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:18 INFO\u001b[0m Step 69/1000 | Loss: 0.9401\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:18 INFO\u001b[0m Step 69/1000 | Loss: 1.0582\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:18 INFO\u001b[0m Step 70/1000 | Loss: 1.0826\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:18 INFO\u001b[0m Step 70/1000 | Loss: 0.9937\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:18 INFO\u001b[0m Step 70/1000 | Loss: 0.8617\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:18 INFO\u001b[0m Step 70/1000 | Loss: 0.9534\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:18 INFO\u001b[0m Step 70/1000 | Loss: 1.0220\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:18 INFO\u001b[0m Step 70/1000 | Loss: 1.0263\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:18 INFO\u001b[0m Step 70/1000 | Loss: 0.9505\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:18 INFO\u001b[0m Step 70/1000 | Loss: 0.9565\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:19 INFO\u001b[0m Step 71/1000 | Loss: 0.9810\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:19 INFO\u001b[0m Step 71/1000 | Loss: 0.9985\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:19 INFO\u001b[0m Step 71/1000 | Loss: 0.9852\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:19 INFO\u001b[0m Step 71/1000 | Loss: 0.8515\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:19 INFO\u001b[0m Step 71/1000 | Loss: 0.9725\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:19 INFO\u001b[0m Step 71/1000 | Loss: 0.8996\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:19 INFO\u001b[0m Step 71/1000 | Loss: 1.0146\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:19 INFO\u001b[0m Step 71/1000 | Loss: 0.9074\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:19 INFO\u001b[0m Step 72/1000 | Loss: 0.8564\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:19 INFO\u001b[0m Step 72/1000 | Loss: 0.8561\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:19 INFO\u001b[0m Step 72/1000 | Loss: 0.9918\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:19 INFO\u001b[0m Step 72/1000 | Loss: 1.1235\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:19 INFO\u001b[0m Step 72/1000 | Loss: 0.7941\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:19 INFO\u001b[0m Step 72/1000 | Loss: 0.8241\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:19 INFO\u001b[0m Step 72/1000 | Loss: 0.7750\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:19 INFO\u001b[0m Step 72/1000 | Loss: 0.7728\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:20 INFO\u001b[0m Step 73/1000 | Loss: 0.8477\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:20 INFO\u001b[0m Step 73/1000 | Loss: 0.8557\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:20 INFO\u001b[0m Step 73/1000 | Loss: 0.9792\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:20 INFO\u001b[0m Step 73/1000 | Loss: 1.0990\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:20 INFO\u001b[0m Step 73/1000 | Loss: 0.7838\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:20 INFO\u001b[0m Step 73/1000 | Loss: 1.0150\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:20 INFO\u001b[0m Step 73/1000 | Loss: 1.0613\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:20 INFO\u001b[0m Step 73/1000 | Loss: 0.8713\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:20 INFO\u001b[0m Step 74/1000 | Loss: 0.9550\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:20 INFO\u001b[0m Step 74/1000 | Loss: 0.9270\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:20 INFO\u001b[0m Step 74/1000 | Loss: 0.9854\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:20 INFO\u001b[0m Step 74/1000 | Loss: 0.9021\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:20 INFO\u001b[0m Step 74/1000 | Loss: 1.0546\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:20 INFO\u001b[0m Step 74/1000 | Loss: 0.8928\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:20 INFO\u001b[0m Step 74/1000 | Loss: 0.8409\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:20 INFO\u001b[0m Step 74/1000 | Loss: 0.8813\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:20 INFO\u001b[0m Step 75/1000 | Loss: 0.7709\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:20 INFO\u001b[0m Step 75/1000 | Loss: 0.8987\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:20 INFO\u001b[0m Step 75/1000 | Loss: 0.8976\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:20 INFO\u001b[0m Step 75/1000 | Loss: 0.9728\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:20 INFO\u001b[0m Step 75/1000 | Loss: 1.1824\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:20 INFO\u001b[0m Step 75/1000 | Loss: 0.9257\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:20 INFO\u001b[0m Step 75/1000 | Loss: 0.9428\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:20 INFO\u001b[0m Step 75/1000 | Loss: 0.8584\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:21 INFO\u001b[0m Step 76/1000 | Loss: 1.0167\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:21 INFO\u001b[0m Step 76/1000 | Loss: 0.8489\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:21 INFO\u001b[0m Step 76/1000 | Loss: 0.9238\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:21 INFO\u001b[0m Step 76/1000 | Loss: 1.0529\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:21 INFO\u001b[0m Step 76/1000 | Loss: 1.1424\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:21 INFO\u001b[0m Step 76/1000 | Loss: 1.4425\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:21 INFO\u001b[0m Step 76/1000 | Loss: 0.9455\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:21 INFO\u001b[0m Step 76/1000 | Loss: 0.8370\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:21 INFO\u001b[0m Step 77/1000 | Loss: 1.0682\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:21 INFO\u001b[0m Step 77/1000 | Loss: 0.9502\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:21 INFO\u001b[0m Step 77/1000 | Loss: 0.9016\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:21 INFO\u001b[0m Step 77/1000 | Loss: 0.8172\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:21 INFO\u001b[0m Step 77/1000 | Loss: 1.0765\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:21 INFO\u001b[0m Step 77/1000 | Loss: 0.8142\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:21 INFO\u001b[0m Step 77/1000 | Loss: 0.9789\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:21 INFO\u001b[0m Step 77/1000 | Loss: 0.9538\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:22 INFO\u001b[0m Step 78/1000 | Loss: 0.9946\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:22 INFO\u001b[0m Step 78/1000 | Loss: 1.2093\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:22 INFO\u001b[0m Step 78/1000 | Loss: 1.0085\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:22 INFO\u001b[0m Step 78/1000 | Loss: 1.1235\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:22 INFO\u001b[0m Step 78/1000 | Loss: 0.9271\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:22 INFO\u001b[0m Step 78/1000 | Loss: 0.9066\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:22 INFO\u001b[0m Step 78/1000 | Loss: 0.9585\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:22 INFO\u001b[0m Step 78/1000 | Loss: 0.9856\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:22 INFO\u001b[0m Step 79/1000 | Loss: 1.0132\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:22 INFO\u001b[0m Step 79/1000 | Loss: 0.9371\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:22 INFO\u001b[0m Step 79/1000 | Loss: 1.2662\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:22 INFO\u001b[0m Step 79/1000 | Loss: 0.9950\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:22 INFO\u001b[0m Step 79/1000 | Loss: 1.0856\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:22 INFO\u001b[0m Step 79/1000 | Loss: 0.8086\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:22 INFO\u001b[0m Step 79/1000 | Loss: 0.8718\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:22 INFO\u001b[0m Step 79/1000 | Loss: 0.9709\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:22 INFO\u001b[0m Step 80/1000 | Loss: 0.9630\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:22 INFO\u001b[0m Step 80/1000 | Loss: 1.0502\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:22 INFO\u001b[0m Step 80/1000 | Loss: 0.8834\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:22 INFO\u001b[0m Step 80/1000 | Loss: 1.0077\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:22 INFO\u001b[0m Step 80/1000 | Loss: 1.0670\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:22 INFO\u001b[0m Step 80/1000 | Loss: 0.8442\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:22 INFO\u001b[0m Step 80/1000 | Loss: 1.1299\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:22 INFO\u001b[0m Step 80/1000 | Loss: 0.8690\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:23 INFO\u001b[0m Step 81/1000 | Loss: 0.7690\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:23 INFO\u001b[0m Step 81/1000 | Loss: 0.7857\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:23 INFO\u001b[0m Step 81/1000 | Loss: 0.9820\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:23 INFO\u001b[0m Step 81/1000 | Loss: 0.9708\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:23 INFO\u001b[0m Step 81/1000 | Loss: 0.9439\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:23 INFO\u001b[0m Step 81/1000 | Loss: 1.0652\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:23 INFO\u001b[0m Step 81/1000 | Loss: 1.0583\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:23 INFO\u001b[0m Step 81/1000 | Loss: 0.8803\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:23 INFO\u001b[0m Step 82/1000 | Loss: 1.1389\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:23 INFO\u001b[0m Step 82/1000 | Loss: 1.1820\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:23 INFO\u001b[0m Step 82/1000 | Loss: 0.9937\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:23 INFO\u001b[0m Step 82/1000 | Loss: 0.9717\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:23 INFO\u001b[0m Step 82/1000 | Loss: 1.1301\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:23 INFO\u001b[0m Step 82/1000 | Loss: 1.1265\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:23 INFO\u001b[0m Step 82/1000 | Loss: 0.8828\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:23 INFO\u001b[0m Step 82/1000 | Loss: 0.7260\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:24 INFO\u001b[0m Step 83/1000 | Loss: 1.0259\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:24 INFO\u001b[0m Step 83/1000 | Loss: 1.0595\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:24 INFO\u001b[0m Step 83/1000 | Loss: 0.9970\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:24 INFO\u001b[0m Step 83/1000 | Loss: 1.0484\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:24 INFO\u001b[0m Step 83/1000 | Loss: 1.0491\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:24 INFO\u001b[0m Step 83/1000 | Loss: 1.0322\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:24 INFO\u001b[0m Step 83/1000 | Loss: 0.9856\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:24 INFO\u001b[0m Step 83/1000 | Loss: 1.1826\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:24 INFO\u001b[0m Step 84/1000 | Loss: 0.9745\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:24 INFO\u001b[0m Step 84/1000 | Loss: 1.0247\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:24 INFO\u001b[0m Step 84/1000 | Loss: 1.0940\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:24 INFO\u001b[0m Step 84/1000 | Loss: 1.2375\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:24 INFO\u001b[0m Step 84/1000 | Loss: 1.1795\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:24 INFO\u001b[0m Step 84/1000 | Loss: 0.9165\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:24 INFO\u001b[0m Step 84/1000 | Loss: 0.8976\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:24 INFO\u001b[0m Step 84/1000 | Loss: 1.0118\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:24 INFO\u001b[0m Step 85/1000 | Loss: 1.0408\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:24 INFO\u001b[0m Step 85/1000 | Loss: 0.9008\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:24 INFO\u001b[0m Step 85/1000 | Loss: 1.0729\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:24 INFO\u001b[0m Step 85/1000 | Loss: 0.9570\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:24 INFO\u001b[0m Step 85/1000 | Loss: 1.0965\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:24 INFO\u001b[0m Step 85/1000 | Loss: 1.1270\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:24 INFO\u001b[0m Step 85/1000 | Loss: 1.1767\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:24 INFO\u001b[0m Step 85/1000 | Loss: 1.0945\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:25 INFO\u001b[0m Step 86/1000 | Loss: 0.9720\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:25 INFO\u001b[0m Step 86/1000 | Loss: 1.2018\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:25 INFO\u001b[0m Step 86/1000 | Loss: 1.1314\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:25 INFO\u001b[0m Step 86/1000 | Loss: 1.1257\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:25 INFO\u001b[0m Step 86/1000 | Loss: 1.3427\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:25 INFO\u001b[0m Step 86/1000 | Loss: 1.2849\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:25 INFO\u001b[0m Step 86/1000 | Loss: 1.0665\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:25 INFO\u001b[0m Step 86/1000 | Loss: 1.0474\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:25 INFO\u001b[0m Step 87/1000 | Loss: 0.9797\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:25 INFO\u001b[0m Step 87/1000 | Loss: 1.1269\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:25 INFO\u001b[0m Step 87/1000 | Loss: 1.0752\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:25 INFO\u001b[0m Step 87/1000 | Loss: 1.1548\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:25 INFO\u001b[0m Step 87/1000 | Loss: 1.1626\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:25 INFO\u001b[0m Step 87/1000 | Loss: 1.1831\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:25 INFO\u001b[0m Step 87/1000 | Loss: 1.2178\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:25 INFO\u001b[0m Step 87/1000 | Loss: 1.1346\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:26 INFO\u001b[0m Step 88/1000 | Loss: 1.1331\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:26 INFO\u001b[0m Step 88/1000 | Loss: 1.0561\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:26 INFO\u001b[0m Step 88/1000 | Loss: 1.1064\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:26 INFO\u001b[0m Step 88/1000 | Loss: 0.9457\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:26 INFO\u001b[0m Step 88/1000 | Loss: 1.1091\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:26 INFO\u001b[0m Step 88/1000 | Loss: 1.1552\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:26 INFO\u001b[0m Step 88/1000 | Loss: 1.2024\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:26 INFO\u001b[0m Step 88/1000 | Loss: 1.2001\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:26 INFO\u001b[0m Step 89/1000 | Loss: 1.0634\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:26 INFO\u001b[0m Step 89/1000 | Loss: 1.0423\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:26 INFO\u001b[0m Step 89/1000 | Loss: 1.0971\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:26 INFO\u001b[0m Step 89/1000 | Loss: 1.1564\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:26 INFO\u001b[0m Step 89/1000 | Loss: 1.3253\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:26 INFO\u001b[0m Step 89/1000 | Loss: 0.9730\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:26 INFO\u001b[0m Step 89/1000 | Loss: 0.7643\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:26 INFO\u001b[0m Step 89/1000 | Loss: 1.0753\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:26 INFO\u001b[0m Step 90/1000 | Loss: 1.0254\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:26 INFO\u001b[0m Step 90/1000 | Loss: 1.1939\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:26 INFO\u001b[0m Step 90/1000 | Loss: 1.0326\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:26 INFO\u001b[0m Step 90/1000 | Loss: 1.0765\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:26 INFO\u001b[0m Step 90/1000 | Loss: 1.2181\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:26 INFO\u001b[0m Step 90/1000 | Loss: 1.1173\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:26 INFO\u001b[0m Step 90/1000 | Loss: 1.0702\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:26 INFO\u001b[0m Step 90/1000 | Loss: 0.7801\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:27 INFO\u001b[0m Step 91/1000 | Loss: 0.7613\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:27 INFO\u001b[0m Step 91/1000 | Loss: 1.0201\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:27 INFO\u001b[0m Step 91/1000 | Loss: 1.1208\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:27 INFO\u001b[0m Step 91/1000 | Loss: 1.2158\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:27 INFO\u001b[0m Step 91/1000 | Loss: 1.0419\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:27 INFO\u001b[0m Step 91/1000 | Loss: 1.0559\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:27 INFO\u001b[0m Step 91/1000 | Loss: 1.1162\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:27 INFO\u001b[0m Step 91/1000 | Loss: 0.7695\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:27 INFO\u001b[0m Step 92/1000 | Loss: 1.1146\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:27 INFO\u001b[0m Step 92/1000 | Loss: 0.8982\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:27 INFO\u001b[0m Step 92/1000 | Loss: 1.0280\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:27 INFO\u001b[0m Step 92/1000 | Loss: 1.0027\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:27 INFO\u001b[0m Step 92/1000 | Loss: 0.9979\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:27 INFO\u001b[0m Step 92/1000 | Loss: 1.0191\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:27 INFO\u001b[0m Step 92/1000 | Loss: 0.9405\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:27 INFO\u001b[0m Step 92/1000 | Loss: 1.1057\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:28 INFO\u001b[0m Step 93/1000 | Loss: 0.9568\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:28 INFO\u001b[0m Step 93/1000 | Loss: 0.9520\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:28 INFO\u001b[0m Step 93/1000 | Loss: 0.8781\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:28 INFO\u001b[0m Step 93/1000 | Loss: 0.8049\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:28 INFO\u001b[0m Step 93/1000 | Loss: 0.9058\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:28 INFO\u001b[0m Step 93/1000 | Loss: 0.9293\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:28 INFO\u001b[0m Step 93/1000 | Loss: 1.0633\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:28 INFO\u001b[0m Step 93/1000 | Loss: 1.0792\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:28 INFO\u001b[0m Step 94/1000 | Loss: 1.3957\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:28 INFO\u001b[0m Step 94/1000 | Loss: 1.1406\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:28 INFO\u001b[0m Step 94/1000 | Loss: 1.0382\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:28 INFO\u001b[0m Step 94/1000 | Loss: 1.0836\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:28 INFO\u001b[0m Step 94/1000 | Loss: 1.0680\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:28 INFO\u001b[0m Step 94/1000 | Loss: 0.9012\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:28 INFO\u001b[0m Step 94/1000 | Loss: 1.1095\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:28 INFO\u001b[0m Step 94/1000 | Loss: 0.9798\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:29 INFO\u001b[0m Step 95/1000 | Loss: 0.8892\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:29 INFO\u001b[0m Step 95/1000 | Loss: 0.7959\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:29 INFO\u001b[0m Step 95/1000 | Loss: 1.0649\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:29 INFO\u001b[0m Step 95/1000 | Loss: 0.9476\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:29 INFO\u001b[0m Step 95/1000 | Loss: 0.9493\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:29 INFO\u001b[0m Step 95/1000 | Loss: 0.9098\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:29 INFO\u001b[0m Step 95/1000 | Loss: 0.9239\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:29 INFO\u001b[0m Step 95/1000 | Loss: 1.1872\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:29 INFO\u001b[0m Step 96/1000 | Loss: 1.0143\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:29 INFO\u001b[0m Step 96/1000 | Loss: 0.9310\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:29 INFO\u001b[0m Step 96/1000 | Loss: 0.9515\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:29 INFO\u001b[0m Step 96/1000 | Loss: 0.8395\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:29 INFO\u001b[0m Step 96/1000 | Loss: 1.2317\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:29 INFO\u001b[0m Step 96/1000 | Loss: 1.0054\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:29 INFO\u001b[0m Step 96/1000 | Loss: 1.0672\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:29 INFO\u001b[0m Step 96/1000 | Loss: 0.9696\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:29 INFO\u001b[0m Step 97/1000 | Loss: 1.0617\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:29 INFO\u001b[0m Step 97/1000 | Loss: 1.0646\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:29 INFO\u001b[0m Step 97/1000 | Loss: 1.0264\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:29 INFO\u001b[0m Step 97/1000 | Loss: 0.9442\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:29 INFO\u001b[0m Step 97/1000 | Loss: 1.1318\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:29 INFO\u001b[0m Step 97/1000 | Loss: 0.9109\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:29 INFO\u001b[0m Step 97/1000 | Loss: 0.9949\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:29 INFO\u001b[0m Step 97/1000 | Loss: 0.9550\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:30 INFO\u001b[0m Step 98/1000 | Loss: 1.0676\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:30 INFO\u001b[0m Step 98/1000 | Loss: 0.9432\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:30 INFO\u001b[0m Step 98/1000 | Loss: 1.1123\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:30 INFO\u001b[0m Step 98/1000 | Loss: 1.0898\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:30 INFO\u001b[0m Step 98/1000 | Loss: 1.0599\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:30 INFO\u001b[0m Step 98/1000 | Loss: 0.7143\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:30 INFO\u001b[0m Step 98/1000 | Loss: 1.0470\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:30 INFO\u001b[0m Step 98/1000 | Loss: 1.0520\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:30 INFO\u001b[0m Step 99/1000 | Loss: 1.0754\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:30 INFO\u001b[0m Step 99/1000 | Loss: 0.9803\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:30 INFO\u001b[0m Step 99/1000 | Loss: 0.9966\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:30 INFO\u001b[0m Step 99/1000 | Loss: 1.0954\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:30 INFO\u001b[0m Step 99/1000 | Loss: 1.0054\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:30 INFO\u001b[0m Step 99/1000 | Loss: 1.1771\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:30 INFO\u001b[0m Step 99/1000 | Loss: 1.2330\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:30 INFO\u001b[0m Step 99/1000 | Loss: 0.9606\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:31 INFO\u001b[0m Step 100/1000 | Loss: 0.9624\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:31 INFO\u001b[0m Step 100/1000 | Loss: 1.0085\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:31 INFO\u001b[0m Step 100/1000 | Loss: 1.0576\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:31 INFO\u001b[0m Step 100/1000 | Loss: 1.0218\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:31 INFO\u001b[0m Step 100/1000 | Loss: 1.0235\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:31 INFO\u001b[0m Step 100/1000 | Loss: 1.1473\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:31 INFO\u001b[0m Step 100/1000 | Loss: 1.0490\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:31 INFO\u001b[0m Step 100/1000 | Loss: 1.0173\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:31 INFO\u001b[0m Step 101/1000 | Loss: 1.1222\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:31 INFO\u001b[0m Step 101/1000 | Loss: 1.1663\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:31 INFO\u001b[0m Step 101/1000 | Loss: 0.9910\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:31 INFO\u001b[0m Step 101/1000 | Loss: 0.9884\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:31 INFO\u001b[0m Step 101/1000 | Loss: 1.0445\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:31 INFO\u001b[0m Step 101/1000 | Loss: 1.0188\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:31 INFO\u001b[0m Step 101/1000 | Loss: 1.2513\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:31 INFO\u001b[0m Step 101/1000 | Loss: 1.1537\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:31 INFO\u001b[0m Step 102/1000 | Loss: 1.0350\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:31 INFO\u001b[0m Step 102/1000 | Loss: 1.1486\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:31 INFO\u001b[0m Step 102/1000 | Loss: 1.0584\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:31 INFO\u001b[0m Step 102/1000 | Loss: 1.1149\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:31 INFO\u001b[0m Step 102/1000 | Loss: 1.0373\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:31 INFO\u001b[0m Step 102/1000 | Loss: 1.2353\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:31 INFO\u001b[0m Step 102/1000 | Loss: 1.1288\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:31 INFO\u001b[0m Step 102/1000 | Loss: 1.1870\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:32 INFO\u001b[0m Step 103/1000 | Loss: 1.2458\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:32 INFO\u001b[0m Step 103/1000 | Loss: 1.1263\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:32 INFO\u001b[0m Step 103/1000 | Loss: 1.1349\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:32 INFO\u001b[0m Step 103/1000 | Loss: 1.1308\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:32 INFO\u001b[0m Step 103/1000 | Loss: 1.0371\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:32 INFO\u001b[0m Step 103/1000 | Loss: 1.2094\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:32 INFO\u001b[0m Step 103/1000 | Loss: 1.1038\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:32 INFO\u001b[0m Step 103/1000 | Loss: 1.2104\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:32 INFO\u001b[0m Step 104/1000 | Loss: 1.2286\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:32 INFO\u001b[0m Step 104/1000 | Loss: 1.3978\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:32 INFO\u001b[0m Step 104/1000 | Loss: 1.2518\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:32 INFO\u001b[0m Step 104/1000 | Loss: 1.1685\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:32 INFO\u001b[0m Step 104/1000 | Loss: 1.4223\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:32 INFO\u001b[0m Step 104/1000 | Loss: 1.3847\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:32 INFO\u001b[0m Step 104/1000 | Loss: 1.1416\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:32 INFO\u001b[0m Step 104/1000 | Loss: 1.2531\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:33 INFO\u001b[0m Step 105/1000 | Loss: 1.1172\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:33 INFO\u001b[0m Step 105/1000 | Loss: 1.3060\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:33 INFO\u001b[0m Step 105/1000 | Loss: 1.3071\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:33 INFO\u001b[0m Step 105/1000 | Loss: 1.2278\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:33 INFO\u001b[0m Step 105/1000 | Loss: 1.2930\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:33 INFO\u001b[0m Step 105/1000 | Loss: 1.3564\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:33 INFO\u001b[0m Step 105/1000 | Loss: 1.2123\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:33 INFO\u001b[0m Step 105/1000 | Loss: 1.2396\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:33 INFO\u001b[0m Step 106/1000 | Loss: 1.3123\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:33 INFO\u001b[0m Step 106/1000 | Loss: 1.3971\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:33 INFO\u001b[0m Step 106/1000 | Loss: 1.3159\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:33 INFO\u001b[0m Step 106/1000 | Loss: 1.2722\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:33 INFO\u001b[0m Step 106/1000 | Loss: 1.1681\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:33 INFO\u001b[0m Step 106/1000 | Loss: 1.1131\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:33 INFO\u001b[0m Step 106/1000 | Loss: 1.2467\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:33 INFO\u001b[0m Step 106/1000 | Loss: 1.3992\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:33 INFO\u001b[0m Step 107/1000 | Loss: 1.2009\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:33 INFO\u001b[0m Step 107/1000 | Loss: 1.4639\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:33 INFO\u001b[0m Step 107/1000 | Loss: 1.2744\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:33 INFO\u001b[0m Step 107/1000 | Loss: 1.3540\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:33 INFO\u001b[0m Step 107/1000 | Loss: 1.2983\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:33 INFO\u001b[0m Step 107/1000 | Loss: 1.4286\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:33 INFO\u001b[0m Step 107/1000 | Loss: 1.2015\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:33 INFO\u001b[0m Step 107/1000 | Loss: 1.4520\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:34 INFO\u001b[0m Step 108/1000 | Loss: 1.3699\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:34 INFO\u001b[0m Step 108/1000 | Loss: 1.3693\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:34 INFO\u001b[0m Step 108/1000 | Loss: 1.6012\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:34 INFO\u001b[0m Step 108/1000 | Loss: 1.2872\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:34 INFO\u001b[0m Step 108/1000 | Loss: 1.3067\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:34 INFO\u001b[0m Step 108/1000 | Loss: 1.3896\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:34 INFO\u001b[0m Step 108/1000 | Loss: 1.4322\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:34 INFO\u001b[0m Step 108/1000 | Loss: 1.3292\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:34 INFO\u001b[0m Step 109/1000 | Loss: 1.3802\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:34 INFO\u001b[0m Step 109/1000 | Loss: 1.4904\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:34 INFO\u001b[0m Step 109/1000 | Loss: 1.4370\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:34 INFO\u001b[0m Step 109/1000 | Loss: 1.2139\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:34 INFO\u001b[0m Step 109/1000 | Loss: 1.4110\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:34 INFO\u001b[0m Step 109/1000 | Loss: 1.3543\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:34 INFO\u001b[0m Step 109/1000 | Loss: 1.3566\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:34 INFO\u001b[0m Step 109/1000 | Loss: 1.4225\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:35 INFO\u001b[0m Step 110/1000 | Loss: 1.2054\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:35 INFO\u001b[0m Step 110/1000 | Loss: 1.4499\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:35 INFO\u001b[0m Step 110/1000 | Loss: 1.7039\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:35 INFO\u001b[0m Step 110/1000 | Loss: 1.2176\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:35 INFO\u001b[0m Step 110/1000 | Loss: 1.2237\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:35 INFO\u001b[0m Step 110/1000 | Loss: 1.1856\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:35 INFO\u001b[0m Step 110/1000 | Loss: 1.2662\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:35 INFO\u001b[0m Step 110/1000 | Loss: 1.3681\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:35 INFO\u001b[0m Step 111/1000 | Loss: 1.2133\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:35 INFO\u001b[0m Step 111/1000 | Loss: 1.2008\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:35 INFO\u001b[0m Step 111/1000 | Loss: 1.1963\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:35 INFO\u001b[0m Step 111/1000 | Loss: 1.4264\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:35 INFO\u001b[0m Step 111/1000 | Loss: 1.2700\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:35 INFO\u001b[0m Step 111/1000 | Loss: 1.3565\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:35 INFO\u001b[0m Step 111/1000 | Loss: 1.2313\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:35 INFO\u001b[0m Step 111/1000 | Loss: 1.1572\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:35 INFO\u001b[0m Step 112/1000 | Loss: 1.2534\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:35 INFO\u001b[0m Step 112/1000 | Loss: 0.9165\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:35 INFO\u001b[0m Step 112/1000 | Loss: 1.6458\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:35 INFO\u001b[0m Step 112/1000 | Loss: 1.1170\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:35 INFO\u001b[0m Step 112/1000 | Loss: 1.2680\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:35 INFO\u001b[0m Step 112/1000 | Loss: 1.1718\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:35 INFO\u001b[0m Step 112/1000 | Loss: 1.1884\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:35 INFO\u001b[0m Step 112/1000 | Loss: 0.9829\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:36 INFO\u001b[0m Step 113/1000 | Loss: 1.1538\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:36 INFO\u001b[0m Step 113/1000 | Loss: 1.3362\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:36 INFO\u001b[0m Step 113/1000 | Loss: 1.1941\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:36 INFO\u001b[0m Step 113/1000 | Loss: 1.2647\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:36 INFO\u001b[0m Step 113/1000 | Loss: 1.3951\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:36 INFO\u001b[0m Step 113/1000 | Loss: 1.2408\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:36 INFO\u001b[0m Step 113/1000 | Loss: 1.1992\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:36 INFO\u001b[0m Step 113/1000 | Loss: 1.1333\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:36 INFO\u001b[0m Step 114/1000 | Loss: 1.2549\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:36 INFO\u001b[0m Step 114/1000 | Loss: 1.1920\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:36 INFO\u001b[0m Step 114/1000 | Loss: 1.1275\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:36 INFO\u001b[0m Step 114/1000 | Loss: 1.2564\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:36 INFO\u001b[0m Step 114/1000 | Loss: 1.1194\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:36 INFO\u001b[0m Step 114/1000 | Loss: 1.1657\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:36 INFO\u001b[0m Step 114/1000 | Loss: 0.8976\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:36 INFO\u001b[0m Step 114/1000 | Loss: 1.0513\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:37 INFO\u001b[0m Step 115/1000 | Loss: 1.0520\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:37 INFO\u001b[0m Step 115/1000 | Loss: 0.8113\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:37 INFO\u001b[0m Step 115/1000 | Loss: 1.1134\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:37 INFO\u001b[0m Step 115/1000 | Loss: 1.0730\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:37 INFO\u001b[0m Step 115/1000 | Loss: 1.1569\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:37 INFO\u001b[0m Step 115/1000 | Loss: 1.0890\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:37 INFO\u001b[0m Step 115/1000 | Loss: 1.2788\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:37 INFO\u001b[0m Step 115/1000 | Loss: 1.2997\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:37 INFO\u001b[0m Step 116/1000 | Loss: 1.0046\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:37 INFO\u001b[0m Step 116/1000 | Loss: 0.9365\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:37 INFO\u001b[0m Step 116/1000 | Loss: 0.9686\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:37 INFO\u001b[0m Step 116/1000 | Loss: 1.1352\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:37 INFO\u001b[0m Step 116/1000 | Loss: 1.2117\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:37 INFO\u001b[0m Step 116/1000 | Loss: 1.0829\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:37 INFO\u001b[0m Step 116/1000 | Loss: 1.1690\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:37 INFO\u001b[0m Step 116/1000 | Loss: 1.1511\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:37 INFO\u001b[0m Step 117/1000 | Loss: 1.2246\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:37 INFO\u001b[0m Step 117/1000 | Loss: 1.2951\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:37 INFO\u001b[0m Step 117/1000 | Loss: 1.1315\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:37 INFO\u001b[0m Step 117/1000 | Loss: 1.1051\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:37 INFO\u001b[0m Step 117/1000 | Loss: 0.9157\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:37 INFO\u001b[0m Step 117/1000 | Loss: 1.0672\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:37 INFO\u001b[0m Step 117/1000 | Loss: 1.1817\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:37 INFO\u001b[0m Step 117/1000 | Loss: 0.9357\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:38 INFO\u001b[0m Step 118/1000 | Loss: 0.8317\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:38 INFO\u001b[0m Step 118/1000 | Loss: 1.1118\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:38 INFO\u001b[0m Step 118/1000 | Loss: 1.0907\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:38 INFO\u001b[0m Step 118/1000 | Loss: 1.0850\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:38 INFO\u001b[0m Step 118/1000 | Loss: 1.2240\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:38 INFO\u001b[0m Step 118/1000 | Loss: 1.0952\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:38 INFO\u001b[0m Step 118/1000 | Loss: 1.0378\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:38 INFO\u001b[0m Step 118/1000 | Loss: 0.9797\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:38 INFO\u001b[0m Step 119/1000 | Loss: 1.0835\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:38 INFO\u001b[0m Step 119/1000 | Loss: 0.9438\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:38 INFO\u001b[0m Step 119/1000 | Loss: 1.2526\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:38 INFO\u001b[0m Step 119/1000 | Loss: 1.2777\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:38 INFO\u001b[0m Step 119/1000 | Loss: 0.9857\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:38 INFO\u001b[0m Step 119/1000 | Loss: 1.0453\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:38 INFO\u001b[0m Step 119/1000 | Loss: 1.0276\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:38 INFO\u001b[0m Step 119/1000 | Loss: 1.0568\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:39 INFO\u001b[0m Step 120/1000 | Loss: 1.3926\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:39 INFO\u001b[0m Step 120/1000 | Loss: 1.2288\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:39 INFO\u001b[0m Step 120/1000 | Loss: 1.1360\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:39 INFO\u001b[0m Step 120/1000 | Loss: 1.1828\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:39 INFO\u001b[0m Step 120/1000 | Loss: 1.3302\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:39 INFO\u001b[0m Step 120/1000 | Loss: 1.2380\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:39 INFO\u001b[0m Step 120/1000 | Loss: 1.2234\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:39 INFO\u001b[0m Step 120/1000 | Loss: 1.3858\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:39 INFO\u001b[0m Step 121/1000 | Loss: 1.1959\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:39 INFO\u001b[0m Step 121/1000 | Loss: 0.8828\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:39 INFO\u001b[0m Step 121/1000 | Loss: 1.1791\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:39 INFO\u001b[0m Step 121/1000 | Loss: 1.2543\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:39 INFO\u001b[0m Step 121/1000 | Loss: 1.3168\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:39 INFO\u001b[0m Step 121/1000 | Loss: 1.0570\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:39 INFO\u001b[0m Step 121/1000 | Loss: 1.2369\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:39 INFO\u001b[0m Step 121/1000 | Loss: 1.0872\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:39 INFO\u001b[0m Step 122/1000 | Loss: 1.1590\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:39 INFO\u001b[0m Step 122/1000 | Loss: 1.2160\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:39 INFO\u001b[0m Step 122/1000 | Loss: 1.4571\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:39 INFO\u001b[0m Step 122/1000 | Loss: 1.2108\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:39 INFO\u001b[0m Step 122/1000 | Loss: 1.1637\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:39 INFO\u001b[0m Step 122/1000 | Loss: 1.2818\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:39 INFO\u001b[0m Step 122/1000 | Loss: 1.2697\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:39 INFO\u001b[0m Step 122/1000 | Loss: 1.2718\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:40 INFO\u001b[0m Step 123/1000 | Loss: 1.2208\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:40 INFO\u001b[0m Step 123/1000 | Loss: 1.2139\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:40 INFO\u001b[0m Step 123/1000 | Loss: 1.4513\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:40 INFO\u001b[0m Step 123/1000 | Loss: 1.4174\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:40 INFO\u001b[0m Step 123/1000 | Loss: 1.3896\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:40 INFO\u001b[0m Step 123/1000 | Loss: 1.3221\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:40 INFO\u001b[0m Step 123/1000 | Loss: 1.2056\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:40 INFO\u001b[0m Step 123/1000 | Loss: 1.2651\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:40 INFO\u001b[0m Step 124/1000 | Loss: 1.4443\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:40 INFO\u001b[0m Step 124/1000 | Loss: 1.2415\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:40 INFO\u001b[0m Step 124/1000 | Loss: 1.4455\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:40 INFO\u001b[0m Step 124/1000 | Loss: 1.3139\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:40 INFO\u001b[0m Step 124/1000 | Loss: 1.3933\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:40 INFO\u001b[0m Step 124/1000 | Loss: 1.5063\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:40 INFO\u001b[0m Step 124/1000 | Loss: 1.3037\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:40 INFO\u001b[0m Step 124/1000 | Loss: 1.4923\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:41 INFO\u001b[0m Step 125/1000 | Loss: 1.4964\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:41 INFO\u001b[0m Step 125/1000 | Loss: 1.4537\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:41 INFO\u001b[0m Step 125/1000 | Loss: 1.6384\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:41 INFO\u001b[0m Step 125/1000 | Loss: 1.7246\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:41 INFO\u001b[0m Step 125/1000 | Loss: 1.3688\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:41 INFO\u001b[0m Step 125/1000 | Loss: 1.3511\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:41 INFO\u001b[0m Step 125/1000 | Loss: 1.6042\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:41 INFO\u001b[0m Step 125/1000 | Loss: 1.1678\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:41 INFO\u001b[0m Step 126/1000 | Loss: 1.4828\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:41 INFO\u001b[0m Step 126/1000 | Loss: 1.5265\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:41 INFO\u001b[0m Step 126/1000 | Loss: 1.7700\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:41 INFO\u001b[0m Step 126/1000 | Loss: 1.8133\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:41 INFO\u001b[0m Step 126/1000 | Loss: 1.2879\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:41 INFO\u001b[0m Step 126/1000 | Loss: 1.3493\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:41 INFO\u001b[0m Step 126/1000 | Loss: 1.7286\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:41 INFO\u001b[0m Step 126/1000 | Loss: 1.5770\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:41 INFO\u001b[0m Step 127/1000 | Loss: 1.6668\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:41 INFO\u001b[0m Step 127/1000 | Loss: 1.6976\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:41 INFO\u001b[0m Step 127/1000 | Loss: 1.5806\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:41 INFO\u001b[0m Step 127/1000 | Loss: 1.3177\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:41 INFO\u001b[0m Step 127/1000 | Loss: 1.4677\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:41 INFO\u001b[0m Step 127/1000 | Loss: 1.7665\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:41 INFO\u001b[0m Step 127/1000 | Loss: 1.6641\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:41 INFO\u001b[0m Step 127/1000 | Loss: 1.4287\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:42 INFO\u001b[0m Step 128/1000 | Loss: 1.0999\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:42 INFO\u001b[0m Step 128/1000 | Loss: 1.6294\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:42 INFO\u001b[0m Step 128/1000 | Loss: 1.4409\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:42 INFO\u001b[0m Step 128/1000 | Loss: 1.6373\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:42 INFO\u001b[0m Step 128/1000 | Loss: 1.4886\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:42 INFO\u001b[0m Step 128/1000 | Loss: 1.5794\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:42 INFO\u001b[0m Step 128/1000 | Loss: 1.7891\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:42 INFO\u001b[0m Step 128/1000 | Loss: 1.6916\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:42 INFO\u001b[0m Step 129/1000 | Loss: 1.4989\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:42 INFO\u001b[0m Step 129/1000 | Loss: 1.5867\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:42 INFO\u001b[0m Step 129/1000 | Loss: 1.4453\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:42 INFO\u001b[0m Step 129/1000 | Loss: 1.4341\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:42 INFO\u001b[0m Step 129/1000 | Loss: 1.6650\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:42 INFO\u001b[0m Step 129/1000 | Loss: 1.4663\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:42 INFO\u001b[0m Step 129/1000 | Loss: 1.6166\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:42 INFO\u001b[0m Step 129/1000 | Loss: 1.6606\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:43 INFO\u001b[0m Step 130/1000 | Loss: 1.5885\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:43 INFO\u001b[0m Step 130/1000 | Loss: 1.9169\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:43 INFO\u001b[0m Step 130/1000 | Loss: 1.4171\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:43 INFO\u001b[0m Step 130/1000 | Loss: 1.6500\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:43 INFO\u001b[0m Step 130/1000 | Loss: 1.6026\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:43 INFO\u001b[0m Step 130/1000 | Loss: 1.5929\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:43 INFO\u001b[0m Step 130/1000 | Loss: 1.6801\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:43 INFO\u001b[0m Step 130/1000 | Loss: 1.4929\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:43 INFO\u001b[0m Step 131/1000 | Loss: 1.5340\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:43 INFO\u001b[0m Step 131/1000 | Loss: 1.5014\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:43 INFO\u001b[0m Step 131/1000 | Loss: 1.6685\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:43 INFO\u001b[0m Step 131/1000 | Loss: 1.7188\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:43 INFO\u001b[0m Step 131/1000 | Loss: 1.6420\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:43 INFO\u001b[0m Step 131/1000 | Loss: 1.6331\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:43 INFO\u001b[0m Step 131/1000 | Loss: 1.5484\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:43 INFO\u001b[0m Step 131/1000 | Loss: 1.6338\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:43 INFO\u001b[0m Step 132/1000 | Loss: 1.6289\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:43 INFO\u001b[0m Step 132/1000 | Loss: 1.2401\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:43 INFO\u001b[0m Step 132/1000 | Loss: 1.4715\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:43 INFO\u001b[0m Step 132/1000 | Loss: 1.8011\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:43 INFO\u001b[0m Step 132/1000 | Loss: 1.7237\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:43 INFO\u001b[0m Step 132/1000 | Loss: 1.4155\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:43 INFO\u001b[0m Step 132/1000 | Loss: 1.5451\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:43 INFO\u001b[0m Step 132/1000 | Loss: 1.6162\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:44 INFO\u001b[0m Step 133/1000 | Loss: 1.3715\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:44 INFO\u001b[0m Step 133/1000 | Loss: 1.7039\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:44 INFO\u001b[0m Step 133/1000 | Loss: 1.2446\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:44 INFO\u001b[0m Step 133/1000 | Loss: 1.4144\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:44 INFO\u001b[0m Step 133/1000 | Loss: 1.6142\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:44 INFO\u001b[0m Step 133/1000 | Loss: 1.3584\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:44 INFO\u001b[0m Step 133/1000 | Loss: 1.3503\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:44 INFO\u001b[0m Step 133/1000 | Loss: 1.6129\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:44 INFO\u001b[0m Step 134/1000 | Loss: 1.3161\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:44 INFO\u001b[0m Step 134/1000 | Loss: 1.6613\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:44 INFO\u001b[0m Step 134/1000 | Loss: 1.3963\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:44 INFO\u001b[0m Step 134/1000 | Loss: 1.3945\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:44 INFO\u001b[0m Step 134/1000 | Loss: 1.4578\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:44 INFO\u001b[0m Step 134/1000 | Loss: 1.5456\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:44 INFO\u001b[0m Step 134/1000 | Loss: 1.5150\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:44 INFO\u001b[0m Step 134/1000 | Loss: 1.7146\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:45 INFO\u001b[0m Step 135/1000 | Loss: 1.2079\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:45 INFO\u001b[0m Step 135/1000 | Loss: 1.5587\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:45 INFO\u001b[0m Step 135/1000 | Loss: 1.2986\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:45 INFO\u001b[0m Step 135/1000 | Loss: 1.2785\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:45 INFO\u001b[0m Step 135/1000 | Loss: 1.2879\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:45 INFO\u001b[0m Step 135/1000 | Loss: 1.4035\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:45 INFO\u001b[0m Step 135/1000 | Loss: 1.4493\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:45 INFO\u001b[0m Step 135/1000 | Loss: 1.4698\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:45 INFO\u001b[0m Step 136/1000 | Loss: 1.2427\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:45 INFO\u001b[0m Step 136/1000 | Loss: 1.1809\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:45 INFO\u001b[0m Step 136/1000 | Loss: 1.0999\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:45 INFO\u001b[0m Step 136/1000 | Loss: 1.4929\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:45 INFO\u001b[0m Step 136/1000 | Loss: 1.1424\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:45 INFO\u001b[0m Step 136/1000 | Loss: 1.3558\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:45 INFO\u001b[0m Step 136/1000 | Loss: 1.2705\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:45 INFO\u001b[0m Step 136/1000 | Loss: 1.3851\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:45 INFO\u001b[0m Step 137/1000 | Loss: 1.4234\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:45 INFO\u001b[0m Step 137/1000 | Loss: 1.0990\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:45 INFO\u001b[0m Step 137/1000 | Loss: 1.2041\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:45 INFO\u001b[0m Step 137/1000 | Loss: 1.2406\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:45 INFO\u001b[0m Step 137/1000 | Loss: 1.1673\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:45 INFO\u001b[0m Step 137/1000 | Loss: 1.1379\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:45 INFO\u001b[0m Step 137/1000 | Loss: 1.3608\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:45 INFO\u001b[0m Step 137/1000 | Loss: 1.3651\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:46 INFO\u001b[0m Step 138/1000 | Loss: 1.1666\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:46 INFO\u001b[0m Step 138/1000 | Loss: 1.0991\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:46 INFO\u001b[0m Step 138/1000 | Loss: 1.0449\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:46 INFO\u001b[0m Step 138/1000 | Loss: 1.2495\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:46 INFO\u001b[0m Step 138/1000 | Loss: 1.2421\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:46 INFO\u001b[0m Step 138/1000 | Loss: 1.1652\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:46 INFO\u001b[0m Step 138/1000 | Loss: 1.3030\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:46 INFO\u001b[0m Step 138/1000 | Loss: 1.2649\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:46 INFO\u001b[0m Step 139/1000 | Loss: 1.3416\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:46 INFO\u001b[0m Step 139/1000 | Loss: 1.0342\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:46 INFO\u001b[0m Step 139/1000 | Loss: 1.0766\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:46 INFO\u001b[0m Step 139/1000 | Loss: 0.9619\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:46 INFO\u001b[0m Step 139/1000 | Loss: 1.1809\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:46 INFO\u001b[0m Step 139/1000 | Loss: 1.0108\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:46 INFO\u001b[0m Step 139/1000 | Loss: 1.1236\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:46 INFO\u001b[0m Step 139/1000 | Loss: 1.1635\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:47 INFO\u001b[0m Step 140/1000 | Loss: 1.1276\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:47 INFO\u001b[0m Step 140/1000 | Loss: 1.1417\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:47 INFO\u001b[0m Step 140/1000 | Loss: 1.0346\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:47 INFO\u001b[0m Step 140/1000 | Loss: 1.3511\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:47 INFO\u001b[0m Step 140/1000 | Loss: 1.0582\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:47 INFO\u001b[0m Step 140/1000 | Loss: 1.1445\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:47 INFO\u001b[0m Step 140/1000 | Loss: 0.9733\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:47 INFO\u001b[0m Step 140/1000 | Loss: 1.1015\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:47 INFO\u001b[0m Step 141/1000 | Loss: 1.2692\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:47 INFO\u001b[0m Step 141/1000 | Loss: 1.2753\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:47 INFO\u001b[0m Step 141/1000 | Loss: 1.0419\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:47 INFO\u001b[0m Step 141/1000 | Loss: 0.9958\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:47 INFO\u001b[0m Step 141/1000 | Loss: 1.2668\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:47 INFO\u001b[0m Step 141/1000 | Loss: 1.2928\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:47 INFO\u001b[0m Step 141/1000 | Loss: 1.1498\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:47 INFO\u001b[0m Step 141/1000 | Loss: 1.2613\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:47 INFO\u001b[0m Step 142/1000 | Loss: 1.1722\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:47 INFO\u001b[0m Step 142/1000 | Loss: 1.2165\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:47 INFO\u001b[0m Step 142/1000 | Loss: 1.2343\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:47 INFO\u001b[0m Step 142/1000 | Loss: 1.1547\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:47 INFO\u001b[0m Step 142/1000 | Loss: 1.1812\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:47 INFO\u001b[0m Step 142/1000 | Loss: 1.1820\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:47 INFO\u001b[0m Step 142/1000 | Loss: 1.1160\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:47 INFO\u001b[0m Step 142/1000 | Loss: 1.1494\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:48 INFO\u001b[0m Step 143/1000 | Loss: 1.1729\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:48 INFO\u001b[0m Step 143/1000 | Loss: 1.1593\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:48 INFO\u001b[0m Step 143/1000 | Loss: 1.1254\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:48 INFO\u001b[0m Step 143/1000 | Loss: 1.2815\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:48 INFO\u001b[0m Step 143/1000 | Loss: 1.2326\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:48 INFO\u001b[0m Step 143/1000 | Loss: 1.4765\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:48 INFO\u001b[0m Step 143/1000 | Loss: 1.1122\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:48 INFO\u001b[0m Step 143/1000 | Loss: 1.4034\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:48 INFO\u001b[0m Step 144/1000 | Loss: 1.3174\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:48 INFO\u001b[0m Step 144/1000 | Loss: 1.3743\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:48 INFO\u001b[0m Step 144/1000 | Loss: 1.0691\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:48 INFO\u001b[0m Step 144/1000 | Loss: 1.2908\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:48 INFO\u001b[0m Step 144/1000 | Loss: 1.4302\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:48 INFO\u001b[0m Step 144/1000 | Loss: 1.1389\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:48 INFO\u001b[0m Step 144/1000 | Loss: 1.2198\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:48 INFO\u001b[0m Step 144/1000 | Loss: 1.2160\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:49 INFO\u001b[0m Step 145/1000 | Loss: 1.3576\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:49 INFO\u001b[0m Step 145/1000 | Loss: 1.0395\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:49 INFO\u001b[0m Step 145/1000 | Loss: 1.0939\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:49 INFO\u001b[0m Step 145/1000 | Loss: 1.2473\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:49 INFO\u001b[0m Step 145/1000 | Loss: 1.3810\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:49 INFO\u001b[0m Step 145/1000 | Loss: 1.3484\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:49 INFO\u001b[0m Step 145/1000 | Loss: 1.1256\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:49 INFO\u001b[0m Step 145/1000 | Loss: 1.3865\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:49 INFO\u001b[0m Step 146/1000 | Loss: 1.5712\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:49 INFO\u001b[0m Step 146/1000 | Loss: 1.3878\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:49 INFO\u001b[0m Step 146/1000 | Loss: 1.6089\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:49 INFO\u001b[0m Step 146/1000 | Loss: 1.4531\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:49 INFO\u001b[0m Step 146/1000 | Loss: 1.4323\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:49 INFO\u001b[0m Step 146/1000 | Loss: 1.0384\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:49 INFO\u001b[0m Step 146/1000 | Loss: 1.6090\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:49 INFO\u001b[0m Step 146/1000 | Loss: 1.4360\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:49 INFO\u001b[0m Step 147/1000 | Loss: 1.6903\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:49 INFO\u001b[0m Step 147/1000 | Loss: 1.3963\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:49 INFO\u001b[0m Step 147/1000 | Loss: 1.6919\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:49 INFO\u001b[0m Step 147/1000 | Loss: 1.5659\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:49 INFO\u001b[0m Step 147/1000 | Loss: 1.6307\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:49 INFO\u001b[0m Step 147/1000 | Loss: 1.3511\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:49 INFO\u001b[0m Step 147/1000 | Loss: 1.6218\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:49 INFO\u001b[0m Step 147/1000 | Loss: 1.6268\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:50 INFO\u001b[0m Step 148/1000 | Loss: 1.8682\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:50 INFO\u001b[0m Step 148/1000 | Loss: 1.5868\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:50 INFO\u001b[0m Step 148/1000 | Loss: 1.5101\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:50 INFO\u001b[0m Step 148/1000 | Loss: 1.9332\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:50 INFO\u001b[0m Step 148/1000 | Loss: 1.4618\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:50 INFO\u001b[0m Step 148/1000 | Loss: 1.8273\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:50 INFO\u001b[0m Step 148/1000 | Loss: 1.8211\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:50 INFO\u001b[0m Step 148/1000 | Loss: 1.8653\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:50 INFO\u001b[0m Step 149/1000 | Loss: 1.6981\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:50 INFO\u001b[0m Step 149/1000 | Loss: 1.6211\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:50 INFO\u001b[0m Step 149/1000 | Loss: 1.7803\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:50 INFO\u001b[0m Step 149/1000 | Loss: 1.6822\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:50 INFO\u001b[0m Step 149/1000 | Loss: 1.4796\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:50 INFO\u001b[0m Step 149/1000 | Loss: 2.0683\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:50 INFO\u001b[0m Step 149/1000 | Loss: 2.0764\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:50 INFO\u001b[0m Step 149/1000 | Loss: 1.8458\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:51 INFO\u001b[0m Step 150/1000 | Loss: 2.1882\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:51 INFO\u001b[0m Step 150/1000 | Loss: 1.9137\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:51 INFO\u001b[0m Step 150/1000 | Loss: 1.8935\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:51 INFO\u001b[0m Step 150/1000 | Loss: 2.1540\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:51 INFO\u001b[0m Step 150/1000 | Loss: 1.6572\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:51 INFO\u001b[0m Step 150/1000 | Loss: 2.0795\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:51 INFO\u001b[0m Step 150/1000 | Loss: 2.0495\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:51 INFO\u001b[0m Step 150/1000 | Loss: 2.0415\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:51 INFO\u001b[0m Step 151/1000 | Loss: 2.2497\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:51 INFO\u001b[0m Step 151/1000 | Loss: 1.5718\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:51 INFO\u001b[0m Step 151/1000 | Loss: 1.8812\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:51 INFO\u001b[0m Step 151/1000 | Loss: 2.2229\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:51 INFO\u001b[0m Step 151/1000 | Loss: 1.8121\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:51 INFO\u001b[0m Step 151/1000 | Loss: 1.9478\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:51 INFO\u001b[0m Step 151/1000 | Loss: 2.0711\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:51 INFO\u001b[0m Step 151/1000 | Loss: 2.1206\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:51 INFO\u001b[0m Step 152/1000 | Loss: 1.9772\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:51 INFO\u001b[0m Step 152/1000 | Loss: 1.9267\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:51 INFO\u001b[0m Step 152/1000 | Loss: 1.8181\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:51 INFO\u001b[0m Step 152/1000 | Loss: 2.1647\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:51 INFO\u001b[0m Step 152/1000 | Loss: 1.7987\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:51 INFO\u001b[0m Step 152/1000 | Loss: 2.3663\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:51 INFO\u001b[0m Step 152/1000 | Loss: 2.1065\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:51 INFO\u001b[0m Step 152/1000 | Loss: 2.1145\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:52 INFO\u001b[0m Step 153/1000 | Loss: 1.9386\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:52 INFO\u001b[0m Step 153/1000 | Loss: 1.8609\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:52 INFO\u001b[0m Step 153/1000 | Loss: 2.0482\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:52 INFO\u001b[0m Step 153/1000 | Loss: 1.6308\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:52 INFO\u001b[0m Step 153/1000 | Loss: 2.2650\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:52 INFO\u001b[0m Step 153/1000 | Loss: 1.8844\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:52 INFO\u001b[0m Step 153/1000 | Loss: 1.9901\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:52 INFO\u001b[0m Step 153/1000 | Loss: 2.2557\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:52 INFO\u001b[0m Step 154/1000 | Loss: 2.0161\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:52 INFO\u001b[0m Step 154/1000 | Loss: 1.7085\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:52 INFO\u001b[0m Step 154/1000 | Loss: 1.8962\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:52 INFO\u001b[0m Step 154/1000 | Loss: 1.9184\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:52 INFO\u001b[0m Step 154/1000 | Loss: 1.9670\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:52 INFO\u001b[0m Step 154/1000 | Loss: 1.2307\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:52 INFO\u001b[0m Step 154/1000 | Loss: 1.8853\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:52 INFO\u001b[0m Step 154/1000 | Loss: 1.9745\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:53 INFO\u001b[0m Step 155/1000 | Loss: 1.6303\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:53 INFO\u001b[0m Step 155/1000 | Loss: 1.7426\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:53 INFO\u001b[0m Step 155/1000 | Loss: 1.6778\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:53 INFO\u001b[0m Step 155/1000 | Loss: 1.9867\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:53 INFO\u001b[0m Step 155/1000 | Loss: 1.5144\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:53 INFO\u001b[0m Step 155/1000 | Loss: 1.8240\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:53 INFO\u001b[0m Step 155/1000 | Loss: 1.6463\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:53 INFO\u001b[0m Step 155/1000 | Loss: 1.8522\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:53 INFO\u001b[0m Step 156/1000 | Loss: 1.6031\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:53 INFO\u001b[0m Step 156/1000 | Loss: 1.4799\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:53 INFO\u001b[0m Step 156/1000 | Loss: 1.3739\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:53 INFO\u001b[0m Step 156/1000 | Loss: 1.7764\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:53 INFO\u001b[0m Step 156/1000 | Loss: 1.4574\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:53 INFO\u001b[0m Step 156/1000 | Loss: 1.3767\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:53 INFO\u001b[0m Step 156/1000 | Loss: 1.7015\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:53 INFO\u001b[0m Step 156/1000 | Loss: 1.5596\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:53 INFO\u001b[0m Step 157/1000 | Loss: 1.4618\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:53 INFO\u001b[0m Step 157/1000 | Loss: 1.6110\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:53 INFO\u001b[0m Step 157/1000 | Loss: 1.2634\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:53 INFO\u001b[0m Step 157/1000 | Loss: 1.4999\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:53 INFO\u001b[0m Step 157/1000 | Loss: 1.3666\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:53 INFO\u001b[0m Step 157/1000 | Loss: 1.6406\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:53 INFO\u001b[0m Step 157/1000 | Loss: 1.6940\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:53 INFO\u001b[0m Step 157/1000 | Loss: 1.5432\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:54 INFO\u001b[0m Step 158/1000 | Loss: 1.4395\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:54 INFO\u001b[0m Step 158/1000 | Loss: 1.6925\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:54 INFO\u001b[0m Step 158/1000 | Loss: 1.5191\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:54 INFO\u001b[0m Step 158/1000 | Loss: 1.3080\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:54 INFO\u001b[0m Step 158/1000 | Loss: 1.4715\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:54 INFO\u001b[0m Step 158/1000 | Loss: 1.7872\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:54 INFO\u001b[0m Step 158/1000 | Loss: 1.6495\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:54 INFO\u001b[0m Step 158/1000 | Loss: 1.2747\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:54 INFO\u001b[0m Step 159/1000 | Loss: 1.3540\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:54 INFO\u001b[0m Step 159/1000 | Loss: 1.3505\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:54 INFO\u001b[0m Step 159/1000 | Loss: 1.3944\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:54 INFO\u001b[0m Step 159/1000 | Loss: 1.5997\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:54 INFO\u001b[0m Step 159/1000 | Loss: 1.4637\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:54 INFO\u001b[0m Step 159/1000 | Loss: 1.6366\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:54 INFO\u001b[0m Step 159/1000 | Loss: 1.3509\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:54 INFO\u001b[0m Step 159/1000 | Loss: 1.4507\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:55 INFO\u001b[0m Step 160/1000 | Loss: 1.3756\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:55 INFO\u001b[0m Step 160/1000 | Loss: 1.3787\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:55 INFO\u001b[0m Step 160/1000 | Loss: 1.2642\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:55 INFO\u001b[0m Step 160/1000 | Loss: 1.4567\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:55 INFO\u001b[0m Step 160/1000 | Loss: 1.0872\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:55 INFO\u001b[0m Step 160/1000 | Loss: 1.3080\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:55 INFO\u001b[0m Step 160/1000 | Loss: 1.4433\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:55 INFO\u001b[0m Step 160/1000 | Loss: 1.6028\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:55 INFO\u001b[0m Step 161/1000 | Loss: 1.0522\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:55 INFO\u001b[0m Step 161/1000 | Loss: 1.2811\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:55 INFO\u001b[0m Step 161/1000 | Loss: 1.3471\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:55 INFO\u001b[0m Step 161/1000 | Loss: 1.3060\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:55 INFO\u001b[0m Step 161/1000 | Loss: 1.3381\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:55 INFO\u001b[0m Step 161/1000 | Loss: 1.4368\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:55 INFO\u001b[0m Step 161/1000 | Loss: 1.3484\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:55 INFO\u001b[0m Step 161/1000 | Loss: 1.5322\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:55 INFO\u001b[0m Step 162/1000 | Loss: 1.3242\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:55 INFO\u001b[0m Step 162/1000 | Loss: 1.5334\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:55 INFO\u001b[0m Step 162/1000 | Loss: 1.4913\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:55 INFO\u001b[0m Step 162/1000 | Loss: 1.4692\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:55 INFO\u001b[0m Step 162/1000 | Loss: 1.4327\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:55 INFO\u001b[0m Step 162/1000 | Loss: 1.6444\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:55 INFO\u001b[0m Step 162/1000 | Loss: 1.6208\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:55 INFO\u001b[0m Step 162/1000 | Loss: 1.4925\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:56 INFO\u001b[0m Step 163/1000 | Loss: 1.6115\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:56 INFO\u001b[0m Step 163/1000 | Loss: 1.6013\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:56 INFO\u001b[0m Step 163/1000 | Loss: 1.6928\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:56 INFO\u001b[0m Step 163/1000 | Loss: 1.5726\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:56 INFO\u001b[0m Step 163/1000 | Loss: 1.1743\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:56 INFO\u001b[0m Step 163/1000 | Loss: 1.4646\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:56 INFO\u001b[0m Step 163/1000 | Loss: 1.6385\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:56 INFO\u001b[0m Step 163/1000 | Loss: 1.3946\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:56 INFO\u001b[0m Step 164/1000 | Loss: 1.5687\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:56 INFO\u001b[0m Step 164/1000 | Loss: 1.6224\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:56 INFO\u001b[0m Step 164/1000 | Loss: 1.6356\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:56 INFO\u001b[0m Step 164/1000 | Loss: 1.4196\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:56 INFO\u001b[0m Step 164/1000 | Loss: 1.4236\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:56 INFO\u001b[0m Step 164/1000 | Loss: 1.4628\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:56 INFO\u001b[0m Step 164/1000 | Loss: 1.4370\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:56 INFO\u001b[0m Step 164/1000 | Loss: 1.3353\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:57 INFO\u001b[0m Step 165/1000 | Loss: 1.6271\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:57 INFO\u001b[0m Step 165/1000 | Loss: 1.7467\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:57 INFO\u001b[0m Step 165/1000 | Loss: 1.5718\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:57 INFO\u001b[0m Step 165/1000 | Loss: 1.7689\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:57 INFO\u001b[0m Step 165/1000 | Loss: 1.5272\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:57 INFO\u001b[0m Step 165/1000 | Loss: 1.5191\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:57 INFO\u001b[0m Step 165/1000 | Loss: 1.6798\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:57 INFO\u001b[0m Step 165/1000 | Loss: 1.4569\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:57 INFO\u001b[0m Step 166/1000 | Loss: 1.7004\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:57 INFO\u001b[0m Step 166/1000 | Loss: 1.7223\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:57 INFO\u001b[0m Step 166/1000 | Loss: 1.5865\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:57 INFO\u001b[0m Step 166/1000 | Loss: 1.5573\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:57 INFO\u001b[0m Step 166/1000 | Loss: 1.8939\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:57 INFO\u001b[0m Step 166/1000 | Loss: 1.4993\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:57 INFO\u001b[0m Step 166/1000 | Loss: 1.5312\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:57 INFO\u001b[0m Step 166/1000 | Loss: 1.6137\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:57 INFO\u001b[0m Step 167/1000 | Loss: 1.5954\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:57 INFO\u001b[0m Step 167/1000 | Loss: 1.6900\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:57 INFO\u001b[0m Step 167/1000 | Loss: 1.6854\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:57 INFO\u001b[0m Step 167/1000 | Loss: 1.7386\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:57 INFO\u001b[0m Step 167/1000 | Loss: 1.6264\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:57 INFO\u001b[0m Step 167/1000 | Loss: 1.7299\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:57 INFO\u001b[0m Step 167/1000 | Loss: 1.6686\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:57 INFO\u001b[0m Step 167/1000 | Loss: 1.8011\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:58 INFO\u001b[0m Step 168/1000 | Loss: 1.8847\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:58 INFO\u001b[0m Step 168/1000 | Loss: 1.6579\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:58 INFO\u001b[0m Step 168/1000 | Loss: 1.7947\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:58 INFO\u001b[0m Step 168/1000 | Loss: 1.4873\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:58 INFO\u001b[0m Step 168/1000 | Loss: 1.7471\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:58 INFO\u001b[0m Step 168/1000 | Loss: 1.5799\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:58 INFO\u001b[0m Step 168/1000 | Loss: 1.7973\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:58 INFO\u001b[0m Step 168/1000 | Loss: 1.7374\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:58 INFO\u001b[0m Step 169/1000 | Loss: 1.5953\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:58 INFO\u001b[0m Step 169/1000 | Loss: 1.5821\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:58 INFO\u001b[0m Step 169/1000 | Loss: 1.8612\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:58 INFO\u001b[0m Step 169/1000 | Loss: 1.9002\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:58 INFO\u001b[0m Step 169/1000 | Loss: 1.6726\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:58 INFO\u001b[0m Step 169/1000 | Loss: 1.6804\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:58 INFO\u001b[0m Step 169/1000 | Loss: 1.7771\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:58 INFO\u001b[0m Step 169/1000 | Loss: 1.9879\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:59 INFO\u001b[0m Step 170/1000 | Loss: 1.7828\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:59 INFO\u001b[0m Step 170/1000 | Loss: 1.6351\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:59 INFO\u001b[0m Step 170/1000 | Loss: 1.8682\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:59 INFO\u001b[0m Step 170/1000 | Loss: 2.0903\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:59 INFO\u001b[0m Step 170/1000 | Loss: 1.7762\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:59 INFO\u001b[0m Step 170/1000 | Loss: 1.7561\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:59 INFO\u001b[0m Step 170/1000 | Loss: 1.6623\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:59 INFO\u001b[0m Step 170/1000 | Loss: 1.7547\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:59 INFO\u001b[0m Step 171/1000 | Loss: 1.5909\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:59 INFO\u001b[0m Step 171/1000 | Loss: 1.6417\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:59 INFO\u001b[0m Step 171/1000 | Loss: 1.7731\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:59 INFO\u001b[0m Step 171/1000 | Loss: 1.7856\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:59 INFO\u001b[0m Step 171/1000 | Loss: 1.5158\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:59 INFO\u001b[0m Step 171/1000 | Loss: 1.6702\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:59 INFO\u001b[0m Step 171/1000 | Loss: 2.0889\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:59 INFO\u001b[0m Step 171/1000 | Loss: 1.9222\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:30:59 INFO\u001b[0m Step 172/1000 | Loss: 1.6327\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:30:59 INFO\u001b[0m Step 172/1000 | Loss: 1.6199\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:30:59 INFO\u001b[0m Step 172/1000 | Loss: 1.6066\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:30:59 INFO\u001b[0m Step 172/1000 | Loss: 1.5294\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:30:59 INFO\u001b[0m Step 172/1000 | Loss: 1.9603\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:30:59 INFO\u001b[0m Step 172/1000 | Loss: 1.8505\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:30:59 INFO\u001b[0m Step 172/1000 | Loss: 1.7585\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:30:59 INFO\u001b[0m Step 172/1000 | Loss: 1.5807\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:00 INFO\u001b[0m Step 173/1000 | Loss: 1.9481\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:00 INFO\u001b[0m Step 173/1000 | Loss: 1.5312\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:00 INFO\u001b[0m Step 173/1000 | Loss: 1.6230\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:00 INFO\u001b[0m Step 173/1000 | Loss: 1.9665\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:00 INFO\u001b[0m Step 173/1000 | Loss: 1.7787\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:00 INFO\u001b[0m Step 173/1000 | Loss: 1.8726\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:00 INFO\u001b[0m Step 173/1000 | Loss: 2.2937\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:00 INFO\u001b[0m Step 173/1000 | Loss: 1.9642\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:00 INFO\u001b[0m Step 174/1000 | Loss: 1.5686\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:00 INFO\u001b[0m Step 174/1000 | Loss: 1.7112\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:00 INFO\u001b[0m Step 174/1000 | Loss: 1.6879\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:00 INFO\u001b[0m Step 174/1000 | Loss: 1.7979\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:00 INFO\u001b[0m Step 174/1000 | Loss: 1.5253\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:00 INFO\u001b[0m Step 174/1000 | Loss: 1.7622\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:00 INFO\u001b[0m Step 174/1000 | Loss: 1.5767\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:00 INFO\u001b[0m Step 174/1000 | Loss: 1.8425\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:01 INFO\u001b[0m Step 175/1000 | Loss: 1.5354\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:01 INFO\u001b[0m Step 175/1000 | Loss: 1.7474\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:01 INFO\u001b[0m Step 175/1000 | Loss: 1.7741\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:01 INFO\u001b[0m Step 175/1000 | Loss: 1.7581\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:01 INFO\u001b[0m Step 175/1000 | Loss: 1.6243\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:01 INFO\u001b[0m Step 175/1000 | Loss: 1.5411\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:01 INFO\u001b[0m Step 175/1000 | Loss: 1.9898\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:01 INFO\u001b[0m Step 175/1000 | Loss: 1.6208\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:01 INFO\u001b[0m Step 176/1000 | Loss: 1.8978\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:01 INFO\u001b[0m Step 176/1000 | Loss: 1.7833\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:01 INFO\u001b[0m Step 176/1000 | Loss: 1.7540\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:01 INFO\u001b[0m Step 176/1000 | Loss: 1.6178\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:01 INFO\u001b[0m Step 176/1000 | Loss: 1.5388\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:01 INFO\u001b[0m Step 176/1000 | Loss: 1.6751\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:01 INFO\u001b[0m Step 176/1000 | Loss: 1.7316\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:01 INFO\u001b[0m Step 176/1000 | Loss: 1.7663\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:02 INFO\u001b[0m Step 177/1000 | Loss: 1.3869\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:02 INFO\u001b[0m Step 177/1000 | Loss: 1.7272\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:02 INFO\u001b[0m Step 177/1000 | Loss: 1.4843\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:02 INFO\u001b[0m Step 177/1000 | Loss: 1.6235\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:02 INFO\u001b[0m Step 177/1000 | Loss: 1.7970\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:02 INFO\u001b[0m Step 177/1000 | Loss: 1.6912\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:02 INFO\u001b[0m Step 177/1000 | Loss: 1.6351\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:02 INFO\u001b[0m Step 177/1000 | Loss: 2.3433\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:02 INFO\u001b[0m Step 178/1000 | Loss: 1.6744\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:02 INFO\u001b[0m Step 178/1000 | Loss: 1.7463\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:02 INFO\u001b[0m Step 178/1000 | Loss: 1.7085\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:02 INFO\u001b[0m Step 178/1000 | Loss: 1.6129\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:02 INFO\u001b[0m Step 178/1000 | Loss: 1.4060\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:02 INFO\u001b[0m Step 178/1000 | Loss: 1.7538\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:02 INFO\u001b[0m Step 178/1000 | Loss: 1.5109\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:02 INFO\u001b[0m Step 178/1000 | Loss: 1.5263\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:02 INFO\u001b[0m Step 179/1000 | Loss: 1.5783\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:02 INFO\u001b[0m Step 179/1000 | Loss: 1.4511\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:02 INFO\u001b[0m Step 179/1000 | Loss: 1.3893\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:02 INFO\u001b[0m Step 179/1000 | Loss: 1.3620\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:02 INFO\u001b[0m Step 179/1000 | Loss: 1.6958\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:02 INFO\u001b[0m Step 179/1000 | Loss: 1.5996\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:02 INFO\u001b[0m Step 179/1000 | Loss: 1.4400\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:02 INFO\u001b[0m Step 179/1000 | Loss: 1.2264\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:03 INFO\u001b[0m Step 180/1000 | Loss: 1.5256\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:03 INFO\u001b[0m Step 180/1000 | Loss: 1.5230\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:03 INFO\u001b[0m Step 180/1000 | Loss: 1.5358\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:03 INFO\u001b[0m Step 180/1000 | Loss: 1.3090\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:03 INFO\u001b[0m Step 180/1000 | Loss: 1.4777\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:03 INFO\u001b[0m Step 180/1000 | Loss: 1.5371\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:03 INFO\u001b[0m Step 180/1000 | Loss: 1.6046\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:03 INFO\u001b[0m Step 180/1000 | Loss: 1.3621\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:03 INFO\u001b[0m Step 181/1000 | Loss: 1.5412\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:03 INFO\u001b[0m Step 181/1000 | Loss: 1.6446\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:03 INFO\u001b[0m Step 181/1000 | Loss: 1.7116\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:03 INFO\u001b[0m Step 181/1000 | Loss: 1.5181\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:03 INFO\u001b[0m Step 181/1000 | Loss: 1.4027\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:03 INFO\u001b[0m Step 181/1000 | Loss: 1.5358\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:03 INFO\u001b[0m Step 181/1000 | Loss: 1.6471\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:03 INFO\u001b[0m Step 181/1000 | Loss: 1.3224\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:04 INFO\u001b[0m Step 182/1000 | Loss: 1.6273\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:04 INFO\u001b[0m Step 182/1000 | Loss: 1.6568\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:04 INFO\u001b[0m Step 182/1000 | Loss: 1.7320\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:04 INFO\u001b[0m Step 182/1000 | Loss: 1.3241\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:04 INFO\u001b[0m Step 182/1000 | Loss: 1.6845\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:04 INFO\u001b[0m Step 182/1000 | Loss: 1.7242\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:04 INFO\u001b[0m Step 182/1000 | Loss: 1.4761\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:04 INFO\u001b[0m Step 182/1000 | Loss: 1.5899\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:04 INFO\u001b[0m Step 183/1000 | Loss: 1.6474\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:04 INFO\u001b[0m Step 183/1000 | Loss: 1.6571\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:04 INFO\u001b[0m Step 183/1000 | Loss: 1.7153\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:04 INFO\u001b[0m Step 183/1000 | Loss: 1.4334\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:04 INFO\u001b[0m Step 183/1000 | Loss: 2.0125\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:04 INFO\u001b[0m Step 183/1000 | Loss: 1.7445\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:04 INFO\u001b[0m Step 183/1000 | Loss: 1.4504\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:04 INFO\u001b[0m Step 183/1000 | Loss: 1.6588\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:04 INFO\u001b[0m Step 184/1000 | Loss: 1.7643\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:04 INFO\u001b[0m Step 184/1000 | Loss: 1.6749\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:04 INFO\u001b[0m Step 184/1000 | Loss: 1.3737\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:04 INFO\u001b[0m Step 184/1000 | Loss: 1.5372\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:04 INFO\u001b[0m Step 184/1000 | Loss: 2.0349\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:04 INFO\u001b[0m Step 184/1000 | Loss: 1.6965\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:04 INFO\u001b[0m Step 184/1000 | Loss: 1.7153\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:04 INFO\u001b[0m Step 184/1000 | Loss: 1.8006\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:05 INFO\u001b[0m Step 185/1000 | Loss: 1.6882\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:05 INFO\u001b[0m Step 185/1000 | Loss: 1.5522\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:05 INFO\u001b[0m Step 185/1000 | Loss: 1.5893\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:05 INFO\u001b[0m Step 185/1000 | Loss: 1.8566\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:05 INFO\u001b[0m Step 185/1000 | Loss: 1.6551\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:05 INFO\u001b[0m Step 185/1000 | Loss: 1.5875\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:05 INFO\u001b[0m Step 185/1000 | Loss: 1.4516\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:05 INFO\u001b[0m Step 185/1000 | Loss: 1.5381\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:05 INFO\u001b[0m Step 186/1000 | Loss: 1.7413\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:05 INFO\u001b[0m Step 186/1000 | Loss: 1.7568\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:05 INFO\u001b[0m Step 186/1000 | Loss: 1.8773\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:05 INFO\u001b[0m Step 186/1000 | Loss: 1.7029\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:05 INFO\u001b[0m Step 186/1000 | Loss: 1.5048\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:05 INFO\u001b[0m Step 186/1000 | Loss: 1.6147\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:05 INFO\u001b[0m Step 186/1000 | Loss: 1.8857\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:05 INFO\u001b[0m Step 186/1000 | Loss: 1.7484\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:06 INFO\u001b[0m Step 187/1000 | Loss: 1.6905\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:06 INFO\u001b[0m Step 187/1000 | Loss: 1.8494\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:06 INFO\u001b[0m Step 187/1000 | Loss: 1.8632\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:06 INFO\u001b[0m Step 187/1000 | Loss: 1.8451\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:06 INFO\u001b[0m Step 187/1000 | Loss: 1.9766\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:06 INFO\u001b[0m Step 187/1000 | Loss: 1.6130\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:06 INFO\u001b[0m Step 187/1000 | Loss: 1.7349\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:06 INFO\u001b[0m Step 187/1000 | Loss: 1.7383\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:06 INFO\u001b[0m Step 188/1000 | Loss: 1.8439\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:06 INFO\u001b[0m Step 188/1000 | Loss: 2.1553\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:06 INFO\u001b[0m Step 188/1000 | Loss: 1.5456\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:06 INFO\u001b[0m Step 188/1000 | Loss: 1.9724\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:06 INFO\u001b[0m Step 188/1000 | Loss: 1.9144\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:06 INFO\u001b[0m Step 188/1000 | Loss: 1.8244\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:06 INFO\u001b[0m Step 188/1000 | Loss: 2.2420\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:06 INFO\u001b[0m Step 188/1000 | Loss: 1.7938\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:07 INFO\u001b[0m Step 189/1000 | Loss: 1.9024\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:07 INFO\u001b[0m Step 189/1000 | Loss: 1.7172\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:07 INFO\u001b[0m Step 189/1000 | Loss: 1.9876\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:07 INFO\u001b[0m Step 189/1000 | Loss: 1.6694\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:07 INFO\u001b[0m Step 189/1000 | Loss: 1.8195\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:07 INFO\u001b[0m Step 189/1000 | Loss: 1.6444\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:07 INFO\u001b[0m Step 189/1000 | Loss: 1.8934\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:07 INFO\u001b[0m Step 189/1000 | Loss: 1.8308\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:07 INFO\u001b[0m Step 190/1000 | Loss: 2.0313\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:07 INFO\u001b[0m Step 190/1000 | Loss: 1.6379\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:07 INFO\u001b[0m Step 190/1000 | Loss: 1.7557\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:07 INFO\u001b[0m Step 190/1000 | Loss: 1.8867\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:07 INFO\u001b[0m Step 190/1000 | Loss: 1.7272\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:07 INFO\u001b[0m Step 190/1000 | Loss: 1.7405\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:07 INFO\u001b[0m Step 190/1000 | Loss: 1.7335\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:07 INFO\u001b[0m Step 190/1000 | Loss: 1.5408\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:07 INFO\u001b[0m Step 191/1000 | Loss: 1.4872\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:07 INFO\u001b[0m Step 191/1000 | Loss: 1.9328\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:07 INFO\u001b[0m Step 191/1000 | Loss: 1.8260\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:07 INFO\u001b[0m Step 191/1000 | Loss: 1.6095\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:07 INFO\u001b[0m Step 191/1000 | Loss: 1.5094\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:07 INFO\u001b[0m Step 191/1000 | Loss: 1.8728\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:07 INFO\u001b[0m Step 191/1000 | Loss: 1.6113\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:07 INFO\u001b[0m Step 191/1000 | Loss: 1.6345\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:08 INFO\u001b[0m Step 192/1000 | Loss: 1.7676\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:08 INFO\u001b[0m Step 192/1000 | Loss: 1.6732\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:08 INFO\u001b[0m Step 192/1000 | Loss: 1.6559\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:08 INFO\u001b[0m Step 192/1000 | Loss: 1.3543\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:08 INFO\u001b[0m Step 192/1000 | Loss: 1.4583\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:08 INFO\u001b[0m Step 192/1000 | Loss: 1.6269\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:08 INFO\u001b[0m Step 192/1000 | Loss: 1.8115\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:08 INFO\u001b[0m Step 192/1000 | Loss: 1.5074\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:08 INFO\u001b[0m Step 193/1000 | Loss: 1.7991\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:08 INFO\u001b[0m Step 193/1000 | Loss: 1.7765\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:08 INFO\u001b[0m Step 193/1000 | Loss: 1.7901\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:08 INFO\u001b[0m Step 193/1000 | Loss: 1.4981\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:08 INFO\u001b[0m Step 193/1000 | Loss: 1.5934\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:08 INFO\u001b[0m Step 193/1000 | Loss: 1.5162\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:08 INFO\u001b[0m Step 193/1000 | Loss: 1.7432\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:08 INFO\u001b[0m Step 193/1000 | Loss: 1.5898\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:09 INFO\u001b[0m Step 194/1000 | Loss: 1.4113\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:09 INFO\u001b[0m Step 194/1000 | Loss: 1.7884\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:09 INFO\u001b[0m Step 194/1000 | Loss: 2.3223\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:09 INFO\u001b[0m Step 194/1000 | Loss: 1.7027\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:09 INFO\u001b[0m Step 194/1000 | Loss: 1.4909\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:09 INFO\u001b[0m Step 194/1000 | Loss: 1.5935\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:09 INFO\u001b[0m Step 194/1000 | Loss: 1.6884\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:09 INFO\u001b[0m Step 194/1000 | Loss: 1.6199\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:09 INFO\u001b[0m Step 195/1000 | Loss: 1.6778\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:09 INFO\u001b[0m Step 195/1000 | Loss: 1.5968\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:09 INFO\u001b[0m Step 195/1000 | Loss: 1.7280\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:09 INFO\u001b[0m Step 195/1000 | Loss: 1.8747\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:09 INFO\u001b[0m Step 195/1000 | Loss: 1.6996\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:09 INFO\u001b[0m Step 195/1000 | Loss: 2.0696\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:09 INFO\u001b[0m Step 195/1000 | Loss: 1.7462\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:09 INFO\u001b[0m Step 195/1000 | Loss: 1.7051\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:09 INFO\u001b[0m Step 196/1000 | Loss: 1.6279\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:09 INFO\u001b[0m Step 196/1000 | Loss: 1.9421\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:09 INFO\u001b[0m Step 196/1000 | Loss: 1.5151\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:09 INFO\u001b[0m Step 196/1000 | Loss: 1.8338\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:09 INFO\u001b[0m Step 196/1000 | Loss: 1.6594\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:09 INFO\u001b[0m Step 196/1000 | Loss: 1.8605\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:09 INFO\u001b[0m Step 196/1000 | Loss: 1.5204\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:09 INFO\u001b[0m Step 196/1000 | Loss: 1.7001\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:10 INFO\u001b[0m Step 197/1000 | Loss: 1.8533\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:10 INFO\u001b[0m Step 197/1000 | Loss: 1.6462\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:10 INFO\u001b[0m Step 197/1000 | Loss: 1.8715\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:10 INFO\u001b[0m Step 197/1000 | Loss: 1.8643\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:10 INFO\u001b[0m Step 197/1000 | Loss: 1.9145\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:10 INFO\u001b[0m Step 197/1000 | Loss: 2.0503\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:10 INFO\u001b[0m Step 197/1000 | Loss: 1.8999\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:10 INFO\u001b[0m Step 197/1000 | Loss: 1.4307\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:10 INFO\u001b[0m Step 198/1000 | Loss: 1.6625\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:10 INFO\u001b[0m Step 198/1000 | Loss: 1.5639\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:10 INFO\u001b[0m Step 198/1000 | Loss: 1.8248\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:10 INFO\u001b[0m Step 198/1000 | Loss: 1.9646\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:10 INFO\u001b[0m Step 198/1000 | Loss: 2.0590\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:10 INFO\u001b[0m Step 198/1000 | Loss: 1.4946\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:10 INFO\u001b[0m Step 198/1000 | Loss: 1.6809\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:10 INFO\u001b[0m Step 198/1000 | Loss: 1.7621\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:11 INFO\u001b[0m Step 199/1000 | Loss: 1.7629\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:11 INFO\u001b[0m Step 199/1000 | Loss: 1.6142\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:11 INFO\u001b[0m Step 199/1000 | Loss: 1.5933\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:11 INFO\u001b[0m Step 199/1000 | Loss: 1.5097\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:11 INFO\u001b[0m Step 199/1000 | Loss: 1.6101\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:11 INFO\u001b[0m Step 199/1000 | Loss: 1.8488\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:11 INFO\u001b[0m Step 199/1000 | Loss: 1.5860\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:11 INFO\u001b[0m Step 199/1000 | Loss: 1.5164\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:11 INFO\u001b[0m Step 200/1000 | Loss: 1.6038\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:11 INFO\u001b[0m Step 200/1000 | Loss: 1.4622\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:11 INFO\u001b[0m Step 200/1000 | Loss: 1.4138\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:11 INFO\u001b[0m Step 200/1000 | Loss: 1.8997\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:11 INFO\u001b[0m Step 200/1000 | Loss: 1.6471\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:11 INFO\u001b[0m Step 200/1000 | Loss: 1.7167\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:11 INFO\u001b[0m Step 200/1000 | Loss: 1.8638\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:11 INFO\u001b[0m Step 200/1000 | Loss: 2.0290\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:11 INFO\u001b[0m Step 201/1000 | Loss: 2.2505\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:11 INFO\u001b[0m Step 201/1000 | Loss: 1.6734\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:11 INFO\u001b[0m Step 201/1000 | Loss: 1.9449\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:11 INFO\u001b[0m Step 201/1000 | Loss: 2.1703\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:11 INFO\u001b[0m Step 201/1000 | Loss: 1.8940\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:11 INFO\u001b[0m Step 201/1000 | Loss: 1.6696\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:11 INFO\u001b[0m Step 201/1000 | Loss: 1.5916\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:11 INFO\u001b[0m Step 201/1000 | Loss: 1.8004\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:12 INFO\u001b[0m Step 202/1000 | Loss: 1.2795\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:12 INFO\u001b[0m Step 202/1000 | Loss: 1.4855\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:12 INFO\u001b[0m Step 202/1000 | Loss: 1.3441\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:12 INFO\u001b[0m Step 202/1000 | Loss: 1.5256\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:12 INFO\u001b[0m Step 202/1000 | Loss: 1.5933\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:12 INFO\u001b[0m Step 202/1000 | Loss: 1.6857\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:12 INFO\u001b[0m Step 202/1000 | Loss: 1.3651\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:12 INFO\u001b[0m Step 202/1000 | Loss: 1.5632\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:12 INFO\u001b[0m Step 203/1000 | Loss: 1.5639\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:12 INFO\u001b[0m Step 203/1000 | Loss: 1.8076\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:12 INFO\u001b[0m Step 203/1000 | Loss: 1.6197\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:12 INFO\u001b[0m Step 203/1000 | Loss: 1.6980\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:12 INFO\u001b[0m Step 203/1000 | Loss: 1.3665\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:12 INFO\u001b[0m Step 203/1000 | Loss: 1.6986\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:12 INFO\u001b[0m Step 203/1000 | Loss: 1.9787\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:12 INFO\u001b[0m Step 203/1000 | Loss: 1.5481\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:13 INFO\u001b[0m Step 204/1000 | Loss: 1.6258\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:13 INFO\u001b[0m Step 204/1000 | Loss: 1.7633\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:13 INFO\u001b[0m Step 204/1000 | Loss: 1.5502\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:13 INFO\u001b[0m Step 204/1000 | Loss: 1.3588\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:13 INFO\u001b[0m Step 204/1000 | Loss: 1.7516\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:13 INFO\u001b[0m Step 204/1000 | Loss: 1.5866\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:13 INFO\u001b[0m Step 204/1000 | Loss: 1.6417\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:13 INFO\u001b[0m Step 204/1000 | Loss: 1.5933\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:13 INFO\u001b[0m Step 205/1000 | Loss: 1.3460\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:13 INFO\u001b[0m Step 205/1000 | Loss: 1.5686\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:13 INFO\u001b[0m Step 205/1000 | Loss: 1.4491\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:13 INFO\u001b[0m Step 205/1000 | Loss: 1.7466\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:13 INFO\u001b[0m Step 205/1000 | Loss: 1.4630\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:13 INFO\u001b[0m Step 205/1000 | Loss: 1.7846\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:13 INFO\u001b[0m Step 205/1000 | Loss: 1.7377\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:13 INFO\u001b[0m Step 205/1000 | Loss: 1.5829\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:13 INFO\u001b[0m Step 206/1000 | Loss: 1.5499\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:13 INFO\u001b[0m Step 206/1000 | Loss: 1.5035\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:13 INFO\u001b[0m Step 206/1000 | Loss: 1.7604\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:13 INFO\u001b[0m Step 206/1000 | Loss: 1.4346\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:13 INFO\u001b[0m Step 206/1000 | Loss: 1.7253\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:13 INFO\u001b[0m Step 206/1000 | Loss: 1.3926\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:13 INFO\u001b[0m Step 206/1000 | Loss: 1.5004\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:13 INFO\u001b[0m Step 206/1000 | Loss: 1.7387\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:14 INFO\u001b[0m Step 207/1000 | Loss: 1.4578\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:14 INFO\u001b[0m Step 207/1000 | Loss: 1.4838\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:14 INFO\u001b[0m Step 207/1000 | Loss: 1.3046\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:14 INFO\u001b[0m Step 207/1000 | Loss: 1.5549\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:14 INFO\u001b[0m Step 207/1000 | Loss: 2.0141\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:14 INFO\u001b[0m Step 207/1000 | Loss: 1.6554\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:14 INFO\u001b[0m Step 207/1000 | Loss: 1.7629\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:14 INFO\u001b[0m Step 207/1000 | Loss: 1.3743\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:14 INFO\u001b[0m Step 208/1000 | Loss: 1.4696\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:14 INFO\u001b[0m Step 208/1000 | Loss: 1.4651\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:14 INFO\u001b[0m Step 208/1000 | Loss: 1.5009\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:14 INFO\u001b[0m Step 208/1000 | Loss: 1.4461\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:14 INFO\u001b[0m Step 208/1000 | Loss: 1.4265\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:14 INFO\u001b[0m Step 208/1000 | Loss: 1.6319\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:14 INFO\u001b[0m Step 208/1000 | Loss: 1.5250\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:14 INFO\u001b[0m Step 208/1000 | Loss: 1.5980\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:15 INFO\u001b[0m Step 209/1000 | Loss: 1.2653\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:15 INFO\u001b[0m Step 209/1000 | Loss: 1.5248\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:15 INFO\u001b[0m Step 209/1000 | Loss: 1.6031\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:15 INFO\u001b[0m Step 209/1000 | Loss: 1.5759\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:15 INFO\u001b[0m Step 209/1000 | Loss: 1.5370\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:15 INFO\u001b[0m Step 209/1000 | Loss: 1.4556\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:15 INFO\u001b[0m Step 209/1000 | Loss: 1.3303\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:15 INFO\u001b[0m Step 209/1000 | Loss: 1.5325\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:15 INFO\u001b[0m Step 210/1000 | Loss: 1.3313\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:15 INFO\u001b[0m Step 210/1000 | Loss: 1.7430\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:15 INFO\u001b[0m Step 210/1000 | Loss: 1.9362\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:15 INFO\u001b[0m Step 210/1000 | Loss: 1.7536\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:15 INFO\u001b[0m Step 210/1000 | Loss: 1.6886\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:15 INFO\u001b[0m Step 210/1000 | Loss: 1.5714\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:15 INFO\u001b[0m Step 210/1000 | Loss: 1.4669\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:15 INFO\u001b[0m Step 210/1000 | Loss: 1.4319\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:15 INFO\u001b[0m Step 211/1000 | Loss: 2.2268\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:15 INFO\u001b[0m Step 211/1000 | Loss: 1.4495\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:15 INFO\u001b[0m Step 211/1000 | Loss: 1.5402\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:15 INFO\u001b[0m Step 211/1000 | Loss: 1.5530\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:15 INFO\u001b[0m Step 211/1000 | Loss: 1.8749\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:15 INFO\u001b[0m Step 211/1000 | Loss: 1.5825\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:15 INFO\u001b[0m Step 211/1000 | Loss: 1.5265\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:15 INFO\u001b[0m Step 211/1000 | Loss: 1.5166\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:16 INFO\u001b[0m Step 212/1000 | Loss: 1.6409\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:16 INFO\u001b[0m Step 212/1000 | Loss: 1.6751\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:16 INFO\u001b[0m Step 212/1000 | Loss: 1.7937\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:16 INFO\u001b[0m Step 212/1000 | Loss: 1.7404\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:16 INFO\u001b[0m Step 212/1000 | Loss: 1.4991\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:16 INFO\u001b[0m Step 212/1000 | Loss: 1.5443\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:16 INFO\u001b[0m Step 212/1000 | Loss: 1.5484\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:16 INFO\u001b[0m Step 212/1000 | Loss: 1.7963\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:16 INFO\u001b[0m Step 213/1000 | Loss: 1.5991\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:16 INFO\u001b[0m Step 213/1000 | Loss: 2.1179\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:16 INFO\u001b[0m Step 213/1000 | Loss: 1.5688\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:16 INFO\u001b[0m Step 213/1000 | Loss: 1.6175\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:16 INFO\u001b[0m Step 213/1000 | Loss: 1.6101\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:16 INFO\u001b[0m Step 213/1000 | Loss: 1.8838\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:16 INFO\u001b[0m Step 213/1000 | Loss: 1.7303\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:16 INFO\u001b[0m Step 213/1000 | Loss: 1.8202\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:17 INFO\u001b[0m Step 214/1000 | Loss: 2.0575\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:17 INFO\u001b[0m Step 214/1000 | Loss: 1.8041\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:17 INFO\u001b[0m Step 214/1000 | Loss: 1.6977\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:17 INFO\u001b[0m Step 214/1000 | Loss: 1.4298\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:17 INFO\u001b[0m Step 214/1000 | Loss: 1.7048\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:17 INFO\u001b[0m Step 214/1000 | Loss: 2.0763\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:17 INFO\u001b[0m Step 214/1000 | Loss: 1.5666\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:17 INFO\u001b[0m Step 214/1000 | Loss: 1.6225\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:17 INFO\u001b[0m Step 215/1000 | Loss: 1.5591\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:17 INFO\u001b[0m Step 215/1000 | Loss: 1.4440\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:17 INFO\u001b[0m Step 215/1000 | Loss: 1.7097\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:17 INFO\u001b[0m Step 215/1000 | Loss: 1.6025\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:17 INFO\u001b[0m Step 215/1000 | Loss: 1.7036\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:17 INFO\u001b[0m Step 215/1000 | Loss: 1.7902\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:17 INFO\u001b[0m Step 215/1000 | Loss: 1.7551\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:17 INFO\u001b[0m Step 215/1000 | Loss: 1.7035\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:17 INFO\u001b[0m Step 216/1000 | Loss: 1.3910\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:17 INFO\u001b[0m Step 216/1000 | Loss: 1.6581\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:17 INFO\u001b[0m Step 216/1000 | Loss: 1.9742\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:17 INFO\u001b[0m Step 216/1000 | Loss: 1.7348\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:17 INFO\u001b[0m Step 216/1000 | Loss: 1.6450\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:17 INFO\u001b[0m Step 216/1000 | Loss: 1.5609\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:17 INFO\u001b[0m Step 216/1000 | Loss: 1.5311\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:17 INFO\u001b[0m Step 216/1000 | Loss: 1.7240\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:18 INFO\u001b[0m Step 217/1000 | Loss: 2.2173\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:18 INFO\u001b[0m Step 217/1000 | Loss: 1.5402\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:18 INFO\u001b[0m Step 217/1000 | Loss: 1.6187\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:18 INFO\u001b[0m Step 217/1000 | Loss: 1.6752\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:18 INFO\u001b[0m Step 217/1000 | Loss: 1.9648\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:18 INFO\u001b[0m Step 217/1000 | Loss: 1.7450\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:18 INFO\u001b[0m Step 217/1000 | Loss: 1.8546\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:18 INFO\u001b[0m Step 217/1000 | Loss: 1.4078\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:18 INFO\u001b[0m Step 218/1000 | Loss: 1.6584\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:18 INFO\u001b[0m Step 218/1000 | Loss: 1.8867\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:18 INFO\u001b[0m Step 218/1000 | Loss: 1.5925\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:18 INFO\u001b[0m Step 218/1000 | Loss: 1.7482\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:18 INFO\u001b[0m Step 218/1000 | Loss: 1.5709\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:18 INFO\u001b[0m Step 218/1000 | Loss: 1.6323\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:18 INFO\u001b[0m Step 218/1000 | Loss: 2.0733\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:18 INFO\u001b[0m Step 218/1000 | Loss: 1.8383\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:19 INFO\u001b[0m Step 219/1000 | Loss: 1.9651\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:19 INFO\u001b[0m Step 219/1000 | Loss: 1.8406\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:19 INFO\u001b[0m Step 219/1000 | Loss: 1.7834\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:19 INFO\u001b[0m Step 219/1000 | Loss: 1.6251\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:19 INFO\u001b[0m Step 219/1000 | Loss: 1.9196\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:19 INFO\u001b[0m Step 219/1000 | Loss: 1.8433\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:19 INFO\u001b[0m Step 219/1000 | Loss: 1.9366\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:19 INFO\u001b[0m Step 219/1000 | Loss: 1.5293\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:19 INFO\u001b[0m Step 220/1000 | Loss: 1.5948\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:19 INFO\u001b[0m Step 220/1000 | Loss: 1.6329\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:19 INFO\u001b[0m Step 220/1000 | Loss: 1.7879\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:19 INFO\u001b[0m Step 220/1000 | Loss: 1.7465\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:19 INFO\u001b[0m Step 220/1000 | Loss: 1.6717\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:19 INFO\u001b[0m Step 220/1000 | Loss: 1.5659\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:19 INFO\u001b[0m Step 220/1000 | Loss: 1.4665\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:19 INFO\u001b[0m Step 220/1000 | Loss: 1.7064\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:19 INFO\u001b[0m Step 221/1000 | Loss: 1.7706\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:19 INFO\u001b[0m Step 221/1000 | Loss: 1.7094\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:19 INFO\u001b[0m Step 221/1000 | Loss: 1.6124\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:19 INFO\u001b[0m Step 221/1000 | Loss: 1.4526\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:19 INFO\u001b[0m Step 221/1000 | Loss: 1.8261\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:19 INFO\u001b[0m Step 221/1000 | Loss: 1.3671\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:19 INFO\u001b[0m Step 221/1000 | Loss: 1.7658\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:19 INFO\u001b[0m Step 221/1000 | Loss: 1.7384\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:20 INFO\u001b[0m Step 222/1000 | Loss: 1.2675\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:20 INFO\u001b[0m Step 222/1000 | Loss: 1.8631\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:20 INFO\u001b[0m Step 222/1000 | Loss: 1.7326\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:20 INFO\u001b[0m Step 222/1000 | Loss: 1.5341\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:20 INFO\u001b[0m Step 222/1000 | Loss: 1.6434\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:20 INFO\u001b[0m Step 222/1000 | Loss: 1.6062\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:20 INFO\u001b[0m Step 222/1000 | Loss: 1.4970\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:20 INFO\u001b[0m Step 222/1000 | Loss: 1.5564\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:20 INFO\u001b[0m Step 223/1000 | Loss: 1.6720\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:20 INFO\u001b[0m Step 223/1000 | Loss: 1.5741\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:20 INFO\u001b[0m Step 223/1000 | Loss: 1.5877\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:20 INFO\u001b[0m Step 223/1000 | Loss: 1.3558\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:20 INFO\u001b[0m Step 223/1000 | Loss: 1.5919\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:20 INFO\u001b[0m Step 223/1000 | Loss: 1.4240\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:20 INFO\u001b[0m Step 223/1000 | Loss: 1.2581\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:20 INFO\u001b[0m Step 223/1000 | Loss: 1.5256\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:21 INFO\u001b[0m Step 224/1000 | Loss: 1.7426\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:21 INFO\u001b[0m Step 224/1000 | Loss: 1.5142\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:21 INFO\u001b[0m Step 224/1000 | Loss: 1.6211\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:21 INFO\u001b[0m Step 224/1000 | Loss: 1.8216\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:21 INFO\u001b[0m Step 224/1000 | Loss: 1.3751\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:21 INFO\u001b[0m Step 224/1000 | Loss: 1.5244\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:21 INFO\u001b[0m Step 224/1000 | Loss: 1.4865\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:21 INFO\u001b[0m Step 224/1000 | Loss: 1.6288\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:21 INFO\u001b[0m Step 225/1000 | Loss: 1.4914\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:21 INFO\u001b[0m Step 225/1000 | Loss: 1.8566\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:21 INFO\u001b[0m Step 225/1000 | Loss: 1.6030\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:21 INFO\u001b[0m Step 225/1000 | Loss: 1.8340\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:21 INFO\u001b[0m Step 225/1000 | Loss: 1.6962\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:21 INFO\u001b[0m Step 225/1000 | Loss: 1.5064\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:21 INFO\u001b[0m Step 225/1000 | Loss: 1.6467\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:21 INFO\u001b[0m Step 225/1000 | Loss: 1.6587\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:21 INFO\u001b[0m Step 226/1000 | Loss: 1.8695\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:21 INFO\u001b[0m Step 226/1000 | Loss: 1.5821\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:21 INFO\u001b[0m Step 226/1000 | Loss: 1.6731\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:21 INFO\u001b[0m Step 226/1000 | Loss: 1.7042\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:21 INFO\u001b[0m Step 226/1000 | Loss: 1.7426\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:21 INFO\u001b[0m Step 226/1000 | Loss: 1.5011\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:21 INFO\u001b[0m Step 226/1000 | Loss: 1.6616\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:21 INFO\u001b[0m Step 226/1000 | Loss: 1.5447\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:22 INFO\u001b[0m Step 227/1000 | Loss: 2.2255\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:22 INFO\u001b[0m Step 227/1000 | Loss: 1.9633\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:22 INFO\u001b[0m Step 227/1000 | Loss: 1.6978\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:22 INFO\u001b[0m Step 227/1000 | Loss: 1.9837\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:22 INFO\u001b[0m Step 227/1000 | Loss: 2.1379\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:22 INFO\u001b[0m Step 227/1000 | Loss: 2.3885\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:22 INFO\u001b[0m Step 227/1000 | Loss: 1.9321\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:22 INFO\u001b[0m Step 227/1000 | Loss: 1.7278\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:22 INFO\u001b[0m Step 228/1000 | Loss: 2.2649\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:22 INFO\u001b[0m Step 228/1000 | Loss: 1.6695\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:22 INFO\u001b[0m Step 228/1000 | Loss: 1.9074\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:22 INFO\u001b[0m Step 228/1000 | Loss: 2.4583\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:22 INFO\u001b[0m Step 228/1000 | Loss: 1.9255\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:22 INFO\u001b[0m Step 228/1000 | Loss: 1.8074\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:22 INFO\u001b[0m Step 228/1000 | Loss: 1.9360\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:22 INFO\u001b[0m Step 228/1000 | Loss: 1.9718\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:23 INFO\u001b[0m Step 229/1000 | Loss: 1.9099\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:23 INFO\u001b[0m Step 229/1000 | Loss: 2.1380\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:23 INFO\u001b[0m Step 229/1000 | Loss: 2.4869\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:23 INFO\u001b[0m Step 229/1000 | Loss: 2.3022\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:23 INFO\u001b[0m Step 229/1000 | Loss: 2.1211\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:23 INFO\u001b[0m Step 229/1000 | Loss: 2.1664\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:23 INFO\u001b[0m Step 229/1000 | Loss: 2.1452\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:23 INFO\u001b[0m Step 229/1000 | Loss: 2.0088\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:23 INFO\u001b[0m Step 230/1000 | Loss: 1.9831\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:23 INFO\u001b[0m Step 230/1000 | Loss: 2.2837\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:23 INFO\u001b[0m Step 230/1000 | Loss: 2.1632\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:23 INFO\u001b[0m Step 230/1000 | Loss: 2.3582\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:23 INFO\u001b[0m Step 230/1000 | Loss: 1.8564\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:23 INFO\u001b[0m Step 230/1000 | Loss: 1.9839\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:23 INFO\u001b[0m Step 230/1000 | Loss: 2.1526\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:23 INFO\u001b[0m Step 230/1000 | Loss: 2.1360\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:24 INFO\u001b[0m Step 231/1000 | Loss: 2.3446\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:24 INFO\u001b[0m Step 231/1000 | Loss: 2.3376\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:24 INFO\u001b[0m Step 231/1000 | Loss: 2.4271\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:24 INFO\u001b[0m Step 231/1000 | Loss: 2.8052\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:24 INFO\u001b[0m Step 231/1000 | Loss: 2.3447\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:24 INFO\u001b[0m Step 231/1000 | Loss: 2.2854\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:24 INFO\u001b[0m Step 231/1000 | Loss: 2.1170\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:24 INFO\u001b[0m Step 231/1000 | Loss: 2.3818\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:24 INFO\u001b[0m Step 232/1000 | Loss: 2.3230\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:24 INFO\u001b[0m Step 232/1000 | Loss: 2.2832\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:24 INFO\u001b[0m Step 232/1000 | Loss: 2.4381\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:24 INFO\u001b[0m Step 232/1000 | Loss: 2.3948\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:24 INFO\u001b[0m Step 232/1000 | Loss: 2.3843\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:24 INFO\u001b[0m Step 232/1000 | Loss: 2.5377\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:24 INFO\u001b[0m Step 232/1000 | Loss: 2.4627\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:24 INFO\u001b[0m Step 232/1000 | Loss: 2.5098\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:24 INFO\u001b[0m Step 233/1000 | Loss: 2.0118\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:24 INFO\u001b[0m Step 233/1000 | Loss: 2.7430\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:24 INFO\u001b[0m Step 233/1000 | Loss: 2.6094\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:24 INFO\u001b[0m Step 233/1000 | Loss: 2.1811\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:24 INFO\u001b[0m Step 233/1000 | Loss: 2.3424\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:24 INFO\u001b[0m Step 233/1000 | Loss: 2.0495\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:24 INFO\u001b[0m Step 233/1000 | Loss: 2.2380\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:24 INFO\u001b[0m Step 233/1000 | Loss: 2.4212\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:25 INFO\u001b[0m Step 234/1000 | Loss: 2.0848\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:25 INFO\u001b[0m Step 234/1000 | Loss: 2.2648\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:25 INFO\u001b[0m Step 234/1000 | Loss: 2.2653\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:25 INFO\u001b[0m Step 234/1000 | Loss: 2.1699\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:25 INFO\u001b[0m Step 234/1000 | Loss: 2.3359\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:25 INFO\u001b[0m Step 234/1000 | Loss: 2.1993\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:25 INFO\u001b[0m Step 234/1000 | Loss: 2.1781\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:25 INFO\u001b[0m Step 234/1000 | Loss: 2.1234\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:25 INFO\u001b[0m Step 235/1000 | Loss: 1.9908\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:25 INFO\u001b[0m Step 235/1000 | Loss: 2.2764\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:25 INFO\u001b[0m Step 235/1000 | Loss: 2.8645\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:25 INFO\u001b[0m Step 235/1000 | Loss: 2.4951\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:25 INFO\u001b[0m Step 235/1000 | Loss: 2.2439\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:25 INFO\u001b[0m Step 235/1000 | Loss: 2.4749\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:25 INFO\u001b[0m Step 235/1000 | Loss: 2.7104\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:25 INFO\u001b[0m Step 235/1000 | Loss: 2.1563\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:26 INFO\u001b[0m Step 236/1000 | Loss: 2.3465\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:26 INFO\u001b[0m Step 236/1000 | Loss: 1.8324\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:26 INFO\u001b[0m Step 236/1000 | Loss: 2.6291\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:26 INFO\u001b[0m Step 236/1000 | Loss: 2.3512\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:26 INFO\u001b[0m Step 236/1000 | Loss: 2.3875\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:26 INFO\u001b[0m Step 236/1000 | Loss: 2.1979\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:26 INFO\u001b[0m Step 236/1000 | Loss: 2.2377\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:26 INFO\u001b[0m Step 236/1000 | Loss: 2.0906\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:26 INFO\u001b[0m Step 237/1000 | Loss: 2.6297\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:26 INFO\u001b[0m Step 237/1000 | Loss: 2.0261\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:26 INFO\u001b[0m Step 237/1000 | Loss: 1.7802\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:26 INFO\u001b[0m Step 237/1000 | Loss: 2.3740\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:26 INFO\u001b[0m Step 237/1000 | Loss: 1.6731\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:26 INFO\u001b[0m Step 237/1000 | Loss: 2.0709\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:26 INFO\u001b[0m Step 237/1000 | Loss: 2.2087\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:26 INFO\u001b[0m Step 237/1000 | Loss: 2.1998\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:27 INFO\u001b[0m Step 238/1000 | Loss: 2.0908\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:27 INFO\u001b[0m Step 238/1000 | Loss: 1.9917\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:27 INFO\u001b[0m Step 238/1000 | Loss: 1.6358\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:27 INFO\u001b[0m Step 238/1000 | Loss: 2.0923\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:27 INFO\u001b[0m Step 238/1000 | Loss: 2.1932\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:27 INFO\u001b[0m Step 238/1000 | Loss: 2.1694\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:27 INFO\u001b[0m Step 238/1000 | Loss: 2.2167\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:27 INFO\u001b[0m Step 238/1000 | Loss: 1.8025\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:27 INFO\u001b[0m Step 239/1000 | Loss: 2.1643\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:27 INFO\u001b[0m Step 239/1000 | Loss: 1.7831\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:27 INFO\u001b[0m Step 239/1000 | Loss: 1.7726\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:27 INFO\u001b[0m Step 239/1000 | Loss: 1.8276\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:27 INFO\u001b[0m Step 239/1000 | Loss: 1.8223\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:27 INFO\u001b[0m Step 239/1000 | Loss: 1.7355\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:27 INFO\u001b[0m Step 239/1000 | Loss: 1.8766\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:27 INFO\u001b[0m Step 239/1000 | Loss: 2.2313\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:27 INFO\u001b[0m Step 240/1000 | Loss: 2.3740\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:27 INFO\u001b[0m Step 240/1000 | Loss: 1.7134\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:27 INFO\u001b[0m Step 240/1000 | Loss: 1.8203\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:27 INFO\u001b[0m Step 240/1000 | Loss: 1.6796\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:27 INFO\u001b[0m Step 240/1000 | Loss: 1.8827\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:27 INFO\u001b[0m Step 240/1000 | Loss: 1.9710\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:27 INFO\u001b[0m Step 240/1000 | Loss: 1.6938\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:27 INFO\u001b[0m Step 240/1000 | Loss: 1.8241\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:28 INFO\u001b[0m Step 241/1000 | Loss: 1.7852\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:28 INFO\u001b[0m Step 241/1000 | Loss: 1.9213\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:28 INFO\u001b[0m Step 241/1000 | Loss: 1.7325\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:28 INFO\u001b[0m Step 241/1000 | Loss: 1.6383\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:28 INFO\u001b[0m Step 241/1000 | Loss: 2.0708\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:28 INFO\u001b[0m Step 241/1000 | Loss: 1.7938\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:28 INFO\u001b[0m Step 241/1000 | Loss: 1.8895\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:28 INFO\u001b[0m Step 241/1000 | Loss: 1.5987\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:28 INFO\u001b[0m Step 242/1000 | Loss: 1.7401\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:28 INFO\u001b[0m Step 242/1000 | Loss: 1.8386\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:28 INFO\u001b[0m Step 242/1000 | Loss: 1.7386\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:28 INFO\u001b[0m Step 242/1000 | Loss: 1.6754\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:28 INFO\u001b[0m Step 242/1000 | Loss: 1.8244\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:28 INFO\u001b[0m Step 242/1000 | Loss: 1.7446\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:28 INFO\u001b[0m Step 242/1000 | Loss: 1.6028\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:28 INFO\u001b[0m Step 242/1000 | Loss: 1.9524\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:29 INFO\u001b[0m Step 243/1000 | Loss: 2.0911\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:29 INFO\u001b[0m Step 243/1000 | Loss: 2.0295\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:29 INFO\u001b[0m Step 243/1000 | Loss: 1.9191\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:29 INFO\u001b[0m Step 243/1000 | Loss: 2.0625\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:29 INFO\u001b[0m Step 243/1000 | Loss: 1.9393\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:29 INFO\u001b[0m Step 243/1000 | Loss: 1.9091\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:29 INFO\u001b[0m Step 243/1000 | Loss: 1.7560\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:29 INFO\u001b[0m Step 243/1000 | Loss: 1.8803\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:29 INFO\u001b[0m Step 244/1000 | Loss: 2.0396\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:29 INFO\u001b[0m Step 244/1000 | Loss: 2.3465\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:29 INFO\u001b[0m Step 244/1000 | Loss: 2.0695\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:29 INFO\u001b[0m Step 244/1000 | Loss: 1.8984\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:29 INFO\u001b[0m Step 244/1000 | Loss: 2.3149\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:29 INFO\u001b[0m Step 244/1000 | Loss: 1.9672\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:29 INFO\u001b[0m Step 244/1000 | Loss: 2.5803\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:29 INFO\u001b[0m Step 244/1000 | Loss: 2.1574\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:29 INFO\u001b[0m Step 245/1000 | Loss: 1.6361\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:29 INFO\u001b[0m Step 245/1000 | Loss: 2.0264\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:29 INFO\u001b[0m Step 245/1000 | Loss: 2.0382\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:29 INFO\u001b[0m Step 245/1000 | Loss: 2.2998\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:29 INFO\u001b[0m Step 245/1000 | Loss: 2.2868\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:29 INFO\u001b[0m Step 245/1000 | Loss: 2.1734\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:29 INFO\u001b[0m Step 245/1000 | Loss: 1.9456\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:29 INFO\u001b[0m Step 245/1000 | Loss: 2.3868\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:30 INFO\u001b[0m Step 246/1000 | Loss: 2.4350\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:30 INFO\u001b[0m Step 246/1000 | Loss: 2.5928\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:30 INFO\u001b[0m Step 246/1000 | Loss: 2.4304\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:30 INFO\u001b[0m Step 246/1000 | Loss: 2.2884\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:30 INFO\u001b[0m Step 246/1000 | Loss: 1.9269\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:30 INFO\u001b[0m Step 246/1000 | Loss: 2.6218\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:30 INFO\u001b[0m Step 246/1000 | Loss: 2.4843\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:30 INFO\u001b[0m Step 246/1000 | Loss: 2.1946\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:30 INFO\u001b[0m Step 247/1000 | Loss: 2.4960\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:30 INFO\u001b[0m Step 247/1000 | Loss: 2.4901\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:30 INFO\u001b[0m Step 247/1000 | Loss: 2.9026\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:30 INFO\u001b[0m Step 247/1000 | Loss: 2.4460\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:30 INFO\u001b[0m Step 247/1000 | Loss: 2.1744\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:30 INFO\u001b[0m Step 247/1000 | Loss: 2.3557\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:30 INFO\u001b[0m Step 247/1000 | Loss: 2.7496\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:30 INFO\u001b[0m Step 247/1000 | Loss: 2.3900\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:31 INFO\u001b[0m Step 248/1000 | Loss: 2.6336\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:31 INFO\u001b[0m Step 248/1000 | Loss: 2.1867\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:31 INFO\u001b[0m Step 248/1000 | Loss: 2.6196\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:31 INFO\u001b[0m Step 248/1000 | Loss: 2.6187\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:31 INFO\u001b[0m Step 248/1000 | Loss: 2.7874\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:31 INFO\u001b[0m Step 248/1000 | Loss: 2.6672\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:31 INFO\u001b[0m Step 248/1000 | Loss: 2.4532\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:31 INFO\u001b[0m Step 248/1000 | Loss: 2.5661\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:31 INFO\u001b[0m Step 249/1000 | Loss: 3.4148\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:31 INFO\u001b[0m Step 249/1000 | Loss: 2.4665\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:31 INFO\u001b[0m Step 249/1000 | Loss: 2.5650\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:31 INFO\u001b[0m Step 249/1000 | Loss: 2.6838\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:31 INFO\u001b[0m Step 249/1000 | Loss: 2.4612\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:31 INFO\u001b[0m Step 249/1000 | Loss: 2.9219\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:31 INFO\u001b[0m Step 249/1000 | Loss: 2.6319\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:31 INFO\u001b[0m Step 249/1000 | Loss: 2.5788\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:31 INFO\u001b[0m Step 250/1000 | Loss: 2.6364\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:31 INFO\u001b[0m Step 250/1000 | Loss: 2.9732\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:31 INFO\u001b[0m Step 250/1000 | Loss: 2.7525\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:31 INFO\u001b[0m Step 250/1000 | Loss: 3.0480\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:31 INFO\u001b[0m Step 250/1000 | Loss: 3.1368\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:31 INFO\u001b[0m Step 250/1000 | Loss: 2.8376\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:31 INFO\u001b[0m Step 250/1000 | Loss: 2.6242\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:31 INFO\u001b[0m Step 250/1000 | Loss: 2.7668\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:32 INFO\u001b[0m Step 251/1000 | Loss: 3.6891\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:32 INFO\u001b[0m Step 251/1000 | Loss: 2.4110\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:32 INFO\u001b[0m Step 251/1000 | Loss: 3.0032\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:32 INFO\u001b[0m Step 251/1000 | Loss: 3.3708\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:32 INFO\u001b[0m Step 251/1000 | Loss: 2.9214\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:32 INFO\u001b[0m Step 251/1000 | Loss: 3.2001\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:32 INFO\u001b[0m Step 251/1000 | Loss: 3.0232\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:32 INFO\u001b[0m Step 251/1000 | Loss: 3.0518\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:32 INFO\u001b[0m Step 252/1000 | Loss: 3.6021\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:32 INFO\u001b[0m Step 252/1000 | Loss: 3.3297\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:32 INFO\u001b[0m Step 252/1000 | Loss: 2.4355\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:32 INFO\u001b[0m Step 252/1000 | Loss: 2.9756\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:32 INFO\u001b[0m Step 252/1000 | Loss: 3.0670\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:32 INFO\u001b[0m Step 252/1000 | Loss: 3.1104\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:32 INFO\u001b[0m Step 252/1000 | Loss: 3.3601\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:32 INFO\u001b[0m Step 252/1000 | Loss: 3.1154\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:33 INFO\u001b[0m Step 253/1000 | Loss: 2.9380\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:33 INFO\u001b[0m Step 253/1000 | Loss: 2.9959\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:33 INFO\u001b[0m Step 253/1000 | Loss: 2.5898\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:33 INFO\u001b[0m Step 253/1000 | Loss: 2.8974\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:33 INFO\u001b[0m Step 253/1000 | Loss: 3.1284\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:33 INFO\u001b[0m Step 253/1000 | Loss: 2.9589\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:33 INFO\u001b[0m Step 253/1000 | Loss: 2.9448\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:33 INFO\u001b[0m Step 253/1000 | Loss: 3.0741\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:33 INFO\u001b[0m Step 254/1000 | Loss: 2.7121\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:33 INFO\u001b[0m Step 254/1000 | Loss: 2.8170\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:33 INFO\u001b[0m Step 254/1000 | Loss: 2.7899\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:33 INFO\u001b[0m Step 254/1000 | Loss: 3.2019\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:33 INFO\u001b[0m Step 254/1000 | Loss: 2.9714\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:33 INFO\u001b[0m Step 254/1000 | Loss: 3.4023\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:33 INFO\u001b[0m Step 254/1000 | Loss: 2.9294\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:33 INFO\u001b[0m Step 254/1000 | Loss: 2.9094\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:33 INFO\u001b[0m Step 255/1000 | Loss: 2.6705\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:33 INFO\u001b[0m Step 255/1000 | Loss: 2.6180\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:33 INFO\u001b[0m Step 255/1000 | Loss: 2.3952\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:33 INFO\u001b[0m Step 255/1000 | Loss: 3.1450\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:33 INFO\u001b[0m Step 255/1000 | Loss: 2.8560\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:33 INFO\u001b[0m Step 255/1000 | Loss: 2.7051\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:33 INFO\u001b[0m Step 255/1000 | Loss: 2.7491\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:33 INFO\u001b[0m Step 255/1000 | Loss: 2.8900\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:34 INFO\u001b[0m Step 256/1000 | Loss: 2.5261\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:34 INFO\u001b[0m Step 256/1000 | Loss: 2.7961\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:34 INFO\u001b[0m Step 256/1000 | Loss: 2.6448\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:34 INFO\u001b[0m Step 256/1000 | Loss: 2.6710\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:34 INFO\u001b[0m Step 256/1000 | Loss: 2.7974\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:34 INFO\u001b[0m Step 256/1000 | Loss: 2.8599\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:34 INFO\u001b[0m Step 256/1000 | Loss: 2.3413\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:34 INFO\u001b[0m Step 256/1000 | Loss: 2.2899\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:34 INFO\u001b[0m Step 257/1000 | Loss: 2.7443\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:34 INFO\u001b[0m Step 257/1000 | Loss: 2.7401\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:34 INFO\u001b[0m Step 257/1000 | Loss: 2.4900\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:34 INFO\u001b[0m Step 257/1000 | Loss: 2.4465\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:34 INFO\u001b[0m Step 257/1000 | Loss: 2.5151\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:34 INFO\u001b[0m Step 257/1000 | Loss: 2.4303\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:34 INFO\u001b[0m Step 257/1000 | Loss: 2.3055\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:34 INFO\u001b[0m Step 257/1000 | Loss: 2.1187\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:35 INFO\u001b[0m Step 258/1000 | Loss: 2.7626\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:35 INFO\u001b[0m Step 258/1000 | Loss: 2.5960\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:35 INFO\u001b[0m Step 258/1000 | Loss: 2.5032\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:35 INFO\u001b[0m Step 258/1000 | Loss: 2.4756\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:35 INFO\u001b[0m Step 258/1000 | Loss: 2.5074\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:35 INFO\u001b[0m Step 258/1000 | Loss: 2.4010\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:35 INFO\u001b[0m Step 258/1000 | Loss: 2.5001\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:35 INFO\u001b[0m Step 258/1000 | Loss: 2.5542\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:35 INFO\u001b[0m Step 259/1000 | Loss: 3.2679\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:35 INFO\u001b[0m Step 259/1000 | Loss: 2.4584\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:35 INFO\u001b[0m Step 259/1000 | Loss: 2.5725\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:35 INFO\u001b[0m Step 259/1000 | Loss: 2.4858\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:35 INFO\u001b[0m Step 259/1000 | Loss: 2.4062\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:35 INFO\u001b[0m Step 259/1000 | Loss: 2.1127\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:35 INFO\u001b[0m Step 259/1000 | Loss: 2.7185\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:35 INFO\u001b[0m Step 259/1000 | Loss: 2.6380\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:35 INFO\u001b[0m Step 260/1000 | Loss: 1.9522\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:35 INFO\u001b[0m Step 260/1000 | Loss: 2.6775\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:35 INFO\u001b[0m Step 260/1000 | Loss: 2.2046\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:35 INFO\u001b[0m Step 260/1000 | Loss: 1.9955\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:35 INFO\u001b[0m Step 260/1000 | Loss: 2.4597\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:35 INFO\u001b[0m Step 260/1000 | Loss: 2.5654\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:35 INFO\u001b[0m Step 260/1000 | Loss: 2.4625\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:35 INFO\u001b[0m Step 260/1000 | Loss: 2.5939\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:36 INFO\u001b[0m Step 261/1000 | Loss: 2.3455\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:36 INFO\u001b[0m Step 261/1000 | Loss: 2.5907\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:36 INFO\u001b[0m Step 261/1000 | Loss: 2.1272\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:36 INFO\u001b[0m Step 261/1000 | Loss: 2.4007\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:36 INFO\u001b[0m Step 261/1000 | Loss: 2.5895\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:36 INFO\u001b[0m Step 261/1000 | Loss: 2.7223\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:36 INFO\u001b[0m Step 261/1000 | Loss: 2.2878\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:36 INFO\u001b[0m Step 261/1000 | Loss: 2.6578\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:36 INFO\u001b[0m Step 262/1000 | Loss: 2.5413\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:36 INFO\u001b[0m Step 262/1000 | Loss: 2.5501\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:36 INFO\u001b[0m Step 262/1000 | Loss: 2.9175\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:36 INFO\u001b[0m Step 262/1000 | Loss: 2.4298\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:36 INFO\u001b[0m Step 262/1000 | Loss: 1.9480\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:36 INFO\u001b[0m Step 262/1000 | Loss: 2.4466\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:36 INFO\u001b[0m Step 262/1000 | Loss: 2.8629\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:36 INFO\u001b[0m Step 262/1000 | Loss: 2.3996\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:37 INFO\u001b[0m Step 263/1000 | Loss: 2.5679\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:37 INFO\u001b[0m Step 263/1000 | Loss: 2.8915\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:37 INFO\u001b[0m Step 263/1000 | Loss: 2.8937\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:37 INFO\u001b[0m Step 263/1000 | Loss: 2.7844\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:37 INFO\u001b[0m Step 263/1000 | Loss: 2.7120\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:37 INFO\u001b[0m Step 263/1000 | Loss: 3.2348\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:37 INFO\u001b[0m Step 263/1000 | Loss: 2.8070\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:37 INFO\u001b[0m Step 263/1000 | Loss: 2.9210\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:37 INFO\u001b[0m Step 264/1000 | Loss: 2.6677\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:37 INFO\u001b[0m Step 264/1000 | Loss: 2.9132\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:37 INFO\u001b[0m Step 264/1000 | Loss: 2.7698\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:37 INFO\u001b[0m Step 264/1000 | Loss: 2.8125\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:37 INFO\u001b[0m Step 264/1000 | Loss: 2.8021\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:37 INFO\u001b[0m Step 264/1000 | Loss: 2.4593\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:37 INFO\u001b[0m Step 264/1000 | Loss: 2.5484\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:37 INFO\u001b[0m Step 264/1000 | Loss: 2.4526\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:38 INFO\u001b[0m Step 265/1000 | Loss: 2.6067\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:38 INFO\u001b[0m Step 265/1000 | Loss: 2.8992\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:38 INFO\u001b[0m Step 265/1000 | Loss: 2.5969\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:38 INFO\u001b[0m Step 265/1000 | Loss: 2.5335\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:38 INFO\u001b[0m Step 265/1000 | Loss: 3.0412\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:38 INFO\u001b[0m Step 265/1000 | Loss: 2.9002\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:38 INFO\u001b[0m Step 265/1000 | Loss: 3.0827\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:38 INFO\u001b[0m Step 265/1000 | Loss: 2.7887\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:38 INFO\u001b[0m Step 266/1000 | Loss: 2.9818\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:38 INFO\u001b[0m Step 266/1000 | Loss: 3.0147\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:38 INFO\u001b[0m Step 266/1000 | Loss: 2.6842\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:38 INFO\u001b[0m Step 266/1000 | Loss: 3.0318\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:38 INFO\u001b[0m Step 266/1000 | Loss: 3.1935\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:38 INFO\u001b[0m Step 266/1000 | Loss: 2.8050\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:38 INFO\u001b[0m Step 266/1000 | Loss: 3.2829\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:38 INFO\u001b[0m Step 266/1000 | Loss: 3.1547\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:38 INFO\u001b[0m Step 267/1000 | Loss: 2.8783\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:38 INFO\u001b[0m Step 267/1000 | Loss: 3.0997\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:38 INFO\u001b[0m Step 267/1000 | Loss: 2.9189\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:38 INFO\u001b[0m Step 267/1000 | Loss: 3.2123\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:38 INFO\u001b[0m Step 267/1000 | Loss: 3.0300\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:38 INFO\u001b[0m Step 267/1000 | Loss: 2.8721\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:38 INFO\u001b[0m Step 267/1000 | Loss: 2.7220\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:38 INFO\u001b[0m Step 267/1000 | Loss: 2.8857\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:39 INFO\u001b[0m Step 268/1000 | Loss: 3.0264\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:39 INFO\u001b[0m Step 268/1000 | Loss: 3.2883\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:39 INFO\u001b[0m Step 268/1000 | Loss: 2.9362\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:39 INFO\u001b[0m Step 268/1000 | Loss: 2.8250\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:39 INFO\u001b[0m Step 268/1000 | Loss: 2.9031\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:39 INFO\u001b[0m Step 268/1000 | Loss: 2.5203\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:39 INFO\u001b[0m Step 268/1000 | Loss: 2.4453\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:39 INFO\u001b[0m Step 268/1000 | Loss: 2.9928\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:39 INFO\u001b[0m Step 269/1000 | Loss: 2.8246\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:39 INFO\u001b[0m Step 269/1000 | Loss: 2.8071\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:39 INFO\u001b[0m Step 269/1000 | Loss: 2.9422\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:39 INFO\u001b[0m Step 269/1000 | Loss: 3.3326\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:39 INFO\u001b[0m Step 269/1000 | Loss: 3.1709\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:39 INFO\u001b[0m Step 269/1000 | Loss: 2.6456\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:39 INFO\u001b[0m Step 269/1000 | Loss: 3.3687\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:39 INFO\u001b[0m Step 269/1000 | Loss: 2.9998\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:40 INFO\u001b[0m Step 270/1000 | Loss: 3.0368\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:40 INFO\u001b[0m Step 270/1000 | Loss: 2.9203\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:40 INFO\u001b[0m Step 270/1000 | Loss: 2.7384\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:40 INFO\u001b[0m Step 270/1000 | Loss: 4.0506\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:40 INFO\u001b[0m Step 270/1000 | Loss: 2.7252\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:40 INFO\u001b[0m Step 270/1000 | Loss: 2.9643\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:40 INFO\u001b[0m Step 270/1000 | Loss: 2.7189\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:40 INFO\u001b[0m Step 270/1000 | Loss: 2.9202\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:40 INFO\u001b[0m Step 271/1000 | Loss: 3.1088\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:40 INFO\u001b[0m Step 271/1000 | Loss: 2.8907\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:40 INFO\u001b[0m Step 271/1000 | Loss: 3.2267\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:40 INFO\u001b[0m Step 271/1000 | Loss: 2.7165\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:40 INFO\u001b[0m Step 271/1000 | Loss: 2.6449\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:40 INFO\u001b[0m Step 271/1000 | Loss: 3.8028\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:40 INFO\u001b[0m Step 271/1000 | Loss: 2.5814\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:40 INFO\u001b[0m Step 271/1000 | Loss: 2.3489\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:40 INFO\u001b[0m Step 272/1000 | Loss: 3.2253\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:40 INFO\u001b[0m Step 272/1000 | Loss: 2.4802\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:40 INFO\u001b[0m Step 272/1000 | Loss: 2.7665\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:40 INFO\u001b[0m Step 272/1000 | Loss: 3.4138\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:40 INFO\u001b[0m Step 272/1000 | Loss: 3.5776\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:40 INFO\u001b[0m Step 272/1000 | Loss: 2.4848\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:40 INFO\u001b[0m Step 272/1000 | Loss: 2.7767\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:40 INFO\u001b[0m Step 272/1000 | Loss: 3.0220\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:41 INFO\u001b[0m Step 273/1000 | Loss: 2.4688\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:41 INFO\u001b[0m Step 273/1000 | Loss: 2.4060\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:41 INFO\u001b[0m Step 273/1000 | Loss: 2.7669\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:41 INFO\u001b[0m Step 273/1000 | Loss: 2.7110\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:41 INFO\u001b[0m Step 273/1000 | Loss: 2.7874\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:41 INFO\u001b[0m Step 273/1000 | Loss: 2.9947\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:41 INFO\u001b[0m Step 273/1000 | Loss: 2.5504\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:41 INFO\u001b[0m Step 273/1000 | Loss: 2.9222\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:41 INFO\u001b[0m Step 274/1000 | Loss: 2.7485\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:41 INFO\u001b[0m Step 274/1000 | Loss: 2.6011\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:41 INFO\u001b[0m Step 274/1000 | Loss: 2.4942\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:41 INFO\u001b[0m Step 274/1000 | Loss: 2.7882\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:41 INFO\u001b[0m Step 274/1000 | Loss: 3.0249\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:41 INFO\u001b[0m Step 274/1000 | Loss: 2.5761\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:41 INFO\u001b[0m Step 274/1000 | Loss: 2.4658\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:41 INFO\u001b[0m Step 274/1000 | Loss: 3.3501\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:42 INFO\u001b[0m Step 275/1000 | Loss: 3.2010\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:42 INFO\u001b[0m Step 275/1000 | Loss: 2.8062\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:42 INFO\u001b[0m Step 275/1000 | Loss: 2.2423\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:42 INFO\u001b[0m Step 275/1000 | Loss: 2.2660\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:42 INFO\u001b[0m Step 275/1000 | Loss: 3.2784\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:42 INFO\u001b[0m Step 275/1000 | Loss: 2.0675\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:42 INFO\u001b[0m Step 275/1000 | Loss: 2.4223\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:42 INFO\u001b[0m Step 275/1000 | Loss: 3.1723\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:42 INFO\u001b[0m Step 276/1000 | Loss: 2.8860\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:42 INFO\u001b[0m Step 276/1000 | Loss: 2.4525\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:42 INFO\u001b[0m Step 276/1000 | Loss: 2.7065\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:42 INFO\u001b[0m Step 276/1000 | Loss: 2.6344\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:42 INFO\u001b[0m Step 276/1000 | Loss: 2.7643\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:42 INFO\u001b[0m Step 276/1000 | Loss: 3.0533\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:42 INFO\u001b[0m Step 276/1000 | Loss: 2.5098\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:42 INFO\u001b[0m Step 276/1000 | Loss: 2.6173\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:42 INFO\u001b[0m Step 277/1000 | Loss: 2.3578\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:42 INFO\u001b[0m Step 277/1000 | Loss: 2.4280\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:42 INFO\u001b[0m Step 277/1000 | Loss: 3.0239\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:42 INFO\u001b[0m Step 277/1000 | Loss: 2.5873\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:42 INFO\u001b[0m Step 277/1000 | Loss: 2.9493\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:42 INFO\u001b[0m Step 277/1000 | Loss: 2.4659\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:42 INFO\u001b[0m Step 277/1000 | Loss: 2.5328\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:42 INFO\u001b[0m Step 277/1000 | Loss: 2.3238\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:43 INFO\u001b[0m Step 278/1000 | Loss: 2.3142\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:43 INFO\u001b[0m Step 278/1000 | Loss: 2.6507\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:43 INFO\u001b[0m Step 278/1000 | Loss: 3.1036\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:43 INFO\u001b[0m Step 278/1000 | Loss: 3.1937\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:43 INFO\u001b[0m Step 278/1000 | Loss: 2.3594\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:43 INFO\u001b[0m Step 278/1000 | Loss: 2.9356\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:43 INFO\u001b[0m Step 278/1000 | Loss: 2.4440\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:43 INFO\u001b[0m Step 278/1000 | Loss: 2.7795\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:43 INFO\u001b[0m Step 279/1000 | Loss: 2.5778\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:43 INFO\u001b[0m Step 279/1000 | Loss: 2.6583\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:43 INFO\u001b[0m Step 279/1000 | Loss: 2.9341\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:43 INFO\u001b[0m Step 279/1000 | Loss: 2.3278\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:43 INFO\u001b[0m Step 279/1000 | Loss: 2.4422\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:43 INFO\u001b[0m Step 279/1000 | Loss: 2.8644\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:43 INFO\u001b[0m Step 279/1000 | Loss: 2.7946\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:43 INFO\u001b[0m Step 279/1000 | Loss: 2.2675\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:44 INFO\u001b[0m Step 280/1000 | Loss: 2.8042\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:44 INFO\u001b[0m Step 280/1000 | Loss: 2.4781\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:44 INFO\u001b[0m Step 280/1000 | Loss: 3.1962\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:44 INFO\u001b[0m Step 280/1000 | Loss: 2.1142\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:44 INFO\u001b[0m Step 280/1000 | Loss: 2.5750\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:44 INFO\u001b[0m Step 280/1000 | Loss: 2.2641\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:44 INFO\u001b[0m Step 280/1000 | Loss: 2.9391\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:44 INFO\u001b[0m Step 280/1000 | Loss: 2.5274\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:44 INFO\u001b[0m Step 281/1000 | Loss: 2.7190\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:44 INFO\u001b[0m Step 281/1000 | Loss: 2.3633\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:44 INFO\u001b[0m Step 281/1000 | Loss: 2.9275\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:44 INFO\u001b[0m Step 281/1000 | Loss: 2.5709\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:44 INFO\u001b[0m Step 281/1000 | Loss: 2.6380\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:44 INFO\u001b[0m Step 281/1000 | Loss: 2.3814\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:44 INFO\u001b[0m Step 281/1000 | Loss: 2.3008\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:44 INFO\u001b[0m Step 281/1000 | Loss: 2.5366\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:45 INFO\u001b[0m Step 282/1000 | Loss: 2.6365\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:45 INFO\u001b[0m Step 282/1000 | Loss: 2.6209\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:45 INFO\u001b[0m Step 282/1000 | Loss: 2.3311\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:45 INFO\u001b[0m Step 282/1000 | Loss: 2.3881\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:45 INFO\u001b[0m Step 282/1000 | Loss: 2.4410\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:45 INFO\u001b[0m Step 282/1000 | Loss: 2.6067\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:45 INFO\u001b[0m Step 282/1000 | Loss: 2.6533\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:45 INFO\u001b[0m Step 282/1000 | Loss: 1.9438\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:45 INFO\u001b[0m Step 283/1000 | Loss: 2.3002\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:45 INFO\u001b[0m Step 283/1000 | Loss: 1.9816\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:45 INFO\u001b[0m Step 283/1000 | Loss: 2.3213\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:45 INFO\u001b[0m Step 283/1000 | Loss: 2.1376\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:45 INFO\u001b[0m Step 283/1000 | Loss: 2.3042\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:45 INFO\u001b[0m Step 283/1000 | Loss: 1.9101\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:45 INFO\u001b[0m Step 283/1000 | Loss: 2.2307\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:45 INFO\u001b[0m Step 283/1000 | Loss: 2.1970\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:45 INFO\u001b[0m Step 284/1000 | Loss: 2.5693\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:45 INFO\u001b[0m Step 284/1000 | Loss: 2.6907\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:45 INFO\u001b[0m Step 284/1000 | Loss: 2.3567\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:45 INFO\u001b[0m Step 284/1000 | Loss: 2.4245\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:45 INFO\u001b[0m Step 284/1000 | Loss: 2.0949\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:45 INFO\u001b[0m Step 284/1000 | Loss: 1.7324\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:45 INFO\u001b[0m Step 284/1000 | Loss: 2.0733\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:45 INFO\u001b[0m Step 284/1000 | Loss: 2.5376\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:46 INFO\u001b[0m Step 285/1000 | Loss: 2.3577\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:46 INFO\u001b[0m Step 285/1000 | Loss: 2.5695\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:46 INFO\u001b[0m Step 285/1000 | Loss: 2.2444\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:46 INFO\u001b[0m Step 285/1000 | Loss: 3.2333\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:46 INFO\u001b[0m Step 285/1000 | Loss: 2.2499\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:46 INFO\u001b[0m Step 285/1000 | Loss: 2.2670\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:46 INFO\u001b[0m Step 285/1000 | Loss: 2.3782\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:46 INFO\u001b[0m Step 285/1000 | Loss: 2.4481\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:46 INFO\u001b[0m Step 286/1000 | Loss: 2.7491\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:46 INFO\u001b[0m Step 286/1000 | Loss: 2.4570\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:46 INFO\u001b[0m Step 286/1000 | Loss: 2.3568\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:46 INFO\u001b[0m Step 286/1000 | Loss: 2.5833\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:46 INFO\u001b[0m Step 286/1000 | Loss: 3.1462\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:46 INFO\u001b[0m Step 286/1000 | Loss: 2.2300\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:46 INFO\u001b[0m Step 286/1000 | Loss: 2.7193\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:46 INFO\u001b[0m Step 286/1000 | Loss: 2.3725\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:47 INFO\u001b[0m Step 287/1000 | Loss: 2.8963\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:47 INFO\u001b[0m Step 287/1000 | Loss: 2.0939\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:47 INFO\u001b[0m Step 287/1000 | Loss: 2.6382\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:47 INFO\u001b[0m Step 287/1000 | Loss: 2.9183\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:47 INFO\u001b[0m Step 287/1000 | Loss: 2.4415\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:47 INFO\u001b[0m Step 287/1000 | Loss: 2.5563\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:47 INFO\u001b[0m Step 287/1000 | Loss: 2.4747\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:47 INFO\u001b[0m Step 287/1000 | Loss: 2.1406\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:47 INFO\u001b[0m Step 288/1000 | Loss: 2.9956\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:47 INFO\u001b[0m Step 288/1000 | Loss: 2.8979\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:47 INFO\u001b[0m Step 288/1000 | Loss: 2.4451\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:47 INFO\u001b[0m Step 288/1000 | Loss: 2.5509\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:47 INFO\u001b[0m Step 288/1000 | Loss: 2.5583\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:47 INFO\u001b[0m Step 288/1000 | Loss: 2.2959\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:47 INFO\u001b[0m Step 288/1000 | Loss: 2.5979\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:47 INFO\u001b[0m Step 288/1000 | Loss: 2.6192\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:49 INFO\u001b[0m Step 289/1000 | Loss: 2.8408\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:49 INFO\u001b[0m Step 289/1000 | Loss: 2.2083\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:49 INFO\u001b[0m Step 289/1000 | Loss: 3.8931\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:49 INFO\u001b[0m Step 289/1000 | Loss: 2.6648\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:49 INFO\u001b[0m Step 289/1000 | Loss: 2.9094\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:49 INFO\u001b[0m Step 289/1000 | Loss: 3.0126\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:49 INFO\u001b[0m Step 289/1000 | Loss: 2.4917\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:49 INFO\u001b[0m Step 289/1000 | Loss: 2.6451\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:50 INFO\u001b[0m Step 290/1000 | Loss: 2.1041\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:50 INFO\u001b[0m Step 290/1000 | Loss: 3.0354\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:50 INFO\u001b[0m Step 290/1000 | Loss: 2.4953\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:50 INFO\u001b[0m Step 290/1000 | Loss: 2.6666\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:50 INFO\u001b[0m Step 290/1000 | Loss: 2.4413\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:50 INFO\u001b[0m Step 290/1000 | Loss: 2.8650\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:50 INFO\u001b[0m Step 290/1000 | Loss: 1.9358\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:50 INFO\u001b[0m Step 290/1000 | Loss: 2.4361\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:54 INFO\u001b[0m Step 291/1000 | Loss: 2.7708\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:54 INFO\u001b[0m Step 291/1000 | Loss: 2.6126\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:54 INFO\u001b[0m Step 291/1000 | Loss: 2.1188\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:54 INFO\u001b[0m Step 291/1000 | Loss: 2.5136\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:54 INFO\u001b[0m Step 291/1000 | Loss: 2.4119\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:54 INFO\u001b[0m Step 291/1000 | Loss: 2.4304\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:54 INFO\u001b[0m Step 291/1000 | Loss: 2.2427\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:54 INFO\u001b[0m Step 291/1000 | Loss: 2.2401\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:57 INFO\u001b[0m Step 292/1000 | Loss: 2.4141\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:57 INFO\u001b[0m Step 292/1000 | Loss: 2.2449\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:57 INFO\u001b[0m Step 292/1000 | Loss: 2.6129\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:57 INFO\u001b[0m Step 292/1000 | Loss: 2.2130\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:57 INFO\u001b[0m Step 292/1000 | Loss: 2.3462\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:57 INFO\u001b[0m Step 292/1000 | Loss: 2.0835\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:57 INFO\u001b[0m Step 292/1000 | Loss: 2.9959\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:57 INFO\u001b[0m Step 292/1000 | Loss: 1.8815\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:58 INFO\u001b[0m Step 293/1000 | Loss: 2.6687\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:58 INFO\u001b[0m Step 293/1000 | Loss: 2.0555\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:58 INFO\u001b[0m Step 293/1000 | Loss: 2.3134\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:58 INFO\u001b[0m Step 293/1000 | Loss: 1.9215\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:58 INFO\u001b[0m Step 293/1000 | Loss: 2.1685\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:58 INFO\u001b[0m Step 293/1000 | Loss: 1.7093\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:58 INFO\u001b[0m Step 293/1000 | Loss: 2.1572\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:58 INFO\u001b[0m Step 293/1000 | Loss: 2.2015\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:31:59 INFO\u001b[0m Step 294/1000 | Loss: 2.6113\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:31:59 INFO\u001b[0m Step 294/1000 | Loss: 2.2072\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:31:59 INFO\u001b[0m Step 294/1000 | Loss: 2.6172\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:31:59 INFO\u001b[0m Step 294/1000 | Loss: 2.4438\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:31:59 INFO\u001b[0m Step 294/1000 | Loss: 2.4608\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:31:59 INFO\u001b[0m Step 294/1000 | Loss: 2.1987\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:31:59 INFO\u001b[0m Step 294/1000 | Loss: 2.5429\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:31:59 INFO\u001b[0m Step 294/1000 | Loss: 2.7570\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:32:01 INFO\u001b[0m Step 295/1000 | Loss: 2.3505\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:32:01 INFO\u001b[0m Step 295/1000 | Loss: 2.4476\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:32:01 INFO\u001b[0m Step 295/1000 | Loss: 1.9648\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:32:01 INFO\u001b[0m Step 295/1000 | Loss: 2.5480\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:32:01 INFO\u001b[0m Step 295/1000 | Loss: 2.2131\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:32:01 INFO\u001b[0m Step 295/1000 | Loss: 2.4007\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:32:01 INFO\u001b[0m Step 295/1000 | Loss: 2.0735\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:32:01 INFO\u001b[0m Step 295/1000 | Loss: 2.3766\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:32:03 INFO\u001b[0m Step 296/1000 | Loss: 2.5683\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:32:03 INFO\u001b[0m Step 296/1000 | Loss: 2.0548\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:32:03 INFO\u001b[0m Step 296/1000 | Loss: 2.1702\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:32:03 INFO\u001b[0m Step 296/1000 | Loss: 2.3550\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:32:03 INFO\u001b[0m Step 296/1000 | Loss: 2.2946\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:32:03 INFO\u001b[0m Step 296/1000 | Loss: 2.2669\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:32:03 INFO\u001b[0m Step 296/1000 | Loss: 2.2574\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:32:03 INFO\u001b[0m Step 296/1000 | Loss: 2.8002\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:32:04 INFO\u001b[0m Step 297/1000 | Loss: 2.3278\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:32:04 INFO\u001b[0m Step 297/1000 | Loss: 2.1511\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:32:04 INFO\u001b[0m Step 297/1000 | Loss: 2.4192\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:32:04 INFO\u001b[0m Step 297/1000 | Loss: 2.1269\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:32:04 INFO\u001b[0m Step 297/1000 | Loss: 2.2005\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:32:04 INFO\u001b[0m Step 297/1000 | Loss: 1.6993\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:32:04 INFO\u001b[0m Step 297/1000 | Loss: 2.4599\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:32:04 INFO\u001b[0m Step 297/1000 | Loss: 2.2043\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:32:05 INFO\u001b[0m Step 298/1000 | Loss: 2.8311\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:32:05 INFO\u001b[0m Step 298/1000 | Loss: 1.8400\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:32:05 INFO\u001b[0m Step 298/1000 | Loss: 3.1561\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:32:05 INFO\u001b[0m Step 298/1000 | Loss: 2.7093\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:32:05 INFO\u001b[0m Step 298/1000 | Loss: 2.2746\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:32:05 INFO\u001b[0m Step 298/1000 | Loss: 2.2854\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:32:05 INFO\u001b[0m Step 298/1000 | Loss: 1.8108\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:32:05 INFO\u001b[0m Step 298/1000 | Loss: 2.3857\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:32:06 INFO\u001b[0m Step 299/1000 | Loss: 2.3817\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:32:06 INFO\u001b[0m Step 299/1000 | Loss: 2.6101\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:32:06 INFO\u001b[0m Step 299/1000 | Loss: 2.2449\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:32:06 INFO\u001b[0m Step 299/1000 | Loss: 2.3831\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:32:06 INFO\u001b[0m Step 299/1000 | Loss: 2.8522\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:32:06 INFO\u001b[0m Step 299/1000 | Loss: 2.6273\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:32:06 INFO\u001b[0m Step 299/1000 | Loss: 2.1697\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:32:06 INFO\u001b[0m Step 299/1000 | Loss: 2.6710\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:32:09 INFO\u001b[0m Step 300/1000 | Loss: 2.5522\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:32:09 INFO\u001b[0m Step 300/1000 | Loss: 1.9847\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:32:09 INFO\u001b[0m Step 300/1000 | Loss: 1.9793\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:32:09 INFO\u001b[0m Step 300/1000 | Loss: 1.8229\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:32:09 INFO\u001b[0m Step 300/1000 | Loss: 2.3440\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:32:09 INFO\u001b[0m Step 300/1000 | Loss: 2.0210\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:32:09 INFO\u001b[0m Step 300/1000 | Loss: 2.1196\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:32:09 INFO\u001b[0m Step 300/1000 | Loss: 2.2552\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:32:12 INFO\u001b[0m Step 301/1000 | Loss: 2.0859\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:32:12 INFO\u001b[0m Step 301/1000 | Loss: 2.1370\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:32:12 INFO\u001b[0m Step 301/1000 | Loss: 2.3355\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:32:12 INFO\u001b[0m Step 301/1000 | Loss: 2.2162\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:32:12 INFO\u001b[0m Step 301/1000 | Loss: 2.1487\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:32:12 INFO\u001b[0m Step 301/1000 | Loss: 1.8616\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:32:12 INFO\u001b[0m Step 301/1000 | Loss: 2.0346\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:32:12 INFO\u001b[0m Step 301/1000 | Loss: 2.4266\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:32:15 INFO\u001b[0m Step 302/1000 | Loss: 2.3833\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:32:15 INFO\u001b[0m Step 302/1000 | Loss: 2.0024\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:32:15 INFO\u001b[0m Step 302/1000 | Loss: 2.3503\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:32:15 INFO\u001b[0m Step 302/1000 | Loss: 2.9791\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:32:15 INFO\u001b[0m Step 302/1000 | Loss: 2.0602\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:32:15 INFO\u001b[0m Step 302/1000 | Loss: 2.1906\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:32:15 INFO\u001b[0m Step 302/1000 | Loss: 2.3968\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:32:15 INFO\u001b[0m Step 302/1000 | Loss: 2.0531\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:32:19 INFO\u001b[0m Step 303/1000 | Loss: 2.1326\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:32:19 INFO\u001b[0m Step 303/1000 | Loss: 2.4717\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:32:19 INFO\u001b[0m Step 303/1000 | Loss: 1.9823\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:32:19 INFO\u001b[0m Step 303/1000 | Loss: 2.0855\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:32:19 INFO\u001b[0m Step 303/1000 | Loss: 2.7899\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:32:19 INFO\u001b[0m Step 303/1000 | Loss: 2.3763\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:32:19 INFO\u001b[0m Step 303/1000 | Loss: 2.1077\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:32:19 INFO\u001b[0m Step 303/1000 | Loss: 2.2913\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:32:23 INFO\u001b[0m Step 304/1000 | Loss: 1.7860\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:32:23 INFO\u001b[0m Step 304/1000 | Loss: 2.1839\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:32:23 INFO\u001b[0m Step 304/1000 | Loss: 2.1582\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:32:23 INFO\u001b[0m Step 304/1000 | Loss: 1.7750\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:32:23 INFO\u001b[0m Step 304/1000 | Loss: 2.8759\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:32:23 INFO\u001b[0m Step 304/1000 | Loss: 2.2473\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:32:23 INFO\u001b[0m Step 304/1000 | Loss: 2.0547\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:32:23 INFO\u001b[0m Step 304/1000 | Loss: 2.3065\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:32:26 INFO\u001b[0m Step 305/1000 | Loss: 1.9398\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:32:26 INFO\u001b[0m Step 305/1000 | Loss: 2.1391\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:32:26 INFO\u001b[0m Step 305/1000 | Loss: 2.2892\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:32:26 INFO\u001b[0m Step 305/1000 | Loss: 2.3241\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:32:26 INFO\u001b[0m Step 305/1000 | Loss: 1.8613\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:32:26 INFO\u001b[0m Step 305/1000 | Loss: 2.0480\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:32:26 INFO\u001b[0m Step 305/1000 | Loss: 2.6839\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:32:26 INFO\u001b[0m Step 305/1000 | Loss: 1.9881\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:32:28 INFO\u001b[0m Step 306/1000 | Loss: 2.3914\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:32:28 INFO\u001b[0m Step 306/1000 | Loss: 2.4713\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:32:28 INFO\u001b[0m Step 306/1000 | Loss: 1.9439\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:32:28 INFO\u001b[0m Step 306/1000 | Loss: 2.1132\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:32:28 INFO\u001b[0m Step 306/1000 | Loss: 2.2686\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:32:28 INFO\u001b[0m Step 306/1000 | Loss: 2.4122\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:32:28 INFO\u001b[0m Step 306/1000 | Loss: 2.2436\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:32:28 INFO\u001b[0m Step 306/1000 | Loss: 2.4276\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:32:30 INFO\u001b[0m Step 307/1000 | Loss: 2.1827\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:32:30 INFO\u001b[0m Step 307/1000 | Loss: 1.9526\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:32:30 INFO\u001b[0m Step 307/1000 | Loss: 2.3022\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:32:30 INFO\u001b[0m Step 307/1000 | Loss: 2.4804\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:32:30 INFO\u001b[0m Step 307/1000 | Loss: 2.1835\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:32:30 INFO\u001b[0m Step 307/1000 | Loss: 2.2500\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:32:30 INFO\u001b[0m Step 307/1000 | Loss: 2.1425\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:32:30 INFO\u001b[0m Step 307/1000 | Loss: 1.7874\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:32:31 INFO\u001b[0m Step 308/1000 | Loss: 2.4698\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:32:31 INFO\u001b[0m Step 308/1000 | Loss: 1.9343\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:32:31 INFO\u001b[0m Step 308/1000 | Loss: 2.6218\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:32:31 INFO\u001b[0m Step 308/1000 | Loss: 2.1028\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:32:31 INFO\u001b[0m Step 308/1000 | Loss: 2.4211\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:32:31 INFO\u001b[0m Step 308/1000 | Loss: 2.0794\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:32:31 INFO\u001b[0m Step 308/1000 | Loss: 2.4886\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:32:31 INFO\u001b[0m Step 308/1000 | Loss: 1.6522\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:32:34 INFO\u001b[0m Step 309/1000 | Loss: 2.2292\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:32:34 INFO\u001b[0m Step 309/1000 | Loss: 1.8880\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:32:34 INFO\u001b[0m Step 309/1000 | Loss: 2.0854\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:32:34 INFO\u001b[0m Step 309/1000 | Loss: 2.0410\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:32:34 INFO\u001b[0m Step 309/1000 | Loss: 1.8193\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:32:34 INFO\u001b[0m Step 309/1000 | Loss: 2.0770\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:32:34 INFO\u001b[0m Step 309/1000 | Loss: 2.3707\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:32:34 INFO\u001b[0m Step 309/1000 | Loss: 2.2662\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:32:36 INFO\u001b[0m Step 310/1000 | Loss: 1.9544\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:32:36 INFO\u001b[0m Step 310/1000 | Loss: 1.8633\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:32:36 INFO\u001b[0m Step 310/1000 | Loss: 2.2708\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:32:36 INFO\u001b[0m Step 310/1000 | Loss: 2.4345\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:32:36 INFO\u001b[0m Step 310/1000 | Loss: 2.2994\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:32:36 INFO\u001b[0m Step 310/1000 | Loss: 2.2968\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:32:36 INFO\u001b[0m Step 310/1000 | Loss: 2.0455\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:32:36 INFO\u001b[0m Step 310/1000 | Loss: 2.2991\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:32:37 INFO\u001b[0m Step 311/1000 | Loss: 1.9992\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:32:37 INFO\u001b[0m Step 311/1000 | Loss: 1.8151\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:32:37 INFO\u001b[0m Step 311/1000 | Loss: 1.7980\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:32:37 INFO\u001b[0m Step 311/1000 | Loss: 2.6167\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:32:37 INFO\u001b[0m Step 311/1000 | Loss: 2.3572\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:32:37 INFO\u001b[0m Step 311/1000 | Loss: 2.0058\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:32:37 INFO\u001b[0m Step 311/1000 | Loss: 2.0399\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:32:37 INFO\u001b[0m Step 311/1000 | Loss: 2.6379\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:32:38 INFO\u001b[0m Step 312/1000 | Loss: 1.9910\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:32:38 INFO\u001b[0m Step 312/1000 | Loss: 1.9985\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:32:38 INFO\u001b[0m Step 312/1000 | Loss: 2.1766\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:32:38 INFO\u001b[0m Step 312/1000 | Loss: 2.1228\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:32:38 INFO\u001b[0m Step 312/1000 | Loss: 1.9610\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:32:38 INFO\u001b[0m Step 312/1000 | Loss: 2.8906\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:32:38 INFO\u001b[0m Step 312/1000 | Loss: 1.8866\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:32:38 INFO\u001b[0m Step 312/1000 | Loss: 2.2389\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:32:41 INFO\u001b[0m Step 313/1000 | Loss: 2.3662\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:32:41 INFO\u001b[0m Step 313/1000 | Loss: 2.4657\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:32:41 INFO\u001b[0m Step 313/1000 | Loss: 2.1112\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:32:41 INFO\u001b[0m Step 313/1000 | Loss: 1.9202\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:32:41 INFO\u001b[0m Step 313/1000 | Loss: 2.1893\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:32:41 INFO\u001b[0m Step 313/1000 | Loss: 2.2051\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:32:41 INFO\u001b[0m Step 313/1000 | Loss: 2.1873\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:32:41 INFO\u001b[0m Step 313/1000 | Loss: 2.1925\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:32:44 INFO\u001b[0m Step 314/1000 | Loss: 2.2833\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:32:44 INFO\u001b[0m Step 314/1000 | Loss: 2.1881\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:32:44 INFO\u001b[0m Step 314/1000 | Loss: 2.4306\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:32:44 INFO\u001b[0m Step 314/1000 | Loss: 1.8764\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:32:44 INFO\u001b[0m Step 314/1000 | Loss: 1.8434\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:32:44 INFO\u001b[0m Step 314/1000 | Loss: 2.2026\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:32:44 INFO\u001b[0m Step 314/1000 | Loss: 1.8876\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:32:44 INFO\u001b[0m Step 314/1000 | Loss: 1.8690\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:32:47 INFO\u001b[0m Step 315/1000 | Loss: 2.0656\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:32:47 INFO\u001b[0m Step 315/1000 | Loss: 2.1961\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:32:47 INFO\u001b[0m Step 315/1000 | Loss: 2.3102\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:32:47 INFO\u001b[0m Step 315/1000 | Loss: 1.9040\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:32:47 INFO\u001b[0m Step 315/1000 | Loss: 2.0735\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:32:47 INFO\u001b[0m Step 315/1000 | Loss: 1.9623\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:32:47 INFO\u001b[0m Step 315/1000 | Loss: 2.1697\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:32:48 INFO\u001b[0m Step 315/1000 | Loss: 2.1885\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:32:50 INFO\u001b[0m Step 316/1000 | Loss: 1.9546\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:32:50 INFO\u001b[0m Step 316/1000 | Loss: 2.8257\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:32:50 INFO\u001b[0m Step 316/1000 | Loss: 2.0896\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:32:50 INFO\u001b[0m Step 316/1000 | Loss: 1.8380\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:32:50 INFO\u001b[0m Step 316/1000 | Loss: 1.9911\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:32:50 INFO\u001b[0m Step 316/1000 | Loss: 2.1477\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:32:50 INFO\u001b[0m Step 316/1000 | Loss: 2.2749\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:32:50 INFO\u001b[0m Step 316/1000 | Loss: 1.9678\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:32:52 INFO\u001b[0m Step 317/1000 | Loss: 1.9855\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:32:52 INFO\u001b[0m Step 317/1000 | Loss: 1.7667\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:32:52 INFO\u001b[0m Step 317/1000 | Loss: 2.1495\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:32:52 INFO\u001b[0m Step 317/1000 | Loss: 1.8651\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:32:52 INFO\u001b[0m Step 317/1000 | Loss: 2.1526\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:32:52 INFO\u001b[0m Step 317/1000 | Loss: 2.1042\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:32:52 INFO\u001b[0m Step 317/1000 | Loss: 2.1814\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:32:52 INFO\u001b[0m Step 317/1000 | Loss: 2.2115\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:32:54 INFO\u001b[0m Step 318/1000 | Loss: 2.2410\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:32:54 INFO\u001b[0m Step 318/1000 | Loss: 1.9787\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:32:54 INFO\u001b[0m Step 318/1000 | Loss: 1.9869\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:32:54 INFO\u001b[0m Step 318/1000 | Loss: 2.2100\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:32:54 INFO\u001b[0m Step 318/1000 | Loss: 2.2745\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:32:54 INFO\u001b[0m Step 318/1000 | Loss: 2.0879\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:32:54 INFO\u001b[0m Step 318/1000 | Loss: 2.1477\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:32:54 INFO\u001b[0m Step 318/1000 | Loss: 2.0594\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:32:55 INFO\u001b[0m Step 319/1000 | Loss: 2.3461\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:32:55 INFO\u001b[0m Step 319/1000 | Loss: 2.2744\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:32:55 INFO\u001b[0m Step 319/1000 | Loss: 2.5023\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:32:55 INFO\u001b[0m Step 319/1000 | Loss: 2.6125\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:32:55 INFO\u001b[0m Step 319/1000 | Loss: 2.8002\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:32:55 INFO\u001b[0m Step 319/1000 | Loss: 2.1960\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:32:55 INFO\u001b[0m Step 319/1000 | Loss: 1.9825\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:32:55 INFO\u001b[0m Step 319/1000 | Loss: 2.5846\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:32:57 INFO\u001b[0m Step 320/1000 | Loss: 2.2128\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:32:57 INFO\u001b[0m Step 320/1000 | Loss: 2.4399\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:32:57 INFO\u001b[0m Step 320/1000 | Loss: 2.0664\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:32:57 INFO\u001b[0m Step 320/1000 | Loss: 2.3224\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:32:57 INFO\u001b[0m Step 320/1000 | Loss: 2.7713\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:32:57 INFO\u001b[0m Step 320/1000 | Loss: 2.6370\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:32:57 INFO\u001b[0m Step 320/1000 | Loss: 2.2738\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:32:57 INFO\u001b[0m Step 320/1000 | Loss: 2.1044\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:33:00 INFO\u001b[0m Step 321/1000 | Loss: 2.6135\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:33:00 INFO\u001b[0m Step 321/1000 | Loss: 1.8833\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:33:00 INFO\u001b[0m Step 321/1000 | Loss: 1.8914\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:33:00 INFO\u001b[0m Step 321/1000 | Loss: 2.5639\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:33:00 INFO\u001b[0m Step 321/1000 | Loss: 2.5284\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:33:00 INFO\u001b[0m Step 321/1000 | Loss: 2.0330\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:33:00 INFO\u001b[0m Step 321/1000 | Loss: 2.1265\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:33:00 INFO\u001b[0m Step 321/1000 | Loss: 2.3242\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:33:01 INFO\u001b[0m Step 322/1000 | Loss: 2.4366\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:33:01 INFO\u001b[0m Step 322/1000 | Loss: 2.7508\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:33:01 INFO\u001b[0m Step 322/1000 | Loss: 2.3834\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:33:01 INFO\u001b[0m Step 322/1000 | Loss: 3.3244\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:33:01 INFO\u001b[0m Step 322/1000 | Loss: 2.2695\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:33:01 INFO\u001b[0m Step 322/1000 | Loss: 2.5603\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:33:01 INFO\u001b[0m Step 322/1000 | Loss: 2.3188\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:33:01 INFO\u001b[0m Step 322/1000 | Loss: 2.4277\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:33:02 INFO\u001b[0m Step 323/1000 | Loss: 2.0900\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:33:02 INFO\u001b[0m Step 323/1000 | Loss: 2.3196\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:33:02 INFO\u001b[0m Step 323/1000 | Loss: 2.2686\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:33:02 INFO\u001b[0m Step 323/1000 | Loss: 2.6735\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:33:02 INFO\u001b[0m Step 323/1000 | Loss: 2.5090\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:33:02 INFO\u001b[0m Step 323/1000 | Loss: 2.3580\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:33:02 INFO\u001b[0m Step 323/1000 | Loss: 2.8831\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:33:02 INFO\u001b[0m Step 323/1000 | Loss: 2.5038\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:33:03 INFO\u001b[0m Step 324/1000 | Loss: 2.2609\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:33:03 INFO\u001b[0m Step 324/1000 | Loss: 2.5049\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:33:03 INFO\u001b[0m Step 324/1000 | Loss: 2.6495\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:33:03 INFO\u001b[0m Step 324/1000 | Loss: 3.9231\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:33:03 INFO\u001b[0m Step 324/1000 | Loss: 2.7575\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:33:03 INFO\u001b[0m Step 324/1000 | Loss: 2.4586\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:33:03 INFO\u001b[0m Step 324/1000 | Loss: 2.5921\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:33:03 INFO\u001b[0m Step 324/1000 | Loss: 2.2703\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:33:05 INFO\u001b[0m Step 325/1000 | Loss: 2.0671\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:33:05 INFO\u001b[0m Step 325/1000 | Loss: 1.9899\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:33:05 INFO\u001b[0m Step 325/1000 | Loss: 2.0736\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:33:05 INFO\u001b[0m Step 325/1000 | Loss: 3.2236\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:33:05 INFO\u001b[0m Step 325/1000 | Loss: 2.5208\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:33:05 INFO\u001b[0m Step 325/1000 | Loss: 2.2754\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:33:05 INFO\u001b[0m Step 325/1000 | Loss: 1.9610\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:33:05 INFO\u001b[0m Step 325/1000 | Loss: 2.2388\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:33:07 INFO\u001b[0m Step 326/1000 | Loss: 2.4965\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:33:07 INFO\u001b[0m Step 326/1000 | Loss: 2.3254\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:33:07 INFO\u001b[0m Step 326/1000 | Loss: 2.0740\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:33:07 INFO\u001b[0m Step 326/1000 | Loss: 2.9429\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:33:07 INFO\u001b[0m Step 326/1000 | Loss: 2.4765\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:33:07 INFO\u001b[0m Step 326/1000 | Loss: 2.3203\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:33:07 INFO\u001b[0m Step 326/1000 | Loss: 2.4338\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:33:07 INFO\u001b[0m Step 326/1000 | Loss: 2.6273\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:33:09 INFO\u001b[0m Step 327/1000 | Loss: 2.1506\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:33:09 INFO\u001b[0m Step 327/1000 | Loss: 2.3030\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:33:09 INFO\u001b[0m Step 327/1000 | Loss: 2.0934\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:33:09 INFO\u001b[0m Step 327/1000 | Loss: 2.3791\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:33:09 INFO\u001b[0m Step 327/1000 | Loss: 2.5569\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:33:09 INFO\u001b[0m Step 327/1000 | Loss: 2.1407\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:33:09 INFO\u001b[0m Step 327/1000 | Loss: 2.1391\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:33:09 INFO\u001b[0m Step 327/1000 | Loss: 2.1274\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:33:12 INFO\u001b[0m Step 328/1000 | Loss: 2.2632\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:33:12 INFO\u001b[0m Step 328/1000 | Loss: 1.8281\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:33:12 INFO\u001b[0m Step 328/1000 | Loss: 2.2258\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:33:12 INFO\u001b[0m Step 328/1000 | Loss: 2.1055\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:33:12 INFO\u001b[0m Step 328/1000 | Loss: 2.6303\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:33:12 INFO\u001b[0m Step 328/1000 | Loss: 2.5060\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:33:12 INFO\u001b[0m Step 328/1000 | Loss: 2.3535\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:33:12 INFO\u001b[0m Step 328/1000 | Loss: 2.5767\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:33:14 INFO\u001b[0m Step 329/1000 | Loss: 2.3055\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:33:14 INFO\u001b[0m Step 329/1000 | Loss: 2.3331\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:33:14 INFO\u001b[0m Step 329/1000 | Loss: 2.2635\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:33:14 INFO\u001b[0m Step 329/1000 | Loss: 2.1046\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:33:14 INFO\u001b[0m Step 329/1000 | Loss: 2.2611\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:33:14 INFO\u001b[0m Step 329/1000 | Loss: 2.2374\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:33:14 INFO\u001b[0m Step 329/1000 | Loss: 2.3651\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:33:14 INFO\u001b[0m Step 329/1000 | Loss: 2.1151\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:33:16 INFO\u001b[0m Step 330/1000 | Loss: 2.3148\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:33:16 INFO\u001b[0m Step 330/1000 | Loss: 2.0619\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:33:16 INFO\u001b[0m Step 330/1000 | Loss: 2.0461\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:33:16 INFO\u001b[0m Step 330/1000 | Loss: 2.2225\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:33:16 INFO\u001b[0m Step 330/1000 | Loss: 1.9612\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:33:16 INFO\u001b[0m Step 330/1000 | Loss: 2.1588\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:33:16 INFO\u001b[0m Step 330/1000 | Loss: 1.8873\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:33:16 INFO\u001b[0m Step 330/1000 | Loss: 2.1662\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:33:18 INFO\u001b[0m Step 331/1000 | Loss: 2.3764\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:33:18 INFO\u001b[0m Step 331/1000 | Loss: 2.1511\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:33:18 INFO\u001b[0m Step 331/1000 | Loss: 2.1263\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:33:18 INFO\u001b[0m Step 331/1000 | Loss: 2.1141\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:33:18 INFO\u001b[0m Step 331/1000 | Loss: 2.2967\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:33:18 INFO\u001b[0m Step 331/1000 | Loss: 2.0966\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:33:18 INFO\u001b[0m Step 331/1000 | Loss: 1.7665\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:33:18 INFO\u001b[0m Step 331/1000 | Loss: 2.6140\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:33:19 INFO\u001b[0m Step 332/1000 | Loss: 2.1269\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:33:19 INFO\u001b[0m Step 332/1000 | Loss: 2.2074\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:33:19 INFO\u001b[0m Step 332/1000 | Loss: 2.3373\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:33:19 INFO\u001b[0m Step 332/1000 | Loss: 2.2373\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:33:19 INFO\u001b[0m Step 332/1000 | Loss: 2.0179\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:33:19 INFO\u001b[0m Step 332/1000 | Loss: 1.7688\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:33:19 INFO\u001b[0m Step 332/1000 | Loss: 2.1287\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:33:19 INFO\u001b[0m Step 332/1000 | Loss: 2.4460\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:33:22 INFO\u001b[0m Step 333/1000 | Loss: 2.0162\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:33:22 INFO\u001b[0m Step 333/1000 | Loss: 1.5763\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:33:22 INFO\u001b[0m Step 333/1000 | Loss: 1.9974\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:33:22 INFO\u001b[0m Step 333/1000 | Loss: 1.8921\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:33:22 INFO\u001b[0m Step 333/1000 | Loss: 2.1027\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:33:22 INFO\u001b[0m Step 333/1000 | Loss: 1.9112\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:33:22 INFO\u001b[0m Step 333/1000 | Loss: 2.1575\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:33:22 INFO\u001b[0m Step 333/1000 | Loss: 2.2365\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:33:24 INFO\u001b[0m Step 334/1000 | Loss: 2.4885\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:33:24 INFO\u001b[0m Step 334/1000 | Loss: 2.3144\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:33:24 INFO\u001b[0m Step 334/1000 | Loss: 1.9747\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:33:24 INFO\u001b[0m Step 334/1000 | Loss: 2.1549\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:33:24 INFO\u001b[0m Step 334/1000 | Loss: 1.7499\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:33:24 INFO\u001b[0m Step 334/1000 | Loss: 2.1410\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:33:24 INFO\u001b[0m Step 334/1000 | Loss: 2.2136\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:33:24 INFO\u001b[0m Step 334/1000 | Loss: 2.1127\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:33:26 INFO\u001b[0m Step 335/1000 | Loss: 1.9305\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:33:26 INFO\u001b[0m Step 335/1000 | Loss: 2.2900\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:33:26 INFO\u001b[0m Step 335/1000 | Loss: 2.0471\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:33:26 INFO\u001b[0m Step 335/1000 | Loss: 2.4137\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:33:26 INFO\u001b[0m Step 335/1000 | Loss: 1.7994\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:33:26 INFO\u001b[0m Step 335/1000 | Loss: 2.4358\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:33:26 INFO\u001b[0m Step 335/1000 | Loss: 2.0937\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:33:26 INFO\u001b[0m Step 335/1000 | Loss: 2.1434\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:33:27 INFO\u001b[0m Step 336/1000 | Loss: 1.8901\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:33:27 INFO\u001b[0m Step 336/1000 | Loss: 1.9309\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:33:27 INFO\u001b[0m Step 336/1000 | Loss: 1.8927\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:33:27 INFO\u001b[0m Step 336/1000 | Loss: 1.9740\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:33:27 INFO\u001b[0m Step 336/1000 | Loss: 2.3721\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:33:27 INFO\u001b[0m Step 336/1000 | Loss: 2.1055\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:33:27 INFO\u001b[0m Step 336/1000 | Loss: 1.6661\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:33:27 INFO\u001b[0m Step 336/1000 | Loss: 2.1097\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:33:28 INFO\u001b[0m Step 337/1000 | Loss: 1.9725\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:33:28 INFO\u001b[0m Step 337/1000 | Loss: 2.4716\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:33:28 INFO\u001b[0m Step 337/1000 | Loss: 2.2391\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:33:28 INFO\u001b[0m Step 337/1000 | Loss: 1.9892\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:33:28 INFO\u001b[0m Step 337/1000 | Loss: 2.0023\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:33:28 INFO\u001b[0m Step 337/1000 | Loss: 2.0798\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:33:28 INFO\u001b[0m Step 337/1000 | Loss: 2.4534\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:33:28 INFO\u001b[0m Step 337/1000 | Loss: 2.3341\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:33:29 INFO\u001b[0m Step 338/1000 | Loss: 2.2924\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:33:29 INFO\u001b[0m Step 338/1000 | Loss: 1.7301\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:33:29 INFO\u001b[0m Step 338/1000 | Loss: 2.3616\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:33:29 INFO\u001b[0m Step 338/1000 | Loss: 1.9975\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:33:29 INFO\u001b[0m Step 338/1000 | Loss: 2.2714\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:33:29 INFO\u001b[0m Step 338/1000 | Loss: 1.7712\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:33:29 INFO\u001b[0m Step 338/1000 | Loss: 1.9277\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:33:29 INFO\u001b[0m Step 338/1000 | Loss: 2.1403\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:33:31 INFO\u001b[0m Step 339/1000 | Loss: 2.0130\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:33:31 INFO\u001b[0m Step 339/1000 | Loss: 2.0715\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:33:31 INFO\u001b[0m Step 339/1000 | Loss: 2.0087\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:33:31 INFO\u001b[0m Step 339/1000 | Loss: 2.1724\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:33:31 INFO\u001b[0m Step 339/1000 | Loss: 2.0952\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:33:31 INFO\u001b[0m Step 339/1000 | Loss: 2.5445\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:33:31 INFO\u001b[0m Step 339/1000 | Loss: 2.4629\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:33:31 INFO\u001b[0m Step 339/1000 | Loss: 2.0508\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:33:34 INFO\u001b[0m Step 340/1000 | Loss: 2.2342\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:33:34 INFO\u001b[0m Step 340/1000 | Loss: 1.9923\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:33:34 INFO\u001b[0m Step 340/1000 | Loss: 2.5947\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:33:34 INFO\u001b[0m Step 340/1000 | Loss: 2.1077\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:33:34 INFO\u001b[0m Step 340/1000 | Loss: 2.2475\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:33:34 INFO\u001b[0m Step 340/1000 | Loss: 2.2188\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:33:34 INFO\u001b[0m Step 340/1000 | Loss: 1.7736\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:33:34 INFO\u001b[0m Step 340/1000 | Loss: 2.6961\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:33:38 INFO\u001b[0m Step 341/1000 | Loss: 1.9011\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:33:38 INFO\u001b[0m Step 341/1000 | Loss: 2.3647\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:33:38 INFO\u001b[0m Step 341/1000 | Loss: 2.3817\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:33:38 INFO\u001b[0m Step 341/1000 | Loss: 2.0007\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:33:38 INFO\u001b[0m Step 341/1000 | Loss: 2.4221\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:33:38 INFO\u001b[0m Step 341/1000 | Loss: 2.2857\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:33:38 INFO\u001b[0m Step 341/1000 | Loss: 1.9814\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:33:38 INFO\u001b[0m Step 341/1000 | Loss: 2.0933\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:33:42 INFO\u001b[0m Step 342/1000 | Loss: 1.6965\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:33:42 INFO\u001b[0m Step 342/1000 | Loss: 2.4065\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:33:42 INFO\u001b[0m Step 342/1000 | Loss: 2.0850\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:33:42 INFO\u001b[0m Step 342/1000 | Loss: 2.1828\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:33:42 INFO\u001b[0m Step 342/1000 | Loss: 2.1903\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:33:42 INFO\u001b[0m Step 342/1000 | Loss: 1.7753\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:33:42 INFO\u001b[0m Step 342/1000 | Loss: 2.1327\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:33:42 INFO\u001b[0m Step 342/1000 | Loss: 2.1970\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:33:43 INFO\u001b[0m Step 343/1000 | Loss: 2.4557\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:33:43 INFO\u001b[0m Step 343/1000 | Loss: 2.2379\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:33:43 INFO\u001b[0m Step 343/1000 | Loss: 2.1948\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:33:43 INFO\u001b[0m Step 343/1000 | Loss: 2.0714\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:33:43 INFO\u001b[0m Step 343/1000 | Loss: 2.1317\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:33:43 INFO\u001b[0m Step 343/1000 | Loss: 2.4908\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:33:43 INFO\u001b[0m Step 343/1000 | Loss: 2.1049\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:33:43 INFO\u001b[0m Step 343/1000 | Loss: 2.0156\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:33:44 INFO\u001b[0m Step 344/1000 | Loss: 2.2633\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:33:44 INFO\u001b[0m Step 344/1000 | Loss: 1.8335\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:33:44 INFO\u001b[0m Step 344/1000 | Loss: 1.8276\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:33:44 INFO\u001b[0m Step 344/1000 | Loss: 2.4570\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:33:44 INFO\u001b[0m Step 344/1000 | Loss: 2.9022\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:33:44 INFO\u001b[0m Step 344/1000 | Loss: 2.0755\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:33:44 INFO\u001b[0m Step 344/1000 | Loss: 2.0498\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:33:44 INFO\u001b[0m Step 344/1000 | Loss: 2.4457\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:33:46 INFO\u001b[0m Step 345/1000 | Loss: 2.6008\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:33:46 INFO\u001b[0m Step 345/1000 | Loss: 1.9902\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:33:46 INFO\u001b[0m Step 345/1000 | Loss: 2.2732\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:33:46 INFO\u001b[0m Step 345/1000 | Loss: 2.1438\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:33:46 INFO\u001b[0m Step 345/1000 | Loss: 2.0645\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:33:46 INFO\u001b[0m Step 345/1000 | Loss: 2.2605\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:33:46 INFO\u001b[0m Step 345/1000 | Loss: 1.9291\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:33:46 INFO\u001b[0m Step 345/1000 | Loss: 2.2987\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:33:48 INFO\u001b[0m Step 346/1000 | Loss: 2.0215\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:33:48 INFO\u001b[0m Step 346/1000 | Loss: 1.9740\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:33:48 INFO\u001b[0m Step 346/1000 | Loss: 2.1690\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:33:48 INFO\u001b[0m Step 346/1000 | Loss: 2.1631\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:33:48 INFO\u001b[0m Step 346/1000 | Loss: 2.0608\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:33:48 INFO\u001b[0m Step 346/1000 | Loss: 1.7350\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:33:48 INFO\u001b[0m Step 346/1000 | Loss: 2.2397\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:33:48 INFO\u001b[0m Step 346/1000 | Loss: 2.0753\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:33:49 INFO\u001b[0m Step 347/1000 | Loss: 2.5639\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:33:49 INFO\u001b[0m Step 347/1000 | Loss: 2.3158\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:33:49 INFO\u001b[0m Step 347/1000 | Loss: 2.0413\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:33:49 INFO\u001b[0m Step 347/1000 | Loss: 2.6459\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:33:49 INFO\u001b[0m Step 347/1000 | Loss: 2.4008\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:33:49 INFO\u001b[0m Step 347/1000 | Loss: 1.8235\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:33:49 INFO\u001b[0m Step 347/1000 | Loss: 2.2010\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:33:49 INFO\u001b[0m Step 347/1000 | Loss: 2.1405\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:33:51 INFO\u001b[0m Step 348/1000 | Loss: 2.3908\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:33:51 INFO\u001b[0m Step 348/1000 | Loss: 2.1725\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:33:51 INFO\u001b[0m Step 348/1000 | Loss: 1.9736\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:33:51 INFO\u001b[0m Step 348/1000 | Loss: 1.9735\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:33:51 INFO\u001b[0m Step 348/1000 | Loss: 2.1687\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:33:51 INFO\u001b[0m Step 348/1000 | Loss: 2.1077\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:33:51 INFO\u001b[0m Step 348/1000 | Loss: 2.3116\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:33:51 INFO\u001b[0m Step 348/1000 | Loss: 1.8867\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:33:53 INFO\u001b[0m Step 349/1000 | Loss: 2.0665\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:33:53 INFO\u001b[0m Step 349/1000 | Loss: 2.1340\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:33:53 INFO\u001b[0m Step 349/1000 | Loss: 2.4116\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:33:53 INFO\u001b[0m Step 349/1000 | Loss: 1.9241\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:33:53 INFO\u001b[0m Step 349/1000 | Loss: 2.4035\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:33:53 INFO\u001b[0m Step 349/1000 | Loss: 2.2484\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:33:53 INFO\u001b[0m Step 349/1000 | Loss: 1.9206\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:33:53 INFO\u001b[0m Step 349/1000 | Loss: 2.2636\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:33:55 INFO\u001b[0m Step 350/1000 | Loss: 2.2777\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:33:55 INFO\u001b[0m Step 350/1000 | Loss: 2.1083\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:33:55 INFO\u001b[0m Step 350/1000 | Loss: 2.3292\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:33:55 INFO\u001b[0m Step 350/1000 | Loss: 2.7523\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:33:55 INFO\u001b[0m Step 350/1000 | Loss: 1.8731\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:33:55 INFO\u001b[0m Step 350/1000 | Loss: 2.0048\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:33:55 INFO\u001b[0m Step 350/1000 | Loss: 2.2846\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:33:55 INFO\u001b[0m Step 350/1000 | Loss: 2.2647\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:33:56 INFO\u001b[0m Step 351/1000 | Loss: 2.0406\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:33:56 INFO\u001b[0m Step 351/1000 | Loss: 1.8936\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:33:56 INFO\u001b[0m Step 351/1000 | Loss: 1.9340\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:33:56 INFO\u001b[0m Step 351/1000 | Loss: 2.1012\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:33:56 INFO\u001b[0m Step 351/1000 | Loss: 2.2467\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:33:56 INFO\u001b[0m Step 351/1000 | Loss: 2.0923\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:33:56 INFO\u001b[0m Step 351/1000 | Loss: 2.1826\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:33:56 INFO\u001b[0m Step 351/1000 | Loss: 2.0772\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:33:59 INFO\u001b[0m Step 352/1000 | Loss: 1.9365\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:33:59 INFO\u001b[0m Step 352/1000 | Loss: 2.0384\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:33:59 INFO\u001b[0m Step 352/1000 | Loss: 2.0739\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:33:59 INFO\u001b[0m Step 352/1000 | Loss: 2.3794\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:33:59 INFO\u001b[0m Step 352/1000 | Loss: 2.1839\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:33:59 INFO\u001b[0m Step 352/1000 | Loss: 2.0057\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:33:59 INFO\u001b[0m Step 352/1000 | Loss: 1.7831\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:33:59 INFO\u001b[0m Step 352/1000 | Loss: 2.0548\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:34:01 INFO\u001b[0m Step 353/1000 | Loss: 2.4956\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:34:01 INFO\u001b[0m Step 353/1000 | Loss: 1.8509\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:34:01 INFO\u001b[0m Step 353/1000 | Loss: 2.4551\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:34:01 INFO\u001b[0m Step 353/1000 | Loss: 1.9091\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:34:01 INFO\u001b[0m Step 353/1000 | Loss: 2.0407\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:34:01 INFO\u001b[0m Step 353/1000 | Loss: 2.4226\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:34:01 INFO\u001b[0m Step 353/1000 | Loss: 2.1632\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:34:01 INFO\u001b[0m Step 353/1000 | Loss: 1.8837\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:34:04 INFO\u001b[0m Step 354/1000 | Loss: 2.2138\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:34:04 INFO\u001b[0m Step 354/1000 | Loss: 1.7130\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:34:04 INFO\u001b[0m Step 354/1000 | Loss: 2.3823\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:34:04 INFO\u001b[0m Step 354/1000 | Loss: 2.1287\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:34:04 INFO\u001b[0m Step 354/1000 | Loss: 2.1179\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:34:04 INFO\u001b[0m Step 354/1000 | Loss: 1.7939\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:34:04 INFO\u001b[0m Step 354/1000 | Loss: 2.3004\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:34:04 INFO\u001b[0m Step 354/1000 | Loss: 2.0836\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:34:06 INFO\u001b[0m Step 355/1000 | Loss: 1.9750\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:34:06 INFO\u001b[0m Step 355/1000 | Loss: 1.8779\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:34:06 INFO\u001b[0m Step 355/1000 | Loss: 1.9420\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:34:06 INFO\u001b[0m Step 355/1000 | Loss: 2.5286\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:34:06 INFO\u001b[0m Step 355/1000 | Loss: 2.1564\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:34:06 INFO\u001b[0m Step 355/1000 | Loss: 2.3363\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:34:06 INFO\u001b[0m Step 355/1000 | Loss: 2.0006\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:34:06 INFO\u001b[0m Step 355/1000 | Loss: 2.0538\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:34:09 INFO\u001b[0m Step 356/1000 | Loss: 2.0827\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:34:09 INFO\u001b[0m Step 356/1000 | Loss: 1.9662\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:34:09 INFO\u001b[0m Step 356/1000 | Loss: 2.5108\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:34:09 INFO\u001b[0m Step 356/1000 | Loss: 2.0477\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:34:09 INFO\u001b[0m Step 356/1000 | Loss: 2.0485\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:34:09 INFO\u001b[0m Step 356/1000 | Loss: 2.3684\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:34:09 INFO\u001b[0m Step 356/1000 | Loss: 2.7819\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:34:09 INFO\u001b[0m Step 356/1000 | Loss: 2.2047\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:34:11 INFO\u001b[0m Step 357/1000 | Loss: 1.8960\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:34:11 INFO\u001b[0m Step 357/1000 | Loss: 1.9925\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:34:11 INFO\u001b[0m Step 357/1000 | Loss: 2.1498\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:34:11 INFO\u001b[0m Step 357/1000 | Loss: 1.7001\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:34:11 INFO\u001b[0m Step 357/1000 | Loss: 1.8819\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:34:11 INFO\u001b[0m Step 357/1000 | Loss: 1.9294\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:34:11 INFO\u001b[0m Step 357/1000 | Loss: 2.9030\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:34:11 INFO\u001b[0m Step 357/1000 | Loss: 1.9056\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:34:13 INFO\u001b[0m Step 358/1000 | Loss: 2.0782\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:34:13 INFO\u001b[0m Step 358/1000 | Loss: 1.9541\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:34:13 INFO\u001b[0m Step 358/1000 | Loss: 2.3971\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:34:13 INFO\u001b[0m Step 358/1000 | Loss: 2.2389\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:34:13 INFO\u001b[0m Step 358/1000 | Loss: 2.1023\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:34:13 INFO\u001b[0m Step 358/1000 | Loss: 2.4953\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:34:13 INFO\u001b[0m Step 358/1000 | Loss: 2.6612\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:34:13 INFO\u001b[0m Step 358/1000 | Loss: 2.0812\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:34:15 INFO\u001b[0m Step 359/1000 | Loss: 1.8386\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:34:15 INFO\u001b[0m Step 359/1000 | Loss: 1.8205\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:34:15 INFO\u001b[0m Step 359/1000 | Loss: 2.5002\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:34:15 INFO\u001b[0m Step 359/1000 | Loss: 1.9981\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:34:15 INFO\u001b[0m Step 359/1000 | Loss: 1.9964\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:34:15 INFO\u001b[0m Step 359/1000 | Loss: 2.2679\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:34:15 INFO\u001b[0m Step 359/1000 | Loss: 1.7984\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:34:15 INFO\u001b[0m Step 359/1000 | Loss: 1.9957\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:34:18 INFO\u001b[0m Step 360/1000 | Loss: 2.2539\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:34:18 INFO\u001b[0m Step 360/1000 | Loss: 2.0218\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:34:18 INFO\u001b[0m Step 360/1000 | Loss: 2.3776\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:34:18 INFO\u001b[0m Step 360/1000 | Loss: 2.0469\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:34:18 INFO\u001b[0m Step 360/1000 | Loss: 1.8668\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:34:18 INFO\u001b[0m Step 360/1000 | Loss: 2.0835\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:34:18 INFO\u001b[0m Step 360/1000 | Loss: 2.1985\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:34:18 INFO\u001b[0m Step 360/1000 | Loss: 2.1303\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:34:22 INFO\u001b[0m Step 361/1000 | Loss: 2.2756\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:34:22 INFO\u001b[0m Step 361/1000 | Loss: 2.0239\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:34:22 INFO\u001b[0m Step 361/1000 | Loss: 2.0531\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:34:22 INFO\u001b[0m Step 361/1000 | Loss: 1.9797\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:34:22 INFO\u001b[0m Step 361/1000 | Loss: 2.0580\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:34:22 INFO\u001b[0m Step 361/1000 | Loss: 2.2243\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:34:22 INFO\u001b[0m Step 361/1000 | Loss: 1.9205\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:34:22 INFO\u001b[0m Step 361/1000 | Loss: 1.9808\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:34:24 INFO\u001b[0m Step 362/1000 | Loss: 2.2768\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:34:24 INFO\u001b[0m Step 362/1000 | Loss: 1.9566\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:34:24 INFO\u001b[0m Step 362/1000 | Loss: 2.3848\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:34:24 INFO\u001b[0m Step 362/1000 | Loss: 1.5662\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:34:24 INFO\u001b[0m Step 362/1000 | Loss: 1.8710\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:34:24 INFO\u001b[0m Step 362/1000 | Loss: 1.9082\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:34:24 INFO\u001b[0m Step 362/1000 | Loss: 1.9415\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:34:24 INFO\u001b[0m Step 362/1000 | Loss: 2.5338\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:34:26 INFO\u001b[0m Step 363/1000 | Loss: 2.1375\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:34:26 INFO\u001b[0m Step 363/1000 | Loss: 1.9972\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:34:26 INFO\u001b[0m Step 363/1000 | Loss: 2.0616\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:34:26 INFO\u001b[0m Step 363/1000 | Loss: 1.8747\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:34:26 INFO\u001b[0m Step 363/1000 | Loss: 1.7293\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:34:26 INFO\u001b[0m Step 363/1000 | Loss: 2.0710\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:34:26 INFO\u001b[0m Step 363/1000 | Loss: 1.8333\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:34:26 INFO\u001b[0m Step 363/1000 | Loss: 2.2226\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:34:27 INFO\u001b[0m Step 364/1000 | Loss: 2.0104\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:34:27 INFO\u001b[0m Step 364/1000 | Loss: 2.0681\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:34:27 INFO\u001b[0m Step 364/1000 | Loss: 2.1991\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:34:27 INFO\u001b[0m Step 364/1000 | Loss: 2.1746\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:34:27 INFO\u001b[0m Step 364/1000 | Loss: 2.1085\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:34:27 INFO\u001b[0m Step 364/1000 | Loss: 2.1209\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:34:27 INFO\u001b[0m Step 364/1000 | Loss: 1.9531\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:34:27 INFO\u001b[0m Step 364/1000 | Loss: 2.1879\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:34:30 INFO\u001b[0m Step 365/1000 | Loss: 2.0138\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:34:30 INFO\u001b[0m Step 365/1000 | Loss: 2.0097\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:34:30 INFO\u001b[0m Step 365/1000 | Loss: 2.0265\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:34:30 INFO\u001b[0m Step 365/1000 | Loss: 1.8067\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:34:30 INFO\u001b[0m Step 365/1000 | Loss: 1.9988\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:34:30 INFO\u001b[0m Step 365/1000 | Loss: 2.2955\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:34:30 INFO\u001b[0m Step 365/1000 | Loss: 2.3117\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:34:30 INFO\u001b[0m Step 365/1000 | Loss: 2.0727\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:34:32 INFO\u001b[0m Step 366/1000 | Loss: 2.2779\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:34:32 INFO\u001b[0m Step 366/1000 | Loss: 2.3440\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:34:32 INFO\u001b[0m Step 366/1000 | Loss: 1.9310\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:34:32 INFO\u001b[0m Step 366/1000 | Loss: 1.8656\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:34:32 INFO\u001b[0m Step 366/1000 | Loss: 1.9121\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:34:32 INFO\u001b[0m Step 366/1000 | Loss: 2.0312\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:34:32 INFO\u001b[0m Step 366/1000 | Loss: 2.4211\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:34:32 INFO\u001b[0m Step 366/1000 | Loss: 2.3807\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:34:35 INFO\u001b[0m Step 367/1000 | Loss: 2.0203\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:34:35 INFO\u001b[0m Step 367/1000 | Loss: 2.4040\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:34:35 INFO\u001b[0m Step 367/1000 | Loss: 2.0749\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:34:35 INFO\u001b[0m Step 367/1000 | Loss: 2.0693\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:34:35 INFO\u001b[0m Step 367/1000 | Loss: 2.1407\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:34:35 INFO\u001b[0m Step 367/1000 | Loss: 2.2041\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:34:35 INFO\u001b[0m Step 367/1000 | Loss: 1.8269\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:34:35 INFO\u001b[0m Step 367/1000 | Loss: 2.5249\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:34:38 INFO\u001b[0m Step 368/1000 | Loss: 1.5276\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:34:38 INFO\u001b[0m Step 368/1000 | Loss: 2.6710\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:34:38 INFO\u001b[0m Step 368/1000 | Loss: 2.2086\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:34:38 INFO\u001b[0m Step 368/1000 | Loss: 2.5624\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:34:38 INFO\u001b[0m Step 368/1000 | Loss: 2.3408\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:34:38 INFO\u001b[0m Step 368/1000 | Loss: 2.1195\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:34:38 INFO\u001b[0m Step 368/1000 | Loss: 2.0751\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:34:38 INFO\u001b[0m Step 368/1000 | Loss: 2.1886\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:34:40 INFO\u001b[0m Step 369/1000 | Loss: 2.5896\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:34:40 INFO\u001b[0m Step 369/1000 | Loss: 2.4495\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:34:40 INFO\u001b[0m Step 369/1000 | Loss: 1.9346\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:34:40 INFO\u001b[0m Step 369/1000 | Loss: 2.0753\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:34:40 INFO\u001b[0m Step 369/1000 | Loss: 1.9150\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:34:40 INFO\u001b[0m Step 369/1000 | Loss: 2.4919\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:34:40 INFO\u001b[0m Step 369/1000 | Loss: 2.5341\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:34:40 INFO\u001b[0m Step 369/1000 | Loss: 2.4307\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:34:42 INFO\u001b[0m Step 370/1000 | Loss: 2.3291\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:34:42 INFO\u001b[0m Step 370/1000 | Loss: 2.4300\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:34:42 INFO\u001b[0m Step 370/1000 | Loss: 1.7626\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:34:42 INFO\u001b[0m Step 370/1000 | Loss: 2.2079\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:34:42 INFO\u001b[0m Step 370/1000 | Loss: 2.0837\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:34:42 INFO\u001b[0m Step 370/1000 | Loss: 2.4128\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:34:42 INFO\u001b[0m Step 370/1000 | Loss: 2.2693\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:34:42 INFO\u001b[0m Step 370/1000 | Loss: 2.1146\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:34:45 INFO\u001b[0m Step 371/1000 | Loss: 2.1472\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:34:45 INFO\u001b[0m Step 371/1000 | Loss: 2.5250\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:34:45 INFO\u001b[0m Step 371/1000 | Loss: 2.3623\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:34:45 INFO\u001b[0m Step 371/1000 | Loss: 2.0684\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:34:45 INFO\u001b[0m Step 371/1000 | Loss: 2.1797\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:34:45 INFO\u001b[0m Step 371/1000 | Loss: 2.4302\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:34:45 INFO\u001b[0m Step 371/1000 | Loss: 2.2976\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:34:45 INFO\u001b[0m Step 371/1000 | Loss: 2.6405\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:34:47 INFO\u001b[0m Step 372/1000 | Loss: 2.0882\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:34:47 INFO\u001b[0m Step 372/1000 | Loss: 2.3161\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:34:47 INFO\u001b[0m Step 372/1000 | Loss: 2.7388\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:34:47 INFO\u001b[0m Step 372/1000 | Loss: 2.4080\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:34:47 INFO\u001b[0m Step 372/1000 | Loss: 1.8744\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:34:47 INFO\u001b[0m Step 372/1000 | Loss: 2.3645\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:34:47 INFO\u001b[0m Step 372/1000 | Loss: 2.3064\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:34:47 INFO\u001b[0m Step 372/1000 | Loss: 2.1595\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:34:50 INFO\u001b[0m Step 373/1000 | Loss: 2.5573\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:34:50 INFO\u001b[0m Step 373/1000 | Loss: 2.2411\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:34:50 INFO\u001b[0m Step 373/1000 | Loss: 2.2146\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:34:50 INFO\u001b[0m Step 373/1000 | Loss: 2.4880\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:34:50 INFO\u001b[0m Step 373/1000 | Loss: 2.3836\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:34:50 INFO\u001b[0m Step 373/1000 | Loss: 2.0308\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:34:50 INFO\u001b[0m Step 373/1000 | Loss: 2.5538\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:34:50 INFO\u001b[0m Step 373/1000 | Loss: 2.2593\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:34:52 INFO\u001b[0m Step 374/1000 | Loss: 2.7460\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:34:52 INFO\u001b[0m Step 374/1000 | Loss: 2.1391\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:34:52 INFO\u001b[0m Step 374/1000 | Loss: 2.1243\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:34:52 INFO\u001b[0m Step 374/1000 | Loss: 2.1313\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:34:52 INFO\u001b[0m Step 374/1000 | Loss: 2.3195\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:34:52 INFO\u001b[0m Step 374/1000 | Loss: 2.0382\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:34:52 INFO\u001b[0m Step 374/1000 | Loss: 2.1233\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:34:52 INFO\u001b[0m Step 374/1000 | Loss: 1.9438\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:34:54 INFO\u001b[0m Step 375/1000 | Loss: 2.2163\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:34:54 INFO\u001b[0m Step 375/1000 | Loss: 2.1592\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:34:54 INFO\u001b[0m Step 375/1000 | Loss: 2.1381\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:34:54 INFO\u001b[0m Step 375/1000 | Loss: 2.5624\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:34:54 INFO\u001b[0m Step 375/1000 | Loss: 2.2573\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:34:54 INFO\u001b[0m Step 375/1000 | Loss: 1.9706\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:34:54 INFO\u001b[0m Step 375/1000 | Loss: 2.5132\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:34:54 INFO\u001b[0m Step 375/1000 | Loss: 2.2948\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:34:56 INFO\u001b[0m Step 376/1000 | Loss: 2.2935\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:34:56 INFO\u001b[0m Step 376/1000 | Loss: 2.9934\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:34:56 INFO\u001b[0m Step 376/1000 | Loss: 2.4008\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:34:56 INFO\u001b[0m Step 376/1000 | Loss: 2.9307\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:34:56 INFO\u001b[0m Step 376/1000 | Loss: 2.3917\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:34:56 INFO\u001b[0m Step 376/1000 | Loss: 2.1063\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:34:56 INFO\u001b[0m Step 376/1000 | Loss: 2.2782\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:34:56 INFO\u001b[0m Step 376/1000 | Loss: 2.2684\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:35:00 INFO\u001b[0m Step 377/1000 | Loss: 2.4833\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:35:00 INFO\u001b[0m Step 377/1000 | Loss: 2.3762\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:35:00 INFO\u001b[0m Step 377/1000 | Loss: 2.0004\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:35:00 INFO\u001b[0m Step 377/1000 | Loss: 2.2849\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:35:00 INFO\u001b[0m Step 377/1000 | Loss: 2.2343\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:35:00 INFO\u001b[0m Step 377/1000 | Loss: 2.1251\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:35:00 INFO\u001b[0m Step 377/1000 | Loss: 2.4160\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:35:00 INFO\u001b[0m Step 377/1000 | Loss: 2.4201\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:35:03 INFO\u001b[0m Step 378/1000 | Loss: 2.9019\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:35:03 INFO\u001b[0m Step 378/1000 | Loss: 2.2508\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:35:03 INFO\u001b[0m Step 378/1000 | Loss: 2.1184\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:35:03 INFO\u001b[0m Step 378/1000 | Loss: 2.0846\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:35:03 INFO\u001b[0m Step 378/1000 | Loss: 2.3203\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:35:03 INFO\u001b[0m Step 378/1000 | Loss: 2.1795\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:35:03 INFO\u001b[0m Step 378/1000 | Loss: 1.9874\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:35:03 INFO\u001b[0m Step 378/1000 | Loss: 2.3073\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:35:04 INFO\u001b[0m Step 379/1000 | Loss: 2.5697\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:35:04 INFO\u001b[0m Step 379/1000 | Loss: 1.9936\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:35:04 INFO\u001b[0m Step 379/1000 | Loss: 2.5352\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:35:04 INFO\u001b[0m Step 379/1000 | Loss: 2.9954\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:35:04 INFO\u001b[0m Step 379/1000 | Loss: 2.6259\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:35:04 INFO\u001b[0m Step 379/1000 | Loss: 2.5817\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:35:04 INFO\u001b[0m Step 379/1000 | Loss: 2.2198\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:35:04 INFO\u001b[0m Step 379/1000 | Loss: 2.1462\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:35:05 INFO\u001b[0m Step 380/1000 | Loss: 2.3918\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:35:05 INFO\u001b[0m Step 380/1000 | Loss: 2.2839\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:35:05 INFO\u001b[0m Step 380/1000 | Loss: 2.3731\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:35:05 INFO\u001b[0m Step 380/1000 | Loss: 3.1182\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:35:05 INFO\u001b[0m Step 380/1000 | Loss: 2.4428\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:35:05 INFO\u001b[0m Step 380/1000 | Loss: 2.0971\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:35:05 INFO\u001b[0m Step 380/1000 | Loss: 2.5485\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:35:05 INFO\u001b[0m Step 380/1000 | Loss: 2.5218\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:35:08 INFO\u001b[0m Step 381/1000 | Loss: 3.0164\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:35:08 INFO\u001b[0m Step 381/1000 | Loss: 2.7571\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:35:08 INFO\u001b[0m Step 381/1000 | Loss: 2.5822\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:35:08 INFO\u001b[0m Step 381/1000 | Loss: 2.6146\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:35:08 INFO\u001b[0m Step 381/1000 | Loss: 2.7037\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:35:08 INFO\u001b[0m Step 381/1000 | Loss: 2.5377\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:35:08 INFO\u001b[0m Step 381/1000 | Loss: 2.7202\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:35:08 INFO\u001b[0m Step 381/1000 | Loss: 2.5144\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:35:09 INFO\u001b[0m Step 382/1000 | Loss: 2.6359\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:35:09 INFO\u001b[0m Step 382/1000 | Loss: 2.1831\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:35:09 INFO\u001b[0m Step 382/1000 | Loss: 1.8416\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:35:09 INFO\u001b[0m Step 382/1000 | Loss: 2.2178\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:35:09 INFO\u001b[0m Step 382/1000 | Loss: 2.3802\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:35:09 INFO\u001b[0m Step 382/1000 | Loss: 3.1502\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:35:09 INFO\u001b[0m Step 382/1000 | Loss: 2.4747\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:35:09 INFO\u001b[0m Step 382/1000 | Loss: 2.6750\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:35:11 INFO\u001b[0m Step 383/1000 | Loss: 2.7028\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:35:11 INFO\u001b[0m Step 383/1000 | Loss: 2.4079\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:35:11 INFO\u001b[0m Step 383/1000 | Loss: 2.1483\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:35:11 INFO\u001b[0m Step 383/1000 | Loss: 2.7565\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:35:11 INFO\u001b[0m Step 383/1000 | Loss: 2.9580\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:35:11 INFO\u001b[0m Step 383/1000 | Loss: 2.6823\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:35:11 INFO\u001b[0m Step 383/1000 | Loss: 2.2304\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:35:11 INFO\u001b[0m Step 383/1000 | Loss: 2.5405\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:35:13 INFO\u001b[0m Step 384/1000 | Loss: 2.2049\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:35:13 INFO\u001b[0m Step 384/1000 | Loss: 2.1229\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:35:13 INFO\u001b[0m Step 384/1000 | Loss: 1.9657\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:35:13 INFO\u001b[0m Step 384/1000 | Loss: 2.8008\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:35:13 INFO\u001b[0m Step 384/1000 | Loss: 2.9824\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:35:13 INFO\u001b[0m Step 384/1000 | Loss: 2.9538\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:35:13 INFO\u001b[0m Step 384/1000 | Loss: 3.2155\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:35:13 INFO\u001b[0m Step 384/1000 | Loss: 2.9936\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:35:14 INFO\u001b[0m Step 385/1000 | Loss: 1.9202\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:35:14 INFO\u001b[0m Step 385/1000 | Loss: 2.0669\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:35:14 INFO\u001b[0m Step 385/1000 | Loss: 2.4151\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:35:14 INFO\u001b[0m Step 385/1000 | Loss: 2.8310\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:35:14 INFO\u001b[0m Step 385/1000 | Loss: 2.7097\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:35:14 INFO\u001b[0m Step 385/1000 | Loss: 2.9825\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:35:14 INFO\u001b[0m Step 385/1000 | Loss: 2.6695\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:35:14 INFO\u001b[0m Step 385/1000 | Loss: 2.0713\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:35:16 INFO\u001b[0m Step 386/1000 | Loss: 2.8838\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:35:16 INFO\u001b[0m Step 386/1000 | Loss: 2.8316\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:35:16 INFO\u001b[0m Step 386/1000 | Loss: 2.5593\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:35:16 INFO\u001b[0m Step 386/1000 | Loss: 2.1449\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:35:16 INFO\u001b[0m Step 386/1000 | Loss: 3.2523\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:35:16 INFO\u001b[0m Step 386/1000 | Loss: 2.2422\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:35:16 INFO\u001b[0m Step 386/1000 | Loss: 2.1375\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:35:16 INFO\u001b[0m Step 386/1000 | Loss: 2.9509\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:35:19 INFO\u001b[0m Step 387/1000 | Loss: 2.2526\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:35:19 INFO\u001b[0m Step 387/1000 | Loss: 2.5748\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:35:19 INFO\u001b[0m Step 387/1000 | Loss: 2.4620\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:35:19 INFO\u001b[0m Step 387/1000 | Loss: 2.5330\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:35:19 INFO\u001b[0m Step 387/1000 | Loss: 2.4074\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:35:19 INFO\u001b[0m Step 387/1000 | Loss: 2.2192\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:35:19 INFO\u001b[0m Step 387/1000 | Loss: 2.4975\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:35:19 INFO\u001b[0m Step 387/1000 | Loss: 2.3602\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:35:21 INFO\u001b[0m Step 388/1000 | Loss: 2.4398\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:35:21 INFO\u001b[0m Step 388/1000 | Loss: 2.4952\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:35:21 INFO\u001b[0m Step 388/1000 | Loss: 2.3674\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:35:21 INFO\u001b[0m Step 388/1000 | Loss: 2.4222\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:35:21 INFO\u001b[0m Step 388/1000 | Loss: 2.4705\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:35:21 INFO\u001b[0m Step 388/1000 | Loss: 2.4000\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:35:21 INFO\u001b[0m Step 388/1000 | Loss: 1.9973\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:35:21 INFO\u001b[0m Step 388/1000 | Loss: 2.8908\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:35:24 INFO\u001b[0m Step 389/1000 | Loss: 2.1809\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:35:24 INFO\u001b[0m Step 389/1000 | Loss: 2.5875\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:35:24 INFO\u001b[0m Step 389/1000 | Loss: 2.1708\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:35:24 INFO\u001b[0m Step 389/1000 | Loss: 2.2987\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:35:24 INFO\u001b[0m Step 389/1000 | Loss: 2.4391\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:35:24 INFO\u001b[0m Step 389/1000 | Loss: 2.4465\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:35:24 INFO\u001b[0m Step 389/1000 | Loss: 2.2947\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:35:24 INFO\u001b[0m Step 389/1000 | Loss: 2.2562\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:35:27 INFO\u001b[0m Step 390/1000 | Loss: 2.3867\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:35:27 INFO\u001b[0m Step 390/1000 | Loss: 2.2632\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:35:27 INFO\u001b[0m Step 390/1000 | Loss: 2.3609\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:35:27 INFO\u001b[0m Step 390/1000 | Loss: 2.5254\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:35:27 INFO\u001b[0m Step 390/1000 | Loss: 2.4720\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:35:27 INFO\u001b[0m Step 390/1000 | Loss: 2.3735\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:35:27 INFO\u001b[0m Step 390/1000 | Loss: 2.4116\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:35:27 INFO\u001b[0m Step 390/1000 | Loss: 2.3177\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:35:28 INFO\u001b[0m Step 391/1000 | Loss: 2.5057\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:35:28 INFO\u001b[0m Step 391/1000 | Loss: 2.5153\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:35:28 INFO\u001b[0m Step 391/1000 | Loss: 2.2015\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:35:28 INFO\u001b[0m Step 391/1000 | Loss: 1.9603\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:35:28 INFO\u001b[0m Step 391/1000 | Loss: 2.4082\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:35:28 INFO\u001b[0m Step 391/1000 | Loss: 2.1317\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:35:28 INFO\u001b[0m Step 391/1000 | Loss: 2.4974\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:35:28 INFO\u001b[0m Step 391/1000 | Loss: 2.3392\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:35:30 INFO\u001b[0m Step 392/1000 | Loss: 2.1749\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:35:30 INFO\u001b[0m Step 392/1000 | Loss: 2.2489\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:35:30 INFO\u001b[0m Step 392/1000 | Loss: 2.1953\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:35:30 INFO\u001b[0m Step 392/1000 | Loss: 2.0030\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:35:30 INFO\u001b[0m Step 392/1000 | Loss: 2.4949\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:35:30 INFO\u001b[0m Step 392/1000 | Loss: 2.5921\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:35:30 INFO\u001b[0m Step 392/1000 | Loss: 2.6628\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:35:30 INFO\u001b[0m Step 392/1000 | Loss: 2.2963\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:35:33 INFO\u001b[0m Step 393/1000 | Loss: 2.2184\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:35:33 INFO\u001b[0m Step 393/1000 | Loss: 2.4323\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:35:33 INFO\u001b[0m Step 393/1000 | Loss: 2.8225\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:35:33 INFO\u001b[0m Step 393/1000 | Loss: 2.4763\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:35:33 INFO\u001b[0m Step 393/1000 | Loss: 2.2637\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:35:33 INFO\u001b[0m Step 393/1000 | Loss: 2.4572\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:35:33 INFO\u001b[0m Step 393/1000 | Loss: 2.1393\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:35:33 INFO\u001b[0m Step 393/1000 | Loss: 2.4534\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:35:34 INFO\u001b[0m Step 394/1000 | Loss: 2.4933\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:35:34 INFO\u001b[0m Step 394/1000 | Loss: 2.4490\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:35:34 INFO\u001b[0m Step 394/1000 | Loss: 2.8034\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:35:34 INFO\u001b[0m Step 394/1000 | Loss: 2.2886\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:35:34 INFO\u001b[0m Step 394/1000 | Loss: 2.4430\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:35:34 INFO\u001b[0m Step 394/1000 | Loss: 2.9557\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:35:34 INFO\u001b[0m Step 394/1000 | Loss: 3.0842\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:35:34 INFO\u001b[0m Step 394/1000 | Loss: 2.0216\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:35:35 INFO\u001b[0m Step 395/1000 | Loss: 1.9264\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:35:35 INFO\u001b[0m Step 395/1000 | Loss: 1.9997\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:35:35 INFO\u001b[0m Step 395/1000 | Loss: 2.7235\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:35:35 INFO\u001b[0m Step 395/1000 | Loss: 2.1055\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:35:35 INFO\u001b[0m Step 395/1000 | Loss: 2.5798\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:35:35 INFO\u001b[0m Step 395/1000 | Loss: 2.6017\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:35:35 INFO\u001b[0m Step 395/1000 | Loss: 2.8132\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:35:35 INFO\u001b[0m Step 395/1000 | Loss: 1.8440\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:35:37 INFO\u001b[0m Step 396/1000 | Loss: 2.4384\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:35:37 INFO\u001b[0m Step 396/1000 | Loss: 2.0817\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:35:37 INFO\u001b[0m Step 396/1000 | Loss: 2.8414\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:35:37 INFO\u001b[0m Step 396/1000 | Loss: 2.9334\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:35:37 INFO\u001b[0m Step 396/1000 | Loss: 2.3762\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:35:37 INFO\u001b[0m Step 396/1000 | Loss: 2.7771\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:35:37 INFO\u001b[0m Step 396/1000 | Loss: 2.2944\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:35:37 INFO\u001b[0m Step 396/1000 | Loss: 2.0643\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:35:40 INFO\u001b[0m Step 397/1000 | Loss: 2.3310\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:35:40 INFO\u001b[0m Step 397/1000 | Loss: 2.5997\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:35:40 INFO\u001b[0m Step 397/1000 | Loss: 2.3294\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:35:40 INFO\u001b[0m Step 397/1000 | Loss: 2.5498\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:35:40 INFO\u001b[0m Step 397/1000 | Loss: 2.4294\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:35:40 INFO\u001b[0m Step 397/1000 | Loss: 2.4765\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:35:40 INFO\u001b[0m Step 397/1000 | Loss: 2.7813\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:35:40 INFO\u001b[0m Step 397/1000 | Loss: 2.1084\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:35:42 INFO\u001b[0m Step 398/1000 | Loss: 2.3781\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:35:42 INFO\u001b[0m Step 398/1000 | Loss: 2.7118\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:35:42 INFO\u001b[0m Step 398/1000 | Loss: 2.8142\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:35:42 INFO\u001b[0m Step 398/1000 | Loss: 1.9833\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:35:42 INFO\u001b[0m Step 398/1000 | Loss: 2.2874\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:35:42 INFO\u001b[0m Step 398/1000 | Loss: 2.3366\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:35:42 INFO\u001b[0m Step 398/1000 | Loss: 2.1054\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:35:42 INFO\u001b[0m Step 398/1000 | Loss: 3.3998\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:35:44 INFO\u001b[0m Step 399/1000 | Loss: 2.5338\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:35:44 INFO\u001b[0m Step 399/1000 | Loss: 2.4265\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:35:44 INFO\u001b[0m Step 399/1000 | Loss: 2.3147\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:35:44 INFO\u001b[0m Step 399/1000 | Loss: 2.2964\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:35:44 INFO\u001b[0m Step 399/1000 | Loss: 2.1912\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:35:44 INFO\u001b[0m Step 399/1000 | Loss: 2.5972\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:35:44 INFO\u001b[0m Step 399/1000 | Loss: 2.0136\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:35:44 INFO\u001b[0m Step 399/1000 | Loss: 2.2217\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:35:46 INFO\u001b[0m Step 400/1000 | Loss: 3.2069\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:35:46 INFO\u001b[0m Step 400/1000 | Loss: 2.8004\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:35:46 INFO\u001b[0m Step 400/1000 | Loss: 2.8657\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:35:46 INFO\u001b[0m Step 400/1000 | Loss: 2.6107\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:35:46 INFO\u001b[0m Step 400/1000 | Loss: 2.4787\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:35:46 INFO\u001b[0m Step 400/1000 | Loss: 2.9091\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:35:46 INFO\u001b[0m Step 400/1000 | Loss: 2.1438\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:35:46 INFO\u001b[0m Step 400/1000 | Loss: 2.5690\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:35:47 INFO\u001b[0m Step 401/1000 | Loss: 2.6686\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:35:47 INFO\u001b[0m Step 401/1000 | Loss: 2.2998\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:35:47 INFO\u001b[0m Step 401/1000 | Loss: 2.0622\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:35:47 INFO\u001b[0m Step 401/1000 | Loss: 3.2867\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:35:47 INFO\u001b[0m Step 401/1000 | Loss: 3.0736\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:35:47 INFO\u001b[0m Step 401/1000 | Loss: 2.3896\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:35:47 INFO\u001b[0m Step 401/1000 | Loss: 2.8888\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:35:47 INFO\u001b[0m Step 401/1000 | Loss: 2.3991\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:35:48 INFO\u001b[0m Step 402/1000 | Loss: 3.3277\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:35:48 INFO\u001b[0m Step 402/1000 | Loss: 2.8518\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:35:48 INFO\u001b[0m Step 402/1000 | Loss: 2.3483\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:35:48 INFO\u001b[0m Step 402/1000 | Loss: 2.5996\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:35:48 INFO\u001b[0m Step 402/1000 | Loss: 2.5348\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:35:48 INFO\u001b[0m Step 402/1000 | Loss: 2.5164\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:35:48 INFO\u001b[0m Step 402/1000 | Loss: 3.0118\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:35:48 INFO\u001b[0m Step 402/1000 | Loss: 2.5763\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:35:50 INFO\u001b[0m Step 403/1000 | Loss: 2.5992\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:35:50 INFO\u001b[0m Step 403/1000 | Loss: 2.2930\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:35:50 INFO\u001b[0m Step 403/1000 | Loss: 2.6473\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:35:50 INFO\u001b[0m Step 403/1000 | Loss: 2.4009\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:35:50 INFO\u001b[0m Step 403/1000 | Loss: 2.9272\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:35:50 INFO\u001b[0m Step 403/1000 | Loss: 2.5130\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:35:50 INFO\u001b[0m Step 403/1000 | Loss: 3.0259\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:35:50 INFO\u001b[0m Step 403/1000 | Loss: 2.9986\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:35:51 INFO\u001b[0m Step 404/1000 | Loss: 2.3147\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:35:51 INFO\u001b[0m Step 404/1000 | Loss: 2.5283\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:35:51 INFO\u001b[0m Step 404/1000 | Loss: 2.4445\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:35:51 INFO\u001b[0m Step 404/1000 | Loss: 2.2028\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:35:51 INFO\u001b[0m Step 404/1000 | Loss: 2.4525\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:35:51 INFO\u001b[0m Step 404/1000 | Loss: 2.4106\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:35:51 INFO\u001b[0m Step 404/1000 | Loss: 2.0555\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:35:51 INFO\u001b[0m Step 404/1000 | Loss: 2.7798\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:35:53 INFO\u001b[0m Step 405/1000 | Loss: 2.1380\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:35:53 INFO\u001b[0m Step 405/1000 | Loss: 2.3123\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:35:53 INFO\u001b[0m Step 405/1000 | Loss: 2.0384\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:35:53 INFO\u001b[0m Step 405/1000 | Loss: 2.0791\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:35:53 INFO\u001b[0m Step 405/1000 | Loss: 2.3084\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:35:53 INFO\u001b[0m Step 405/1000 | Loss: 2.3805\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:35:53 INFO\u001b[0m Step 405/1000 | Loss: 2.2346\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:35:53 INFO\u001b[0m Step 405/1000 | Loss: 2.9662\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:35:55 INFO\u001b[0m Step 406/1000 | Loss: 2.7467\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:35:55 INFO\u001b[0m Step 406/1000 | Loss: 2.7311\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:35:55 INFO\u001b[0m Step 406/1000 | Loss: 2.2958\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:35:55 INFO\u001b[0m Step 406/1000 | Loss: 2.3768\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:35:55 INFO\u001b[0m Step 406/1000 | Loss: 2.0745\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:35:55 INFO\u001b[0m Step 406/1000 | Loss: 2.0830\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:35:55 INFO\u001b[0m Step 406/1000 | Loss: 2.0355\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:35:55 INFO\u001b[0m Step 406/1000 | Loss: 2.2714\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:35:59 INFO\u001b[0m Step 407/1000 | Loss: 2.1508\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:35:59 INFO\u001b[0m Step 407/1000 | Loss: 2.4766\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:35:59 INFO\u001b[0m Step 407/1000 | Loss: 2.4933\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:35:59 INFO\u001b[0m Step 407/1000 | Loss: 1.8972\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:35:59 INFO\u001b[0m Step 407/1000 | Loss: 2.3882\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:35:59 INFO\u001b[0m Step 407/1000 | Loss: 2.1826\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:35:59 INFO\u001b[0m Step 407/1000 | Loss: 2.4255\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:35:59 INFO\u001b[0m Step 407/1000 | Loss: 2.1869\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:36:01 INFO\u001b[0m Step 408/1000 | Loss: 2.1599\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:36:01 INFO\u001b[0m Step 408/1000 | Loss: 2.3385\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:36:01 INFO\u001b[0m Step 408/1000 | Loss: 2.2330\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:36:01 INFO\u001b[0m Step 408/1000 | Loss: 2.5496\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:36:01 INFO\u001b[0m Step 408/1000 | Loss: 2.4220\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:36:01 INFO\u001b[0m Step 408/1000 | Loss: 2.1084\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:36:01 INFO\u001b[0m Step 408/1000 | Loss: 2.2213\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:36:01 INFO\u001b[0m Step 408/1000 | Loss: 2.0453\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:36:03 INFO\u001b[0m Step 409/1000 | Loss: 2.2420\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:36:03 INFO\u001b[0m Step 409/1000 | Loss: 2.2005\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:36:03 INFO\u001b[0m Step 409/1000 | Loss: 2.1634\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:36:03 INFO\u001b[0m Step 409/1000 | Loss: 2.1481\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:36:03 INFO\u001b[0m Step 409/1000 | Loss: 2.6359\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:36:03 INFO\u001b[0m Step 409/1000 | Loss: 2.2338\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:36:03 INFO\u001b[0m Step 409/1000 | Loss: 2.2284\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:36:03 INFO\u001b[0m Step 409/1000 | Loss: 2.8053\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:36:06 INFO\u001b[0m Step 410/1000 | Loss: 2.1901\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:36:06 INFO\u001b[0m Step 410/1000 | Loss: 1.9193\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:36:06 INFO\u001b[0m Step 410/1000 | Loss: 2.7001\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:36:06 INFO\u001b[0m Step 410/1000 | Loss: 2.0995\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:36:06 INFO\u001b[0m Step 410/1000 | Loss: 2.7658\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:36:06 INFO\u001b[0m Step 410/1000 | Loss: 2.3217\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:36:06 INFO\u001b[0m Step 410/1000 | Loss: 2.4793\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:36:06 INFO\u001b[0m Step 410/1000 | Loss: 2.5398\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:36:08 INFO\u001b[0m Step 411/1000 | Loss: 2.5559\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:36:08 INFO\u001b[0m Step 411/1000 | Loss: 2.5159\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:36:08 INFO\u001b[0m Step 411/1000 | Loss: 2.3382\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:36:08 INFO\u001b[0m Step 411/1000 | Loss: 2.2753\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:36:08 INFO\u001b[0m Step 411/1000 | Loss: 2.2938\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:36:08 INFO\u001b[0m Step 411/1000 | Loss: 2.3022\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:36:08 INFO\u001b[0m Step 411/1000 | Loss: 2.5081\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:36:08 INFO\u001b[0m Step 411/1000 | Loss: 2.6375\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:36:10 INFO\u001b[0m Step 412/1000 | Loss: 2.9322\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:36:10 INFO\u001b[0m Step 412/1000 | Loss: 2.4382\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:36:10 INFO\u001b[0m Step 412/1000 | Loss: 2.8317\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:36:10 INFO\u001b[0m Step 412/1000 | Loss: 2.3441\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:36:10 INFO\u001b[0m Step 412/1000 | Loss: 2.7450\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:36:10 INFO\u001b[0m Step 412/1000 | Loss: 3.1061\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:36:10 INFO\u001b[0m Step 412/1000 | Loss: 2.5902\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:36:10 INFO\u001b[0m Step 412/1000 | Loss: 2.5670\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:36:12 INFO\u001b[0m Step 413/1000 | Loss: 2.1076\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:36:12 INFO\u001b[0m Step 413/1000 | Loss: 2.6041\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:36:12 INFO\u001b[0m Step 413/1000 | Loss: 2.2437\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:36:12 INFO\u001b[0m Step 413/1000 | Loss: 2.5586\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:36:12 INFO\u001b[0m Step 413/1000 | Loss: 3.0158\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:36:12 INFO\u001b[0m Step 413/1000 | Loss: 2.2835\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:36:12 INFO\u001b[0m Step 413/1000 | Loss: 2.1980\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:36:12 INFO\u001b[0m Step 413/1000 | Loss: 2.2266\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:36:14 INFO\u001b[0m Step 414/1000 | Loss: 2.9179\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:36:14 INFO\u001b[0m Step 414/1000 | Loss: 2.8661\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:36:14 INFO\u001b[0m Step 414/1000 | Loss: 2.4412\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:36:14 INFO\u001b[0m Step 414/1000 | Loss: 2.6808\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:36:14 INFO\u001b[0m Step 414/1000 | Loss: 2.1997\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:36:14 INFO\u001b[0m Step 414/1000 | Loss: 2.6852\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:36:14 INFO\u001b[0m Step 414/1000 | Loss: 2.9446\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:36:14 INFO\u001b[0m Step 414/1000 | Loss: 2.8059\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:36:16 INFO\u001b[0m Step 415/1000 | Loss: 3.5154\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:36:16 INFO\u001b[0m Step 415/1000 | Loss: 2.0937\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:36:16 INFO\u001b[0m Step 415/1000 | Loss: 3.8516\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:36:16 INFO\u001b[0m Step 415/1000 | Loss: 2.4095\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:36:16 INFO\u001b[0m Step 415/1000 | Loss: 4.0047\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:36:16 INFO\u001b[0m Step 415/1000 | Loss: 2.3901\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:36:16 INFO\u001b[0m Step 415/1000 | Loss: 2.7306\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:36:16 INFO\u001b[0m Step 415/1000 | Loss: 2.8658\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:36:18 INFO\u001b[0m Step 416/1000 | Loss: 2.6255\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:36:18 INFO\u001b[0m Step 416/1000 | Loss: 3.3914\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:36:18 INFO\u001b[0m Step 416/1000 | Loss: 2.2691\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:36:18 INFO\u001b[0m Step 416/1000 | Loss: 2.9292\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:36:18 INFO\u001b[0m Step 416/1000 | Loss: 3.2212\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:36:18 INFO\u001b[0m Step 416/1000 | Loss: 1.9719\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:36:18 INFO\u001b[0m Step 416/1000 | Loss: 2.4667\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:36:18 INFO\u001b[0m Step 416/1000 | Loss: 2.3715\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:36:20 INFO\u001b[0m Step 417/1000 | Loss: 3.7061\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:36:20 INFO\u001b[0m Step 417/1000 | Loss: 3.2362\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:36:20 INFO\u001b[0m Step 417/1000 | Loss: 3.5192\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:36:20 INFO\u001b[0m Step 417/1000 | Loss: 3.2868\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:36:20 INFO\u001b[0m Step 417/1000 | Loss: 2.9526\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:36:20 INFO\u001b[0m Step 417/1000 | Loss: 2.5908\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:36:20 INFO\u001b[0m Step 417/1000 | Loss: 3.0614\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:36:20 INFO\u001b[0m Step 417/1000 | Loss: 3.3368\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:36:22 INFO\u001b[0m Step 418/1000 | Loss: 3.1515\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:36:22 INFO\u001b[0m Step 418/1000 | Loss: 2.3757\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:36:22 INFO\u001b[0m Step 418/1000 | Loss: 3.0445\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:36:22 INFO\u001b[0m Step 418/1000 | Loss: 2.9402\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:36:22 INFO\u001b[0m Step 418/1000 | Loss: 2.7685\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:36:22 INFO\u001b[0m Step 418/1000 | Loss: 3.0104\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:36:22 INFO\u001b[0m Step 418/1000 | Loss: 3.7620\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:36:22 INFO\u001b[0m Step 418/1000 | Loss: 2.8479\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:36:23 INFO\u001b[0m Step 419/1000 | Loss: 3.4789\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:36:23 INFO\u001b[0m Step 419/1000 | Loss: 2.3077\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:36:23 INFO\u001b[0m Step 419/1000 | Loss: 3.1010\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:36:23 INFO\u001b[0m Step 419/1000 | Loss: 3.5816\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:36:23 INFO\u001b[0m Step 419/1000 | Loss: 4.0587\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:36:23 INFO\u001b[0m Step 419/1000 | Loss: 3.2948\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:36:23 INFO\u001b[0m Step 419/1000 | Loss: 3.0004\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:36:23 INFO\u001b[0m Step 419/1000 | Loss: 2.6152\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:36:27 INFO\u001b[0m Step 420/1000 | Loss: 3.0405\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:36:27 INFO\u001b[0m Step 420/1000 | Loss: 3.0576\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:36:27 INFO\u001b[0m Step 420/1000 | Loss: 3.0804\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:36:27 INFO\u001b[0m Step 420/1000 | Loss: 3.0916\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:36:27 INFO\u001b[0m Step 420/1000 | Loss: 3.1425\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:36:27 INFO\u001b[0m Step 420/1000 | Loss: 2.9297\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:36:27 INFO\u001b[0m Step 420/1000 | Loss: 3.3039\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:36:27 INFO\u001b[0m Step 420/1000 | Loss: 3.4910\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:36:29 INFO\u001b[0m Step 421/1000 | Loss: 3.0789\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:36:29 INFO\u001b[0m Step 421/1000 | Loss: 3.4194\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:36:29 INFO\u001b[0m Step 421/1000 | Loss: 3.0361\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:36:29 INFO\u001b[0m Step 421/1000 | Loss: 2.7524\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:36:29 INFO\u001b[0m Step 421/1000 | Loss: 3.5226\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:36:29 INFO\u001b[0m Step 421/1000 | Loss: 3.7228\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:36:29 INFO\u001b[0m Step 421/1000 | Loss: 3.3088\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:36:29 INFO\u001b[0m Step 421/1000 | Loss: 2.5152\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:36:31 INFO\u001b[0m Step 422/1000 | Loss: 3.5629\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:36:31 INFO\u001b[0m Step 422/1000 | Loss: 3.5828\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:36:31 INFO\u001b[0m Step 422/1000 | Loss: 3.0848\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:36:31 INFO\u001b[0m Step 422/1000 | Loss: 3.2328\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:36:31 INFO\u001b[0m Step 422/1000 | Loss: 2.8519\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:36:31 INFO\u001b[0m Step 422/1000 | Loss: 3.0012\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:36:31 INFO\u001b[0m Step 422/1000 | Loss: 2.9376\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:36:31 INFO\u001b[0m Step 422/1000 | Loss: 3.0429\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:36:32 INFO\u001b[0m Step 423/1000 | Loss: 2.8669\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:36:32 INFO\u001b[0m Step 423/1000 | Loss: 3.1503\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:36:32 INFO\u001b[0m Step 423/1000 | Loss: 2.5917\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:36:32 INFO\u001b[0m Step 423/1000 | Loss: 2.2382\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:36:32 INFO\u001b[0m Step 423/1000 | Loss: 2.7030\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:36:32 INFO\u001b[0m Step 423/1000 | Loss: 2.9783\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:36:32 INFO\u001b[0m Step 423/1000 | Loss: 3.1135\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:36:32 INFO\u001b[0m Step 423/1000 | Loss: 3.0720\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:36:35 INFO\u001b[0m Step 424/1000 | Loss: 3.4434\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:36:35 INFO\u001b[0m Step 424/1000 | Loss: 2.4725\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:36:35 INFO\u001b[0m Step 424/1000 | Loss: 2.6544\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:36:35 INFO\u001b[0m Step 424/1000 | Loss: 2.3131\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:36:35 INFO\u001b[0m Step 424/1000 | Loss: 2.7623\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:36:35 INFO\u001b[0m Step 424/1000 | Loss: 2.8492\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:36:35 INFO\u001b[0m Step 424/1000 | Loss: 3.3510\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:36:35 INFO\u001b[0m Step 424/1000 | Loss: 3.2263\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:36:37 INFO\u001b[0m Step 425/1000 | Loss: 2.6572\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:36:37 INFO\u001b[0m Step 425/1000 | Loss: 2.8769\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:36:37 INFO\u001b[0m Step 425/1000 | Loss: 2.7941\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:36:37 INFO\u001b[0m Step 425/1000 | Loss: 2.8049\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:36:37 INFO\u001b[0m Step 425/1000 | Loss: 3.1696\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:36:37 INFO\u001b[0m Step 425/1000 | Loss: 2.6925\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:36:37 INFO\u001b[0m Step 425/1000 | Loss: 2.6452\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:36:37 INFO\u001b[0m Step 425/1000 | Loss: 2.9657\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:36:39 INFO\u001b[0m Step 426/1000 | Loss: 3.4088\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:36:39 INFO\u001b[0m Step 426/1000 | Loss: 2.8095\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:36:39 INFO\u001b[0m Step 426/1000 | Loss: 2.9817\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:36:39 INFO\u001b[0m Step 426/1000 | Loss: 2.7515\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:36:39 INFO\u001b[0m Step 426/1000 | Loss: 2.5800\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:36:39 INFO\u001b[0m Step 426/1000 | Loss: 3.2404\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:36:39 INFO\u001b[0m Step 426/1000 | Loss: 3.4708\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:36:39 INFO\u001b[0m Step 426/1000 | Loss: 2.6327\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:36:41 INFO\u001b[0m Step 427/1000 | Loss: 3.0194\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:36:41 INFO\u001b[0m Step 427/1000 | Loss: 2.8361\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:36:41 INFO\u001b[0m Step 427/1000 | Loss: 2.5957\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:36:41 INFO\u001b[0m Step 427/1000 | Loss: 2.2936\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:36:41 INFO\u001b[0m Step 427/1000 | Loss: 2.6070\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:36:41 INFO\u001b[0m Step 427/1000 | Loss: 2.3551\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:36:41 INFO\u001b[0m Step 427/1000 | Loss: 3.0183\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:36:41 INFO\u001b[0m Step 427/1000 | Loss: 2.9406\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:36:45 INFO\u001b[0m Step 428/1000 | Loss: 2.4494\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:36:45 INFO\u001b[0m Step 428/1000 | Loss: 2.7558\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:36:45 INFO\u001b[0m Step 428/1000 | Loss: 1.9921\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:36:45 INFO\u001b[0m Step 428/1000 | Loss: 2.3781\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:36:45 INFO\u001b[0m Step 428/1000 | Loss: 3.0954\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:36:45 INFO\u001b[0m Step 428/1000 | Loss: 2.5856\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:36:45 INFO\u001b[0m Step 428/1000 | Loss: 2.9431\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:36:45 INFO\u001b[0m Step 428/1000 | Loss: 2.2079\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:36:47 INFO\u001b[0m Step 429/1000 | Loss: 1.9707\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:36:47 INFO\u001b[0m Step 429/1000 | Loss: 1.9142\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:36:47 INFO\u001b[0m Step 429/1000 | Loss: 2.3998\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:36:47 INFO\u001b[0m Step 429/1000 | Loss: 2.4233\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:36:47 INFO\u001b[0m Step 429/1000 | Loss: 2.8014\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:36:47 INFO\u001b[0m Step 429/1000 | Loss: 2.2578\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:36:47 INFO\u001b[0m Step 429/1000 | Loss: 2.5557\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:36:47 INFO\u001b[0m Step 429/1000 | Loss: 2.4421\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:36:50 INFO\u001b[0m Step 430/1000 | Loss: 2.4400\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:36:50 INFO\u001b[0m Step 430/1000 | Loss: 3.0135\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:36:50 INFO\u001b[0m Step 430/1000 | Loss: 1.9413\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:36:50 INFO\u001b[0m Step 430/1000 | Loss: 2.3759\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:36:50 INFO\u001b[0m Step 430/1000 | Loss: 2.0526\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:36:50 INFO\u001b[0m Step 430/1000 | Loss: 2.6560\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:36:50 INFO\u001b[0m Step 430/1000 | Loss: 2.5631\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:36:50 INFO\u001b[0m Step 430/1000 | Loss: 2.4925\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:36:52 INFO\u001b[0m Step 431/1000 | Loss: 2.9358\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:36:52 INFO\u001b[0m Step 431/1000 | Loss: 2.1874\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:36:52 INFO\u001b[0m Step 431/1000 | Loss: 3.2089\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:36:52 INFO\u001b[0m Step 431/1000 | Loss: 2.5096\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:36:52 INFO\u001b[0m Step 431/1000 | Loss: 2.1675\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:36:52 INFO\u001b[0m Step 431/1000 | Loss: 2.6088\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:36:52 INFO\u001b[0m Step 431/1000 | Loss: 2.2365\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:36:52 INFO\u001b[0m Step 431/1000 | Loss: 2.7495\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:36:53 INFO\u001b[0m Step 432/1000 | Loss: 2.9263\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:36:53 INFO\u001b[0m Step 432/1000 | Loss: 2.3419\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:36:53 INFO\u001b[0m Step 432/1000 | Loss: 2.4556\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:36:53 INFO\u001b[0m Step 432/1000 | Loss: 2.4253\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:36:53 INFO\u001b[0m Step 432/1000 | Loss: 2.4830\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:36:53 INFO\u001b[0m Step 432/1000 | Loss: 2.6136\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:36:53 INFO\u001b[0m Step 432/1000 | Loss: 2.4277\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:36:53 INFO\u001b[0m Step 432/1000 | Loss: 2.1366\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:36:57 INFO\u001b[0m Step 433/1000 | Loss: 2.1473\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:36:57 INFO\u001b[0m Step 433/1000 | Loss: 2.1886\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:36:57 INFO\u001b[0m Step 433/1000 | Loss: 2.9617\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:36:57 INFO\u001b[0m Step 433/1000 | Loss: 6.1237\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:36:57 INFO\u001b[0m Step 433/1000 | Loss: 2.4334\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:36:57 INFO\u001b[0m Step 433/1000 | Loss: 2.6573\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:36:57 INFO\u001b[0m Step 433/1000 | Loss: 2.7607\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:36:57 INFO\u001b[0m Step 433/1000 | Loss: 2.6807\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:36:58 INFO\u001b[0m Step 434/1000 | Loss: 2.4123\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:36:58 INFO\u001b[0m Step 434/1000 | Loss: 2.2196\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:36:58 INFO\u001b[0m Step 434/1000 | Loss: 2.2155\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:36:58 INFO\u001b[0m Step 434/1000 | Loss: 2.9660\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:36:58 INFO\u001b[0m Step 434/1000 | Loss: 2.5518\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:36:58 INFO\u001b[0m Step 434/1000 | Loss: 2.8150\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:36:58 INFO\u001b[0m Step 434/1000 | Loss: 2.5774\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:36:58 INFO\u001b[0m Step 434/1000 | Loss: 3.1018\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:37:01 INFO\u001b[0m Step 435/1000 | Loss: 2.8578\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:37:01 INFO\u001b[0m Step 435/1000 | Loss: 3.2469\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:37:01 INFO\u001b[0m Step 435/1000 | Loss: 2.4404\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:37:01 INFO\u001b[0m Step 435/1000 | Loss: 2.8107\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:37:01 INFO\u001b[0m Step 435/1000 | Loss: 2.2460\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:37:01 INFO\u001b[0m Step 435/1000 | Loss: 2.0916\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:37:01 INFO\u001b[0m Step 435/1000 | Loss: 2.3033\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:37:01 INFO\u001b[0m Step 435/1000 | Loss: 2.4654\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:37:03 INFO\u001b[0m Step 436/1000 | Loss: 2.6624\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:37:03 INFO\u001b[0m Step 436/1000 | Loss: 2.9055\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:37:03 INFO\u001b[0m Step 436/1000 | Loss: 2.6266\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:37:03 INFO\u001b[0m Step 436/1000 | Loss: 2.4053\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:37:03 INFO\u001b[0m Step 436/1000 | Loss: 2.1758\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:37:03 INFO\u001b[0m Step 436/1000 | Loss: 2.1422\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:37:03 INFO\u001b[0m Step 436/1000 | Loss: 2.6623\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:37:03 INFO\u001b[0m Step 436/1000 | Loss: 3.2182\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:37:04 INFO\u001b[0m Step 437/1000 | Loss: 2.9997\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:37:04 INFO\u001b[0m Step 437/1000 | Loss: 2.4559\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:37:04 INFO\u001b[0m Step 437/1000 | Loss: 2.4228\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:37:04 INFO\u001b[0m Step 437/1000 | Loss: 2.3684\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:37:04 INFO\u001b[0m Step 437/1000 | Loss: 2.2953\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:37:04 INFO\u001b[0m Step 437/1000 | Loss: 2.7472\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:37:04 INFO\u001b[0m Step 437/1000 | Loss: 2.8507\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:37:04 INFO\u001b[0m Step 437/1000 | Loss: 2.7071\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:37:05 INFO\u001b[0m Step 438/1000 | Loss: 3.0607\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:37:05 INFO\u001b[0m Step 438/1000 | Loss: 3.2485\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:37:05 INFO\u001b[0m Step 438/1000 | Loss: 3.0865\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:37:05 INFO\u001b[0m Step 438/1000 | Loss: 3.2632\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:37:05 INFO\u001b[0m Step 438/1000 | Loss: 3.2280\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:37:05 INFO\u001b[0m Step 438/1000 | Loss: 2.4796\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:37:05 INFO\u001b[0m Step 438/1000 | Loss: 3.0513\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:37:05 INFO\u001b[0m Step 438/1000 | Loss: 3.3467\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:37:07 INFO\u001b[0m Step 439/1000 | Loss: 2.8977\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:37:07 INFO\u001b[0m Step 439/1000 | Loss: 2.5544\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:37:07 INFO\u001b[0m Step 439/1000 | Loss: 3.4586\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:37:07 INFO\u001b[0m Step 439/1000 | Loss: 3.3707\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:37:07 INFO\u001b[0m Step 439/1000 | Loss: 3.1669\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:37:07 INFO\u001b[0m Step 439/1000 | Loss: 2.5346\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:37:07 INFO\u001b[0m Step 439/1000 | Loss: 3.0959\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:37:07 INFO\u001b[0m Step 439/1000 | Loss: 2.4450\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:37:08 INFO\u001b[0m Step 440/1000 | Loss: 3.0473\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:37:08 INFO\u001b[0m Step 440/1000 | Loss: 2.9472\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:37:08 INFO\u001b[0m Step 440/1000 | Loss: 2.5789\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:37:08 INFO\u001b[0m Step 440/1000 | Loss: 2.9956\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:37:08 INFO\u001b[0m Step 440/1000 | Loss: 3.1640\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:37:08 INFO\u001b[0m Step 440/1000 | Loss: 2.6604\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:37:08 INFO\u001b[0m Step 440/1000 | Loss: 3.9771\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:37:08 INFO\u001b[0m Step 440/1000 | Loss: 3.1100\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:37:10 INFO\u001b[0m Step 441/1000 | Loss: 3.3520\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:37:10 INFO\u001b[0m Step 441/1000 | Loss: 2.6690\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:37:10 INFO\u001b[0m Step 441/1000 | Loss: 3.3073\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:37:10 INFO\u001b[0m Step 441/1000 | Loss: 2.7675\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:37:10 INFO\u001b[0m Step 441/1000 | Loss: 2.5122\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:37:10 INFO\u001b[0m Step 441/1000 | Loss: 3.2557\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:37:10 INFO\u001b[0m Step 441/1000 | Loss: 3.3039\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:37:10 INFO\u001b[0m Step 441/1000 | Loss: 3.6282\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:37:11 INFO\u001b[0m Step 442/1000 | Loss: 3.0769\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:37:11 INFO\u001b[0m Step 442/1000 | Loss: 3.3065\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:37:11 INFO\u001b[0m Step 442/1000 | Loss: 2.7186\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:37:11 INFO\u001b[0m Step 442/1000 | Loss: 2.7700\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:37:11 INFO\u001b[0m Step 442/1000 | Loss: 3.1101\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:37:11 INFO\u001b[0m Step 442/1000 | Loss: 2.9269\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:37:11 INFO\u001b[0m Step 442/1000 | Loss: 2.8179\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:37:11 INFO\u001b[0m Step 442/1000 | Loss: 2.6520\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:37:14 INFO\u001b[0m Step 443/1000 | Loss: 3.3156\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:37:14 INFO\u001b[0m Step 443/1000 | Loss: 2.6787\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:37:14 INFO\u001b[0m Step 443/1000 | Loss: 2.6896\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:37:14 INFO\u001b[0m Step 443/1000 | Loss: 3.0264\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:37:14 INFO\u001b[0m Step 443/1000 | Loss: 3.2091\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:37:14 INFO\u001b[0m Step 443/1000 | Loss: 3.3496\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:37:14 INFO\u001b[0m Step 443/1000 | Loss: 2.7849\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:37:14 INFO\u001b[0m Step 443/1000 | Loss: 3.4546\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:37:18 INFO\u001b[0m Step 444/1000 | Loss: 2.8532\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:37:18 INFO\u001b[0m Step 444/1000 | Loss: 3.0770\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:37:18 INFO\u001b[0m Step 444/1000 | Loss: 3.1547\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:37:18 INFO\u001b[0m Step 444/1000 | Loss: 3.1729\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:37:18 INFO\u001b[0m Step 444/1000 | Loss: 3.0926\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:37:18 INFO\u001b[0m Step 444/1000 | Loss: 2.9312\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:37:18 INFO\u001b[0m Step 444/1000 | Loss: 2.8293\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:37:18 INFO\u001b[0m Step 444/1000 | Loss: 2.9440\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:37:21 INFO\u001b[0m Step 445/1000 | Loss: 3.6969\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:37:21 INFO\u001b[0m Step 445/1000 | Loss: 3.6629\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:37:21 INFO\u001b[0m Step 445/1000 | Loss: 2.9612\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:37:21 INFO\u001b[0m Step 445/1000 | Loss: 2.8566\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:37:21 INFO\u001b[0m Step 445/1000 | Loss: 3.3975\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:37:21 INFO\u001b[0m Step 445/1000 | Loss: 4.3092\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:37:21 INFO\u001b[0m Step 445/1000 | Loss: 2.9954\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:37:21 INFO\u001b[0m Step 445/1000 | Loss: 2.9716\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:37:23 INFO\u001b[0m Step 446/1000 | Loss: 2.7682\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:37:23 INFO\u001b[0m Step 446/1000 | Loss: 3.0288\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:37:23 INFO\u001b[0m Step 446/1000 | Loss: 3.3883\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:37:23 INFO\u001b[0m Step 446/1000 | Loss: 2.8115\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:37:23 INFO\u001b[0m Step 446/1000 | Loss: 2.8462\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:37:23 INFO\u001b[0m Step 446/1000 | Loss: 3.0572\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:37:23 INFO\u001b[0m Step 446/1000 | Loss: 2.5267\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:37:23 INFO\u001b[0m Step 446/1000 | Loss: 3.5728\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:37:25 INFO\u001b[0m Step 447/1000 | Loss: 2.8871\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:37:25 INFO\u001b[0m Step 447/1000 | Loss: 3.1628\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:37:25 INFO\u001b[0m Step 447/1000 | Loss: 3.4012\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:37:25 INFO\u001b[0m Step 447/1000 | Loss: 3.2975\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:37:25 INFO\u001b[0m Step 447/1000 | Loss: 2.9445\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:37:25 INFO\u001b[0m Step 447/1000 | Loss: 2.5929\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:37:25 INFO\u001b[0m Step 447/1000 | Loss: 3.0926\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:37:25 INFO\u001b[0m Step 447/1000 | Loss: 2.6609\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:37:26 INFO\u001b[0m Step 448/1000 | Loss: 2.6487\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:37:26 INFO\u001b[0m Step 448/1000 | Loss: 3.0831\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:37:26 INFO\u001b[0m Step 448/1000 | Loss: 2.9141\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:37:26 INFO\u001b[0m Step 448/1000 | Loss: 3.4645\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:37:26 INFO\u001b[0m Step 448/1000 | Loss: 2.9896\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:37:26 INFO\u001b[0m Step 448/1000 | Loss: 2.9099\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:37:26 INFO\u001b[0m Step 448/1000 | Loss: 3.0417\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:37:26 INFO\u001b[0m Step 448/1000 | Loss: 3.0054\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:37:28 INFO\u001b[0m Step 449/1000 | Loss: 2.8835\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:37:28 INFO\u001b[0m Step 449/1000 | Loss: 2.8201\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:37:28 INFO\u001b[0m Step 449/1000 | Loss: 2.8247\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:37:28 INFO\u001b[0m Step 449/1000 | Loss: 2.7579\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:37:28 INFO\u001b[0m Step 449/1000 | Loss: 2.9995\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:37:28 INFO\u001b[0m Step 449/1000 | Loss: 2.9078\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:37:28 INFO\u001b[0m Step 449/1000 | Loss: 3.0918\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:37:28 INFO\u001b[0m Step 449/1000 | Loss: 3.0981\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:37:30 INFO\u001b[0m Step 450/1000 | Loss: 2.7794\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:37:30 INFO\u001b[0m Step 450/1000 | Loss: 2.6545\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:37:30 INFO\u001b[0m Step 450/1000 | Loss: 2.8484\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:37:30 INFO\u001b[0m Step 450/1000 | Loss: 2.8606\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:37:30 INFO\u001b[0m Step 450/1000 | Loss: 2.6346\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:37:30 INFO\u001b[0m Step 450/1000 | Loss: 3.1025\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:37:30 INFO\u001b[0m Step 450/1000 | Loss: 2.8534\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:37:30 INFO\u001b[0m Step 450/1000 | Loss: 2.5562\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:37:32 INFO\u001b[0m Step 451/1000 | Loss: 3.2391\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:37:32 INFO\u001b[0m Step 451/1000 | Loss: 2.7782\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:37:32 INFO\u001b[0m Step 451/1000 | Loss: 2.4271\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:37:32 INFO\u001b[0m Step 451/1000 | Loss: 3.2787\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:37:32 INFO\u001b[0m Step 451/1000 | Loss: 3.0267\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:37:32 INFO\u001b[0m Step 451/1000 | Loss: 2.9527\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:37:32 INFO\u001b[0m Step 451/1000 | Loss: 2.5542\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:37:32 INFO\u001b[0m Step 451/1000 | Loss: 2.3605\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:37:35 INFO\u001b[0m Step 452/1000 | Loss: 2.9213\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:37:35 INFO\u001b[0m Step 452/1000 | Loss: 3.4230\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:37:35 INFO\u001b[0m Step 452/1000 | Loss: 3.1208\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:37:35 INFO\u001b[0m Step 452/1000 | Loss: 2.7167\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:37:35 INFO\u001b[0m Step 452/1000 | Loss: 3.3457\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:37:35 INFO\u001b[0m Step 452/1000 | Loss: 2.6830\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:37:35 INFO\u001b[0m Step 452/1000 | Loss: 3.0238\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:37:35 INFO\u001b[0m Step 452/1000 | Loss: 3.2303\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:37:37 INFO\u001b[0m Step 453/1000 | Loss: 2.6155\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:37:37 INFO\u001b[0m Step 453/1000 | Loss: 3.1369\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:37:37 INFO\u001b[0m Step 453/1000 | Loss: 2.5376\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:37:37 INFO\u001b[0m Step 453/1000 | Loss: 2.7700\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:37:37 INFO\u001b[0m Step 453/1000 | Loss: 3.0986\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:37:37 INFO\u001b[0m Step 453/1000 | Loss: 2.7138\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:37:37 INFO\u001b[0m Step 453/1000 | Loss: 2.7701\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:37:37 INFO\u001b[0m Step 453/1000 | Loss: 4.0415\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:37:38 INFO\u001b[0m Step 454/1000 | Loss: 2.7422\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:37:38 INFO\u001b[0m Step 454/1000 | Loss: 2.9524\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:37:38 INFO\u001b[0m Step 454/1000 | Loss: 2.6634\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:37:38 INFO\u001b[0m Step 454/1000 | Loss: 2.8045\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:37:38 INFO\u001b[0m Step 454/1000 | Loss: 3.1213\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:37:38 INFO\u001b[0m Step 454/1000 | Loss: 3.1308\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:37:38 INFO\u001b[0m Step 454/1000 | Loss: 2.5187\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:37:38 INFO\u001b[0m Step 454/1000 | Loss: 3.1416\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:37:40 INFO\u001b[0m Step 455/1000 | Loss: 2.7139\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:37:40 INFO\u001b[0m Step 455/1000 | Loss: 2.4746\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:37:40 INFO\u001b[0m Step 455/1000 | Loss: 2.9073\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:37:40 INFO\u001b[0m Step 455/1000 | Loss: 2.8027\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:37:40 INFO\u001b[0m Step 455/1000 | Loss: 2.9924\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:37:40 INFO\u001b[0m Step 455/1000 | Loss: 2.7747\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:37:40 INFO\u001b[0m Step 455/1000 | Loss: 2.7529\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:37:40 INFO\u001b[0m Step 455/1000 | Loss: 2.3475\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:37:42 INFO\u001b[0m Step 456/1000 | Loss: 2.6767\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:37:42 INFO\u001b[0m Step 456/1000 | Loss: 2.4953\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:37:42 INFO\u001b[0m Step 456/1000 | Loss: 2.9951\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:37:42 INFO\u001b[0m Step 456/1000 | Loss: 2.7920\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:37:42 INFO\u001b[0m Step 456/1000 | Loss: 2.7459\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:37:42 INFO\u001b[0m Step 456/1000 | Loss: 2.1390\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:37:42 INFO\u001b[0m Step 456/1000 | Loss: 2.2970\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:37:42 INFO\u001b[0m Step 456/1000 | Loss: 2.6935\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:37:43 INFO\u001b[0m Step 457/1000 | Loss: 2.4671\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:37:43 INFO\u001b[0m Step 457/1000 | Loss: 3.2975\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:37:43 INFO\u001b[0m Step 457/1000 | Loss: 3.0819\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:37:43 INFO\u001b[0m Step 457/1000 | Loss: 2.4355\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:37:43 INFO\u001b[0m Step 457/1000 | Loss: 3.0153\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:37:43 INFO\u001b[0m Step 457/1000 | Loss: 2.8314\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:37:43 INFO\u001b[0m Step 457/1000 | Loss: 2.7155\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:37:43 INFO\u001b[0m Step 457/1000 | Loss: 2.4614\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:37:45 INFO\u001b[0m Step 458/1000 | Loss: 2.6860\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:37:45 INFO\u001b[0m Step 458/1000 | Loss: 3.1058\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:37:45 INFO\u001b[0m Step 458/1000 | Loss: 2.9383\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:37:45 INFO\u001b[0m Step 458/1000 | Loss: 2.8548\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:37:45 INFO\u001b[0m Step 458/1000 | Loss: 2.6160\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:37:45 INFO\u001b[0m Step 458/1000 | Loss: 3.2843\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:37:45 INFO\u001b[0m Step 458/1000 | Loss: 2.9243\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:37:46 INFO\u001b[0m Step 458/1000 | Loss: 2.9514\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:37:48 INFO\u001b[0m Step 459/1000 | Loss: 2.6772\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:37:48 INFO\u001b[0m Step 459/1000 | Loss: 2.3498\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:37:48 INFO\u001b[0m Step 459/1000 | Loss: 3.4930\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:37:48 INFO\u001b[0m Step 459/1000 | Loss: 2.9776\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:37:48 INFO\u001b[0m Step 459/1000 | Loss: 2.4445\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:37:48 INFO\u001b[0m Step 459/1000 | Loss: 2.2711\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:37:48 INFO\u001b[0m Step 459/1000 | Loss: 2.7669\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:37:48 INFO\u001b[0m Step 459/1000 | Loss: 2.9231\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:37:50 INFO\u001b[0m Step 460/1000 | Loss: 2.8258\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:37:50 INFO\u001b[0m Step 460/1000 | Loss: 3.0123\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:37:50 INFO\u001b[0m Step 460/1000 | Loss: 2.2329\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:37:50 INFO\u001b[0m Step 460/1000 | Loss: 2.5809\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:37:50 INFO\u001b[0m Step 460/1000 | Loss: 2.8804\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:37:50 INFO\u001b[0m Step 460/1000 | Loss: 2.8026\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:37:50 INFO\u001b[0m Step 460/1000 | Loss: 2.8700\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:37:50 INFO\u001b[0m Step 460/1000 | Loss: 2.9753\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:37:53 INFO\u001b[0m Step 461/1000 | Loss: 2.6373\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:37:53 INFO\u001b[0m Step 461/1000 | Loss: 2.8807\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:37:53 INFO\u001b[0m Step 461/1000 | Loss: 2.5210\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:37:53 INFO\u001b[0m Step 461/1000 | Loss: 2.5802\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:37:53 INFO\u001b[0m Step 461/1000 | Loss: 2.5984\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:37:53 INFO\u001b[0m Step 461/1000 | Loss: 2.7639\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:37:53 INFO\u001b[0m Step 461/1000 | Loss: 2.1999\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:37:53 INFO\u001b[0m Step 461/1000 | Loss: 2.8101\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:37:54 INFO\u001b[0m Step 462/1000 | Loss: 2.5378\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:37:54 INFO\u001b[0m Step 462/1000 | Loss: 3.0642\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:37:54 INFO\u001b[0m Step 462/1000 | Loss: 2.4472\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:37:54 INFO\u001b[0m Step 462/1000 | Loss: 2.4377\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:37:54 INFO\u001b[0m Step 462/1000 | Loss: 2.5729\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:37:54 INFO\u001b[0m Step 462/1000 | Loss: 3.0330\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:37:54 INFO\u001b[0m Step 462/1000 | Loss: 2.7666\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:37:54 INFO\u001b[0m Step 462/1000 | Loss: 2.7888\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:37:55 INFO\u001b[0m Step 463/1000 | Loss: 2.5895\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:37:55 INFO\u001b[0m Step 463/1000 | Loss: 2.7532\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:37:55 INFO\u001b[0m Step 463/1000 | Loss: 2.7765\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:37:55 INFO\u001b[0m Step 463/1000 | Loss: 2.3918\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:37:55 INFO\u001b[0m Step 463/1000 | Loss: 3.2789\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:37:55 INFO\u001b[0m Step 463/1000 | Loss: 2.4080\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:37:55 INFO\u001b[0m Step 463/1000 | Loss: 2.3214\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:37:55 INFO\u001b[0m Step 463/1000 | Loss: 2.4562\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:37:56 INFO\u001b[0m Step 464/1000 | Loss: 3.2276\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:37:56 INFO\u001b[0m Step 464/1000 | Loss: 2.1533\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:37:56 INFO\u001b[0m Step 464/1000 | Loss: 2.7806\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:37:56 INFO\u001b[0m Step 464/1000 | Loss: 2.9203\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:37:56 INFO\u001b[0m Step 464/1000 | Loss: 2.4231\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:37:56 INFO\u001b[0m Step 464/1000 | Loss: 2.3375\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:37:56 INFO\u001b[0m Step 464/1000 | Loss: 2.5953\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:37:56 INFO\u001b[0m Step 464/1000 | Loss: 2.8773\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:37:58 INFO\u001b[0m Step 465/1000 | Loss: 2.8292\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:37:58 INFO\u001b[0m Step 465/1000 | Loss: 2.8959\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:37:58 INFO\u001b[0m Step 465/1000 | Loss: 2.8689\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:37:58 INFO\u001b[0m Step 465/1000 | Loss: 2.5403\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:37:58 INFO\u001b[0m Step 465/1000 | Loss: 3.0330\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:37:58 INFO\u001b[0m Step 465/1000 | Loss: 2.9521\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:37:58 INFO\u001b[0m Step 465/1000 | Loss: 3.1916\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:37:58 INFO\u001b[0m Step 465/1000 | Loss: 2.8348\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:37:58 INFO\u001b[0m Step 466/1000 | Loss: 2.6637\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:37:58 INFO\u001b[0m Step 466/1000 | Loss: 2.8535\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:37:58 INFO\u001b[0m Step 466/1000 | Loss: 3.2457\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:37:58 INFO\u001b[0m Step 466/1000 | Loss: 3.0712\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:37:58 INFO\u001b[0m Step 466/1000 | Loss: 2.4377\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:37:58 INFO\u001b[0m Step 466/1000 | Loss: 2.8400\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:37:58 INFO\u001b[0m Step 466/1000 | Loss: 2.8362\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:37:58 INFO\u001b[0m Step 466/1000 | Loss: 3.2452\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:38:01 INFO\u001b[0m Step 467/1000 | Loss: 2.6996\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:38:01 INFO\u001b[0m Step 467/1000 | Loss: 2.5565\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:38:01 INFO\u001b[0m Step 467/1000 | Loss: 2.6951\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:38:01 INFO\u001b[0m Step 467/1000 | Loss: 2.2857\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:38:01 INFO\u001b[0m Step 467/1000 | Loss: 3.3106\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:38:01 INFO\u001b[0m Step 467/1000 | Loss: 2.6474\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:38:01 INFO\u001b[0m Step 467/1000 | Loss: 2.2606\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:38:01 INFO\u001b[0m Step 467/1000 | Loss: 3.0590\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:38:03 INFO\u001b[0m Step 468/1000 | Loss: 2.7860\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:38:03 INFO\u001b[0m Step 468/1000 | Loss: 2.9843\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:38:03 INFO\u001b[0m Step 468/1000 | Loss: 2.8685\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:38:03 INFO\u001b[0m Step 468/1000 | Loss: 2.6531\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:38:03 INFO\u001b[0m Step 468/1000 | Loss: 2.7076\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:38:03 INFO\u001b[0m Step 468/1000 | Loss: 3.2974\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:38:03 INFO\u001b[0m Step 468/1000 | Loss: 2.6577\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:38:03 INFO\u001b[0m Step 468/1000 | Loss: 3.1400\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:38:05 INFO\u001b[0m Step 469/1000 | Loss: 3.1883\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:38:05 INFO\u001b[0m Step 469/1000 | Loss: 2.6308\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:38:05 INFO\u001b[0m Step 469/1000 | Loss: 2.3048\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:38:05 INFO\u001b[0m Step 469/1000 | Loss: 2.9257\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:38:05 INFO\u001b[0m Step 469/1000 | Loss: 2.6425\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:38:05 INFO\u001b[0m Step 469/1000 | Loss: 2.6509\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:38:05 INFO\u001b[0m Step 469/1000 | Loss: 2.8607\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:38:05 INFO\u001b[0m Step 469/1000 | Loss: 2.5262\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:38:08 INFO\u001b[0m Step 470/1000 | Loss: 2.8307\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:38:08 INFO\u001b[0m Step 470/1000 | Loss: 2.5788\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:38:08 INFO\u001b[0m Step 470/1000 | Loss: 2.9697\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:38:08 INFO\u001b[0m Step 470/1000 | Loss: 2.9201\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:38:08 INFO\u001b[0m Step 470/1000 | Loss: 2.3330\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:38:08 INFO\u001b[0m Step 470/1000 | Loss: 2.7564\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:38:08 INFO\u001b[0m Step 470/1000 | Loss: 2.5369\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:38:08 INFO\u001b[0m Step 470/1000 | Loss: 3.0828\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:38:09 INFO\u001b[0m Step 471/1000 | Loss: 2.7476\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:38:09 INFO\u001b[0m Step 471/1000 | Loss: 2.7974\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:38:09 INFO\u001b[0m Step 471/1000 | Loss: 2.6504\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:38:09 INFO\u001b[0m Step 471/1000 | Loss: 3.2751\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:38:09 INFO\u001b[0m Step 471/1000 | Loss: 2.7702\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:38:09 INFO\u001b[0m Step 471/1000 | Loss: 2.6127\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:38:09 INFO\u001b[0m Step 471/1000 | Loss: 2.9384\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:38:09 INFO\u001b[0m Step 471/1000 | Loss: 2.6919\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:38:12 INFO\u001b[0m Step 472/1000 | Loss: 2.4155\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:38:12 INFO\u001b[0m Step 472/1000 | Loss: 2.8120\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:38:12 INFO\u001b[0m Step 472/1000 | Loss: 2.3530\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:38:12 INFO\u001b[0m Step 472/1000 | Loss: 2.9278\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:38:12 INFO\u001b[0m Step 472/1000 | Loss: 2.7653\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:38:12 INFO\u001b[0m Step 472/1000 | Loss: 2.6039\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:38:12 INFO\u001b[0m Step 472/1000 | Loss: 3.0836\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:38:12 INFO\u001b[0m Step 472/1000 | Loss: 2.5839\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:38:14 INFO\u001b[0m Step 473/1000 | Loss: 2.5885\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:38:14 INFO\u001b[0m Step 473/1000 | Loss: 2.8548\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:38:14 INFO\u001b[0m Step 473/1000 | Loss: 2.4166\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:38:14 INFO\u001b[0m Step 473/1000 | Loss: 2.4363\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:38:14 INFO\u001b[0m Step 473/1000 | Loss: 2.9021\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:38:14 INFO\u001b[0m Step 473/1000 | Loss: 2.5407\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:38:14 INFO\u001b[0m Step 473/1000 | Loss: 2.4128\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:38:14 INFO\u001b[0m Step 473/1000 | Loss: 2.4604\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:38:15 INFO\u001b[0m Step 474/1000 | Loss: 2.5888\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:38:15 INFO\u001b[0m Step 474/1000 | Loss: 2.7760\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:38:15 INFO\u001b[0m Step 474/1000 | Loss: 3.4774\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:38:15 INFO\u001b[0m Step 474/1000 | Loss: 2.0625\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:38:15 INFO\u001b[0m Step 474/1000 | Loss: 2.6580\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:38:15 INFO\u001b[0m Step 474/1000 | Loss: 2.5873\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:38:15 INFO\u001b[0m Step 474/1000 | Loss: 2.2382\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:38:15 INFO\u001b[0m Step 474/1000 | Loss: 2.7979\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:38:17 INFO\u001b[0m Step 475/1000 | Loss: 2.2702\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:38:17 INFO\u001b[0m Step 475/1000 | Loss: 2.8305\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:38:17 INFO\u001b[0m Step 475/1000 | Loss: 2.6105\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:38:17 INFO\u001b[0m Step 475/1000 | Loss: 2.0667\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:38:17 INFO\u001b[0m Step 475/1000 | Loss: 3.0648\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:38:17 INFO\u001b[0m Step 475/1000 | Loss: 2.5465\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:38:17 INFO\u001b[0m Step 475/1000 | Loss: 2.6573\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:38:17 INFO\u001b[0m Step 475/1000 | Loss: 2.9753\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:38:20 INFO\u001b[0m Step 476/1000 | Loss: 3.1062\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:38:20 INFO\u001b[0m Step 476/1000 | Loss: 2.4508\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:38:20 INFO\u001b[0m Step 476/1000 | Loss: 2.7819\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:38:20 INFO\u001b[0m Step 476/1000 | Loss: 2.5570\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:38:20 INFO\u001b[0m Step 476/1000 | Loss: 2.5754\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:38:20 INFO\u001b[0m Step 476/1000 | Loss: 2.2777\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:38:20 INFO\u001b[0m Step 476/1000 | Loss: 3.3472\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:38:20 INFO\u001b[0m Step 476/1000 | Loss: 3.0045\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:38:23 INFO\u001b[0m Step 477/1000 | Loss: 3.1525\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:38:23 INFO\u001b[0m Step 477/1000 | Loss: 2.1627\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:38:23 INFO\u001b[0m Step 477/1000 | Loss: 2.9410\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:38:23 INFO\u001b[0m Step 477/1000 | Loss: 2.3044\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:38:23 INFO\u001b[0m Step 477/1000 | Loss: 2.5263\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:38:23 INFO\u001b[0m Step 477/1000 | Loss: 2.4889\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:38:23 INFO\u001b[0m Step 477/1000 | Loss: 2.0987\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:38:23 INFO\u001b[0m Step 477/1000 | Loss: 2.3859\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:38:27 INFO\u001b[0m Step 478/1000 | Loss: 2.9633\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:38:27 INFO\u001b[0m Step 478/1000 | Loss: 2.6859\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:38:27 INFO\u001b[0m Step 478/1000 | Loss: 2.1048\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:38:27 INFO\u001b[0m Step 478/1000 | Loss: 3.1762\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:38:27 INFO\u001b[0m Step 478/1000 | Loss: 2.4523\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:38:27 INFO\u001b[0m Step 478/1000 | Loss: 2.9102\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:38:27 INFO\u001b[0m Step 478/1000 | Loss: 2.8157\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:38:27 INFO\u001b[0m Step 478/1000 | Loss: 2.3801\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:38:29 INFO\u001b[0m Step 479/1000 | Loss: 2.2338\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:38:29 INFO\u001b[0m Step 479/1000 | Loss: 2.3648\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:38:29 INFO\u001b[0m Step 479/1000 | Loss: 2.8729\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:38:29 INFO\u001b[0m Step 479/1000 | Loss: 2.4508\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:38:29 INFO\u001b[0m Step 479/1000 | Loss: 2.6236\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:38:29 INFO\u001b[0m Step 479/1000 | Loss: 2.6545\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:38:29 INFO\u001b[0m Step 479/1000 | Loss: 1.9219\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:38:29 INFO\u001b[0m Step 479/1000 | Loss: 2.4925\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:38:31 INFO\u001b[0m Step 480/1000 | Loss: 2.2609\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:38:31 INFO\u001b[0m Step 480/1000 | Loss: 2.7170\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:38:31 INFO\u001b[0m Step 480/1000 | Loss: 2.5615\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:38:31 INFO\u001b[0m Step 480/1000 | Loss: 2.9558\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:38:31 INFO\u001b[0m Step 480/1000 | Loss: 2.7875\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:38:31 INFO\u001b[0m Step 480/1000 | Loss: 2.3785\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:38:31 INFO\u001b[0m Step 480/1000 | Loss: 2.8771\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:38:31 INFO\u001b[0m Step 480/1000 | Loss: 2.4200\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:38:33 INFO\u001b[0m Step 481/1000 | Loss: 2.6667\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:38:33 INFO\u001b[0m Step 481/1000 | Loss: 3.2033\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:38:33 INFO\u001b[0m Step 481/1000 | Loss: 3.1458\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:38:33 INFO\u001b[0m Step 481/1000 | Loss: 2.5068\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:38:33 INFO\u001b[0m Step 481/1000 | Loss: 2.5384\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:38:33 INFO\u001b[0m Step 481/1000 | Loss: 2.4200\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:38:33 INFO\u001b[0m Step 481/1000 | Loss: 2.3661\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:38:33 INFO\u001b[0m Step 481/1000 | Loss: 2.8136\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:38:35 INFO\u001b[0m Step 482/1000 | Loss: 2.5650\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:38:35 INFO\u001b[0m Step 482/1000 | Loss: 3.2221\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:38:35 INFO\u001b[0m Step 482/1000 | Loss: 2.9313\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:38:35 INFO\u001b[0m Step 482/1000 | Loss: 2.9838\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:38:35 INFO\u001b[0m Step 482/1000 | Loss: 2.2801\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:38:35 INFO\u001b[0m Step 482/1000 | Loss: 2.0968\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:38:35 INFO\u001b[0m Step 482/1000 | Loss: 2.2020\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:38:35 INFO\u001b[0m Step 482/1000 | Loss: 2.4979\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:38:37 INFO\u001b[0m Step 483/1000 | Loss: 2.9546\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:38:37 INFO\u001b[0m Step 483/1000 | Loss: 2.1134\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:38:37 INFO\u001b[0m Step 483/1000 | Loss: 2.1623\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:38:37 INFO\u001b[0m Step 483/1000 | Loss: 1.9402\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:38:37 INFO\u001b[0m Step 483/1000 | Loss: 3.0314\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:38:37 INFO\u001b[0m Step 483/1000 | Loss: 2.4972\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:38:37 INFO\u001b[0m Step 483/1000 | Loss: 2.8709\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:38:37 INFO\u001b[0m Step 483/1000 | Loss: 2.9337\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:38:38 INFO\u001b[0m Step 484/1000 | Loss: 2.4738\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:38:38 INFO\u001b[0m Step 484/1000 | Loss: 2.4494\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:38:38 INFO\u001b[0m Step 484/1000 | Loss: 2.8879\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:38:38 INFO\u001b[0m Step 484/1000 | Loss: 2.8541\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:38:38 INFO\u001b[0m Step 484/1000 | Loss: 3.0620\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:38:38 INFO\u001b[0m Step 484/1000 | Loss: 2.6642\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:38:38 INFO\u001b[0m Step 484/1000 | Loss: 2.2385\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:38:38 INFO\u001b[0m Step 484/1000 | Loss: 2.6190\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:38:40 INFO\u001b[0m Step 485/1000 | Loss: 2.5871\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:38:40 INFO\u001b[0m Step 485/1000 | Loss: 2.8243\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:38:40 INFO\u001b[0m Step 485/1000 | Loss: 2.4696\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:38:40 INFO\u001b[0m Step 485/1000 | Loss: 2.7780\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:38:40 INFO\u001b[0m Step 485/1000 | Loss: 2.7504\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:38:40 INFO\u001b[0m Step 485/1000 | Loss: 2.9475\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:38:40 INFO\u001b[0m Step 485/1000 | Loss: 3.0852\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:38:40 INFO\u001b[0m Step 485/1000 | Loss: 2.2750\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:38:42 INFO\u001b[0m Step 486/1000 | Loss: 2.5609\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:38:42 INFO\u001b[0m Step 486/1000 | Loss: 2.8750\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:38:42 INFO\u001b[0m Step 486/1000 | Loss: 2.6888\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:38:42 INFO\u001b[0m Step 486/1000 | Loss: 2.8851\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:38:42 INFO\u001b[0m Step 486/1000 | Loss: 2.5709\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:38:42 INFO\u001b[0m Step 486/1000 | Loss: 3.2045\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:38:42 INFO\u001b[0m Step 486/1000 | Loss: 2.7022\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:38:42 INFO\u001b[0m Step 486/1000 | Loss: 2.5913\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:38:45 INFO\u001b[0m Step 487/1000 | Loss: 2.7724\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:38:45 INFO\u001b[0m Step 487/1000 | Loss: 2.9820\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:38:45 INFO\u001b[0m Step 487/1000 | Loss: 2.4028\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:38:45 INFO\u001b[0m Step 487/1000 | Loss: 2.5196\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:38:45 INFO\u001b[0m Step 487/1000 | Loss: 2.4923\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:38:45 INFO\u001b[0m Step 487/1000 | Loss: 2.7192\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:38:45 INFO\u001b[0m Step 487/1000 | Loss: 3.2199\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:38:45 INFO\u001b[0m Step 487/1000 | Loss: 3.3262\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:38:46 INFO\u001b[0m Step 488/1000 | Loss: 2.8497\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:38:46 INFO\u001b[0m Step 488/1000 | Loss: 2.7233\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:38:46 INFO\u001b[0m Step 488/1000 | Loss: 2.6359\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:38:46 INFO\u001b[0m Step 488/1000 | Loss: 2.9681\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:38:46 INFO\u001b[0m Step 488/1000 | Loss: 2.9333\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:38:46 INFO\u001b[0m Step 488/1000 | Loss: 3.1652\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:38:46 INFO\u001b[0m Step 488/1000 | Loss: 2.6827\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:38:46 INFO\u001b[0m Step 488/1000 | Loss: 2.5553\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:38:48 INFO\u001b[0m Step 489/1000 | Loss: 2.7735\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:38:48 INFO\u001b[0m Step 489/1000 | Loss: 2.4354\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:38:48 INFO\u001b[0m Step 489/1000 | Loss: 2.8605\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:38:48 INFO\u001b[0m Step 489/1000 | Loss: 2.4455\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:38:48 INFO\u001b[0m Step 489/1000 | Loss: 2.6788\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:38:48 INFO\u001b[0m Step 489/1000 | Loss: 2.8544\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:38:48 INFO\u001b[0m Step 489/1000 | Loss: 3.2062\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:38:48 INFO\u001b[0m Step 489/1000 | Loss: 2.1664\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:38:50 INFO\u001b[0m Step 490/1000 | Loss: 4.5842\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:38:50 INFO\u001b[0m Step 490/1000 | Loss: 2.3877\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:38:50 INFO\u001b[0m Step 490/1000 | Loss: 2.2616\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:38:50 INFO\u001b[0m Step 490/1000 | Loss: 2.6741\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:38:50 INFO\u001b[0m Step 490/1000 | Loss: 2.6481\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:38:50 INFO\u001b[0m Step 490/1000 | Loss: 3.3276\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:38:50 INFO\u001b[0m Step 490/1000 | Loss: 2.4099\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:38:50 INFO\u001b[0m Step 490/1000 | Loss: 3.1821\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:38:51 INFO\u001b[0m Step 491/1000 | Loss: 2.6353\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:38:51 INFO\u001b[0m Step 491/1000 | Loss: 2.4994\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:38:51 INFO\u001b[0m Step 491/1000 | Loss: 2.7469\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:38:51 INFO\u001b[0m Step 491/1000 | Loss: 2.6709\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:38:51 INFO\u001b[0m Step 491/1000 | Loss: 2.8609\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:38:51 INFO\u001b[0m Step 491/1000 | Loss: 2.6823\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:38:51 INFO\u001b[0m Step 491/1000 | Loss: 2.3031\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:38:51 INFO\u001b[0m Step 491/1000 | Loss: 2.7672\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:38:54 INFO\u001b[0m Step 492/1000 | Loss: 2.7667\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:38:54 INFO\u001b[0m Step 492/1000 | Loss: 2.1703\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:38:54 INFO\u001b[0m Step 492/1000 | Loss: 2.8690\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:38:54 INFO\u001b[0m Step 492/1000 | Loss: 3.5282\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:38:54 INFO\u001b[0m Step 492/1000 | Loss: 2.4742\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:38:54 INFO\u001b[0m Step 492/1000 | Loss: 2.6763\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:38:54 INFO\u001b[0m Step 492/1000 | Loss: 2.6928\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:38:54 INFO\u001b[0m Step 492/1000 | Loss: 2.9967\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:38:56 INFO\u001b[0m Step 493/1000 | Loss: 2.4205\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:38:56 INFO\u001b[0m Step 493/1000 | Loss: 2.6975\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:38:56 INFO\u001b[0m Step 493/1000 | Loss: 2.7141\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:38:56 INFO\u001b[0m Step 493/1000 | Loss: 2.8314\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:38:56 INFO\u001b[0m Step 493/1000 | Loss: 2.5953\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:38:56 INFO\u001b[0m Step 493/1000 | Loss: 2.8845\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:38:56 INFO\u001b[0m Step 493/1000 | Loss: 3.0295\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:38:56 INFO\u001b[0m Step 493/1000 | Loss: 2.3617\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:38:58 INFO\u001b[0m Step 494/1000 | Loss: 2.5102\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:38:58 INFO\u001b[0m Step 494/1000 | Loss: 2.4274\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:38:58 INFO\u001b[0m Step 494/1000 | Loss: 2.6913\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:38:58 INFO\u001b[0m Step 494/1000 | Loss: 2.0521\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:38:58 INFO\u001b[0m Step 494/1000 | Loss: 2.5608\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:38:58 INFO\u001b[0m Step 494/1000 | Loss: 2.9657\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:38:58 INFO\u001b[0m Step 494/1000 | Loss: 2.7529\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:38:58 INFO\u001b[0m Step 494/1000 | Loss: 3.0440\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:39:02 INFO\u001b[0m Step 495/1000 | Loss: 2.8285\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:39:02 INFO\u001b[0m Step 495/1000 | Loss: 2.7770\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:39:02 INFO\u001b[0m Step 495/1000 | Loss: 2.8461\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:39:02 INFO\u001b[0m Step 495/1000 | Loss: 2.5956\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:39:02 INFO\u001b[0m Step 495/1000 | Loss: 2.6171\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:39:02 INFO\u001b[0m Step 495/1000 | Loss: 2.5633\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:39:02 INFO\u001b[0m Step 495/1000 | Loss: 2.4559\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:39:02 INFO\u001b[0m Step 495/1000 | Loss: 2.9268\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:39:05 INFO\u001b[0m Step 496/1000 | Loss: 2.4601\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:39:05 INFO\u001b[0m Step 496/1000 | Loss: 2.3594\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:39:05 INFO\u001b[0m Step 496/1000 | Loss: 2.7805\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:39:05 INFO\u001b[0m Step 496/1000 | Loss: 2.5830\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:39:05 INFO\u001b[0m Step 496/1000 | Loss: 2.3817\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:39:05 INFO\u001b[0m Step 496/1000 | Loss: 2.7189\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:39:05 INFO\u001b[0m Step 496/1000 | Loss: 2.8922\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:39:05 INFO\u001b[0m Step 496/1000 | Loss: 1.9610\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:39:07 INFO\u001b[0m Step 497/1000 | Loss: 2.8156\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:39:07 INFO\u001b[0m Step 497/1000 | Loss: 3.3832\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:39:07 INFO\u001b[0m Step 497/1000 | Loss: 2.8465\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:39:07 INFO\u001b[0m Step 497/1000 | Loss: 2.2130\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:39:07 INFO\u001b[0m Step 497/1000 | Loss: 2.3907\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:39:07 INFO\u001b[0m Step 497/1000 | Loss: 2.5831\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:39:07 INFO\u001b[0m Step 497/1000 | Loss: 2.6552\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:39:07 INFO\u001b[0m Step 497/1000 | Loss: 2.5837\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:39:09 INFO\u001b[0m Step 498/1000 | Loss: 2.5325\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:39:09 INFO\u001b[0m Step 498/1000 | Loss: 2.8629\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:39:09 INFO\u001b[0m Step 498/1000 | Loss: 1.9404\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:39:09 INFO\u001b[0m Step 498/1000 | Loss: 2.5053\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:39:09 INFO\u001b[0m Step 498/1000 | Loss: 2.4792\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:39:09 INFO\u001b[0m Step 498/1000 | Loss: 2.7102\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:39:09 INFO\u001b[0m Step 498/1000 | Loss: 2.5984\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:39:09 INFO\u001b[0m Step 498/1000 | Loss: 2.3879\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:39:11 INFO\u001b[0m Step 499/1000 | Loss: 2.7941\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:39:11 INFO\u001b[0m Step 499/1000 | Loss: 2.6152\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:39:11 INFO\u001b[0m Step 499/1000 | Loss: 2.2911\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:39:11 INFO\u001b[0m Step 499/1000 | Loss: 2.3330\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:39:11 INFO\u001b[0m Step 499/1000 | Loss: 2.5035\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:39:11 INFO\u001b[0m Step 499/1000 | Loss: 2.9933\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:39:11 INFO\u001b[0m Step 499/1000 | Loss: 2.8530\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:39:11 INFO\u001b[0m Step 499/1000 | Loss: 2.5989\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:39:11 INFO\u001b[0m Saving the checkpoint (or staging if async is enabled).\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:39:11 INFO\u001b[0m Saving the checkpoint (or staging if async is enabled).\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:39:11 INFO\u001b[0m Saving the checkpoint (or staging if async is enabled).\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:39:11 INFO\u001b[0m Saving the checkpoint (or staging if async is enabled).\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:39:11 INFO\u001b[0m Saving the checkpoint (or staging if async is enabled).\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:39:11 INFO\u001b[0m Saving the checkpoint (or staging if async is enabled).\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:39:11 INFO\u001b[0m Saving the checkpoint (or staging if async is enabled).\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:39:11 INFO\u001b[0m Saving the checkpoint (or staging if async is enabled).\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:40:44 INFO\u001b[0m [GC] GC collection invoked by checkpointer. took 2.49 seconds\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:40:44 INFO\u001b[0m Finished saving the checkpoint (or staging if async is enabled)in 92.78 seconds.\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:40:44 INFO\u001b[0m [GC] GC collection invoked by checkpointer. took 2.50 seconds\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:40:44 INFO\u001b[0m Finished saving the checkpoint (or staging if async is enabled)in 92.79 seconds.\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:40:44 INFO\u001b[0m [GC] GC collection invoked by checkpointer. took 2.50 seconds\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:40:44 INFO\u001b[0m [GC] GC collection invoked by checkpointer. took 2.50 seconds\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:40:44 INFO\u001b[0m Finished saving the checkpoint (or staging if async is enabled)in 92.80 seconds.\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:40:44 INFO\u001b[0m Finished saving the checkpoint (or staging if async is enabled)in 92.80 seconds.\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:40:44 INFO\u001b[0m [GC] GC collection invoked by checkpointer. took 2.53 seconds\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:40:44 INFO\u001b[0m Finished saving the checkpoint (or staging if async is enabled)in 92.82 seconds.\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:40:44 INFO\u001b[0m [GC] GC collection invoked by checkpointer. took 2.53 seconds\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:40:44 INFO\u001b[0m Finished saving the checkpoint (or staging if async is enabled)in 92.83 seconds.\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:40:44 INFO\u001b[0m [GC] GC collection invoked by checkpointer. took 2.62 seconds\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:40:44 INFO\u001b[0m Finished saving the checkpoint (or staging if async is enabled)in 92.91 seconds.\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:40:44 INFO\u001b[0m [GC] GC collection invoked by checkpointer. took 2.70 seconds\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:40:44 INFO\u001b[0m Finished saving the checkpoint (or staging if async is enabled)in 93.00 seconds.\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:40:47 INFO\u001b[0m Step 500/1000 | Loss: 2.9440\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:40:47 INFO\u001b[0m Step 500/1000 | Loss: 2.7306\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:40:47 INFO\u001b[0m Step 500/1000 | Loss: 2.6224\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:40:47 INFO\u001b[0m Step 500/1000 | Loss: 3.0446\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:40:47 INFO\u001b[0m Step 500/1000 | Loss: 2.5858\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:40:47 INFO\u001b[0m Step 500/1000 | Loss: 2.6242\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:40:47 INFO\u001b[0m Step 500/1000 | Loss: 2.2440\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:40:47 INFO\u001b[0m Step 500/1000 | Loss: 2.5121\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:40:49 INFO\u001b[0m Step 501/1000 | Loss: 2.7963\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:40:49 INFO\u001b[0m Step 501/1000 | Loss: 2.5722\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:40:49 INFO\u001b[0m Step 501/1000 | Loss: 2.6778\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:40:49 INFO\u001b[0m Step 501/1000 | Loss: 2.1457\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:40:49 INFO\u001b[0m Step 501/1000 | Loss: 3.1274\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:40:49 INFO\u001b[0m Step 501/1000 | Loss: 2.9696\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:40:49 INFO\u001b[0m Step 501/1000 | Loss: 1.9289\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:40:49 INFO\u001b[0m Step 501/1000 | Loss: 2.6886\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:40:51 INFO\u001b[0m Step 502/1000 | Loss: 3.7937\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:40:51 INFO\u001b[0m Step 502/1000 | Loss: 2.7812\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:40:51 INFO\u001b[0m Step 502/1000 | Loss: 2.5192\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:40:51 INFO\u001b[0m Step 502/1000 | Loss: 2.1333\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:40:51 INFO\u001b[0m Step 502/1000 | Loss: 2.7933\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:40:51 INFO\u001b[0m Step 502/1000 | Loss: 2.5335\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:40:51 INFO\u001b[0m Step 502/1000 | Loss: 2.9547\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:40:51 INFO\u001b[0m Step 502/1000 | Loss: 2.8773\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:40:52 INFO\u001b[0m Step 503/1000 | Loss: 3.0718\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:40:52 INFO\u001b[0m Step 503/1000 | Loss: 2.3830\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:40:52 INFO\u001b[0m Step 503/1000 | Loss: 2.7314\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:40:52 INFO\u001b[0m Step 503/1000 | Loss: 2.3097\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:40:52 INFO\u001b[0m Step 503/1000 | Loss: 2.4918\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:40:52 INFO\u001b[0m Step 503/1000 | Loss: 2.8483\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:40:52 INFO\u001b[0m Step 503/1000 | Loss: 2.5756\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:40:52 INFO\u001b[0m Step 503/1000 | Loss: 2.4220\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:40:53 INFO\u001b[0m Step 504/1000 | Loss: 2.7220\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:40:53 INFO\u001b[0m Step 504/1000 | Loss: 2.4142\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:40:53 INFO\u001b[0m Step 504/1000 | Loss: 2.2296\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:40:53 INFO\u001b[0m Step 504/1000 | Loss: 2.6259\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:40:53 INFO\u001b[0m Step 504/1000 | Loss: 3.0848\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:40:53 INFO\u001b[0m Step 504/1000 | Loss: 2.5922\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:40:53 INFO\u001b[0m Step 504/1000 | Loss: 2.5533\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:40:53 INFO\u001b[0m Step 504/1000 | Loss: 2.2758\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:40:54 INFO\u001b[0m Step 505/1000 | Loss: 2.1899\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:40:54 INFO\u001b[0m Step 505/1000 | Loss: 2.5843\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:40:54 INFO\u001b[0m Step 505/1000 | Loss: 3.3031\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:40:54 INFO\u001b[0m Step 505/1000 | Loss: 2.7648\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:40:54 INFO\u001b[0m Step 505/1000 | Loss: 2.1094\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:40:54 INFO\u001b[0m Step 505/1000 | Loss: 2.7891\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:40:54 INFO\u001b[0m Step 505/1000 | Loss: 2.2176\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:40:54 INFO\u001b[0m Step 505/1000 | Loss: 2.4723\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:40:55 INFO\u001b[0m Step 506/1000 | Loss: 2.9701\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:40:55 INFO\u001b[0m Step 506/1000 | Loss: 2.6925\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:40:55 INFO\u001b[0m Step 506/1000 | Loss: 2.5428\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:40:55 INFO\u001b[0m Step 506/1000 | Loss: 2.7545\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:40:55 INFO\u001b[0m Step 506/1000 | Loss: 2.9567\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:40:55 INFO\u001b[0m Step 506/1000 | Loss: 2.9198\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:40:55 INFO\u001b[0m Step 506/1000 | Loss: 3.1694\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:40:55 INFO\u001b[0m Step 506/1000 | Loss: 2.8597\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:40:56 INFO\u001b[0m Step 507/1000 | Loss: 2.5858\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:40:56 INFO\u001b[0m Step 507/1000 | Loss: 2.5619\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:40:56 INFO\u001b[0m Step 507/1000 | Loss: 2.2369\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:40:56 INFO\u001b[0m Step 507/1000 | Loss: 2.0788\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:40:56 INFO\u001b[0m Step 507/1000 | Loss: 2.4718\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:40:56 INFO\u001b[0m Step 507/1000 | Loss: 2.3156\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:40:56 INFO\u001b[0m Step 507/1000 | Loss: 3.0290\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:40:56 INFO\u001b[0m Step 507/1000 | Loss: 2.7250\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:40:57 INFO\u001b[0m Step 508/1000 | Loss: 2.7865\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:40:57 INFO\u001b[0m Step 508/1000 | Loss: 2.4940\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:40:57 INFO\u001b[0m Step 508/1000 | Loss: 2.0412\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:40:57 INFO\u001b[0m Step 508/1000 | Loss: 2.5538\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:40:57 INFO\u001b[0m Step 508/1000 | Loss: 2.2591\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:40:57 INFO\u001b[0m Step 508/1000 | Loss: 2.5136\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:40:57 INFO\u001b[0m Step 508/1000 | Loss: 2.9595\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:40:57 INFO\u001b[0m Step 508/1000 | Loss: 2.3034\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:40:58 INFO\u001b[0m Step 509/1000 | Loss: 2.9670\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:40:58 INFO\u001b[0m Step 509/1000 | Loss: 3.2397\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:40:58 INFO\u001b[0m Step 509/1000 | Loss: 2.1344\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:40:58 INFO\u001b[0m Step 509/1000 | Loss: 2.7709\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:40:58 INFO\u001b[0m Step 509/1000 | Loss: 2.5374\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:40:58 INFO\u001b[0m Step 509/1000 | Loss: 2.2178\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:40:58 INFO\u001b[0m Step 509/1000 | Loss: 2.8039\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:40:58 INFO\u001b[0m Step 509/1000 | Loss: 2.3520\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:41:01 INFO\u001b[0m Step 510/1000 | Loss: 2.5803\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:41:01 INFO\u001b[0m Step 510/1000 | Loss: 3.5653\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:41:01 INFO\u001b[0m Step 510/1000 | Loss: 1.7533\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:41:01 INFO\u001b[0m Step 510/1000 | Loss: 2.3666\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:41:01 INFO\u001b[0m Step 510/1000 | Loss: 2.6635\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:41:01 INFO\u001b[0m Step 510/1000 | Loss: 2.3210\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:41:01 INFO\u001b[0m Step 510/1000 | Loss: 2.2324\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:41:01 INFO\u001b[0m Step 510/1000 | Loss: 2.8852\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:41:02 INFO\u001b[0m Step 511/1000 | Loss: 2.3916\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:41:02 INFO\u001b[0m Step 511/1000 | Loss: 2.7059\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:41:02 INFO\u001b[0m Step 511/1000 | Loss: 2.4717\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:41:02 INFO\u001b[0m Step 511/1000 | Loss: 2.6775\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:41:02 INFO\u001b[0m Step 511/1000 | Loss: 2.8741\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:41:02 INFO\u001b[0m Step 511/1000 | Loss: 2.9065\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:41:02 INFO\u001b[0m Step 511/1000 | Loss: 2.5565\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:41:02 INFO\u001b[0m Step 511/1000 | Loss: 2.2207\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:41:03 INFO\u001b[0m Step 512/1000 | Loss: 2.5667\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:41:03 INFO\u001b[0m Step 512/1000 | Loss: 2.3069\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:41:03 INFO\u001b[0m Step 512/1000 | Loss: 2.8085\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:41:03 INFO\u001b[0m Step 512/1000 | Loss: 3.1792\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:41:03 INFO\u001b[0m Step 512/1000 | Loss: 2.6900\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:41:03 INFO\u001b[0m Step 512/1000 | Loss: 2.4358\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:41:03 INFO\u001b[0m Step 512/1000 | Loss: 2.5529\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:41:03 INFO\u001b[0m Step 512/1000 | Loss: 3.0580\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:41:04 INFO\u001b[0m Step 513/1000 | Loss: 3.0135\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:41:04 INFO\u001b[0m Step 513/1000 | Loss: 3.1486\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:41:04 INFO\u001b[0m Step 513/1000 | Loss: 2.6048\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:41:04 INFO\u001b[0m Step 513/1000 | Loss: 2.1891\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:41:04 INFO\u001b[0m Step 513/1000 | Loss: 2.3426\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:41:04 INFO\u001b[0m Step 513/1000 | Loss: 2.4888\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:41:04 INFO\u001b[0m Step 513/1000 | Loss: 2.3486\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:41:04 INFO\u001b[0m Step 513/1000 | Loss: 2.4284\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:41:05 INFO\u001b[0m Step 514/1000 | Loss: 2.7598\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:41:05 INFO\u001b[0m Step 514/1000 | Loss: 2.7138\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:41:05 INFO\u001b[0m Step 514/1000 | Loss: 2.5080\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:41:05 INFO\u001b[0m Step 514/1000 | Loss: 3.0432\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:41:05 INFO\u001b[0m Step 514/1000 | Loss: 2.5516\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:41:05 INFO\u001b[0m Step 514/1000 | Loss: 2.5499\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:41:05 INFO\u001b[0m Step 514/1000 | Loss: 2.5005\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:41:05 INFO\u001b[0m Step 514/1000 | Loss: 2.9158\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:41:06 INFO\u001b[0m Step 515/1000 | Loss: 2.4104\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:41:06 INFO\u001b[0m Step 515/1000 | Loss: 2.8103\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:41:06 INFO\u001b[0m Step 515/1000 | Loss: 2.4328\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:41:06 INFO\u001b[0m Step 515/1000 | Loss: 3.0090\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:41:06 INFO\u001b[0m Step 515/1000 | Loss: 2.7636\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:41:06 INFO\u001b[0m Step 515/1000 | Loss: 2.6524\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:41:06 INFO\u001b[0m Step 515/1000 | Loss: 3.6398\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:41:06 INFO\u001b[0m Step 515/1000 | Loss: 2.8933\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:41:07 INFO\u001b[0m Step 516/1000 | Loss: 2.9991\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:41:07 INFO\u001b[0m Step 516/1000 | Loss: 2.5486\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:41:07 INFO\u001b[0m Step 516/1000 | Loss: 2.6051\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:41:07 INFO\u001b[0m Step 516/1000 | Loss: 3.2018\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:41:07 INFO\u001b[0m Step 516/1000 | Loss: 2.2170\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:41:07 INFO\u001b[0m Step 516/1000 | Loss: 2.5167\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:41:07 INFO\u001b[0m Step 516/1000 | Loss: 2.8521\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:41:07 INFO\u001b[0m Step 516/1000 | Loss: 2.8011\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:41:09 INFO\u001b[0m Step 517/1000 | Loss: 2.3813\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:41:09 INFO\u001b[0m Step 517/1000 | Loss: 2.5300\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:41:09 INFO\u001b[0m Step 517/1000 | Loss: 2.8699\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:41:09 INFO\u001b[0m Step 517/1000 | Loss: 2.8985\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:41:09 INFO\u001b[0m Step 517/1000 | Loss: 2.3876\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:41:09 INFO\u001b[0m Step 517/1000 | Loss: 2.6863\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:41:09 INFO\u001b[0m Step 517/1000 | Loss: 2.4866\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:41:09 INFO\u001b[0m Step 517/1000 | Loss: 2.4556\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:41:11 INFO\u001b[0m Step 518/1000 | Loss: 2.3310\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:41:11 INFO\u001b[0m Step 518/1000 | Loss: 2.5383\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:41:11 INFO\u001b[0m Step 518/1000 | Loss: 2.6672\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:41:11 INFO\u001b[0m Step 518/1000 | Loss: 2.7259\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:41:11 INFO\u001b[0m Step 518/1000 | Loss: 2.4447\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:41:11 INFO\u001b[0m Step 518/1000 | Loss: 2.3270\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:41:11 INFO\u001b[0m Step 518/1000 | Loss: 2.8799\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:41:11 INFO\u001b[0m Step 518/1000 | Loss: 2.2120\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:41:13 INFO\u001b[0m Step 519/1000 | Loss: 2.0195\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:41:13 INFO\u001b[0m Step 519/1000 | Loss: 2.5456\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:41:13 INFO\u001b[0m Step 519/1000 | Loss: 2.6467\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:41:13 INFO\u001b[0m Step 519/1000 | Loss: 2.5389\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:41:13 INFO\u001b[0m Step 519/1000 | Loss: 2.3027\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:41:13 INFO\u001b[0m Step 519/1000 | Loss: 2.2082\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:41:13 INFO\u001b[0m Step 519/1000 | Loss: 3.5163\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:41:13 INFO\u001b[0m Step 519/1000 | Loss: 3.3186\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:41:17 INFO\u001b[0m Step 520/1000 | Loss: 2.2979\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:41:17 INFO\u001b[0m Step 520/1000 | Loss: 2.4803\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:41:17 INFO\u001b[0m Step 520/1000 | Loss: 2.8514\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:41:17 INFO\u001b[0m Step 520/1000 | Loss: 2.8440\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:41:17 INFO\u001b[0m Step 520/1000 | Loss: 3.3724\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:41:17 INFO\u001b[0m Step 520/1000 | Loss: 2.1917\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:41:17 INFO\u001b[0m Step 520/1000 | Loss: 2.5553\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:41:17 INFO\u001b[0m Step 520/1000 | Loss: 2.8393\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:41:19 INFO\u001b[0m Step 521/1000 | Loss: 2.8207\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:41:19 INFO\u001b[0m Step 521/1000 | Loss: 2.7691\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:41:19 INFO\u001b[0m Step 521/1000 | Loss: 2.9994\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:41:19 INFO\u001b[0m Step 521/1000 | Loss: 2.4889\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:41:19 INFO\u001b[0m Step 521/1000 | Loss: 2.5595\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:41:19 INFO\u001b[0m Step 521/1000 | Loss: 2.8649\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:41:19 INFO\u001b[0m Step 521/1000 | Loss: 2.6513\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:41:19 INFO\u001b[0m Step 521/1000 | Loss: 2.4360\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:41:21 INFO\u001b[0m Step 522/1000 | Loss: 2.3105\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:41:21 INFO\u001b[0m Step 522/1000 | Loss: 2.6968\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:41:21 INFO\u001b[0m Step 522/1000 | Loss: 2.3632\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:41:21 INFO\u001b[0m Step 522/1000 | Loss: 2.8451\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:41:21 INFO\u001b[0m Step 522/1000 | Loss: 1.9320\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:41:21 INFO\u001b[0m Step 522/1000 | Loss: 2.2519\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:41:21 INFO\u001b[0m Step 522/1000 | Loss: 2.2479\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:41:21 INFO\u001b[0m Step 522/1000 | Loss: 2.7348\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:41:22 INFO\u001b[0m Step 523/1000 | Loss: 2.7129\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:41:22 INFO\u001b[0m Step 523/1000 | Loss: 2.2447\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:41:22 INFO\u001b[0m Step 523/1000 | Loss: 2.6499\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:41:22 INFO\u001b[0m Step 523/1000 | Loss: 2.5424\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:41:22 INFO\u001b[0m Step 523/1000 | Loss: 2.2775\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:41:22 INFO\u001b[0m Step 523/1000 | Loss: 2.3644\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:41:22 INFO\u001b[0m Step 523/1000 | Loss: 2.4595\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:41:22 INFO\u001b[0m Step 523/1000 | Loss: 2.4542\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:41:25 INFO\u001b[0m Step 524/1000 | Loss: 2.4478\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:41:25 INFO\u001b[0m Step 524/1000 | Loss: 2.9218\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:41:25 INFO\u001b[0m Step 524/1000 | Loss: 2.0485\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:41:25 INFO\u001b[0m Step 524/1000 | Loss: 2.7418\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:41:25 INFO\u001b[0m Step 524/1000 | Loss: 2.3835\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:41:25 INFO\u001b[0m Step 524/1000 | Loss: 2.4776\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:41:25 INFO\u001b[0m Step 524/1000 | Loss: 2.4987\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:41:25 INFO\u001b[0m Step 524/1000 | Loss: 2.9356\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:41:27 INFO\u001b[0m Step 525/1000 | Loss: 2.1574\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:41:27 INFO\u001b[0m Step 525/1000 | Loss: 2.0424\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:41:27 INFO\u001b[0m Step 525/1000 | Loss: 2.6200\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:41:27 INFO\u001b[0m Step 525/1000 | Loss: 2.2969\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:41:27 INFO\u001b[0m Step 525/1000 | Loss: 2.2499\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:41:27 INFO\u001b[0m Step 525/1000 | Loss: 2.2123\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:41:27 INFO\u001b[0m Step 525/1000 | Loss: 2.0766\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:41:27 INFO\u001b[0m Step 525/1000 | Loss: 2.0372\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:41:29 INFO\u001b[0m Step 526/1000 | Loss: 2.4785\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:41:29 INFO\u001b[0m Step 526/1000 | Loss: 2.6239\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:41:29 INFO\u001b[0m Step 526/1000 | Loss: 2.1526\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:41:29 INFO\u001b[0m Step 526/1000 | Loss: 2.6791\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:41:29 INFO\u001b[0m Step 526/1000 | Loss: 2.9962\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:41:29 INFO\u001b[0m Step 526/1000 | Loss: 2.6491\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:41:29 INFO\u001b[0m Step 526/1000 | Loss: 2.1972\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:41:29 INFO\u001b[0m Step 526/1000 | Loss: 2.2326\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:41:30 INFO\u001b[0m Step 527/1000 | Loss: 2.7790\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:41:30 INFO\u001b[0m Step 527/1000 | Loss: 2.5468\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:41:30 INFO\u001b[0m Step 527/1000 | Loss: 2.5409\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:41:30 INFO\u001b[0m Step 527/1000 | Loss: 2.0363\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:41:30 INFO\u001b[0m Step 527/1000 | Loss: 2.3941\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:41:30 INFO\u001b[0m Step 527/1000 | Loss: 3.2909\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:41:30 INFO\u001b[0m Step 527/1000 | Loss: 2.5967\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:41:30 INFO\u001b[0m Step 527/1000 | Loss: 2.2757\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:41:32 INFO\u001b[0m Step 528/1000 | Loss: 2.5878\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:41:32 INFO\u001b[0m Step 528/1000 | Loss: 2.2477\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:41:32 INFO\u001b[0m Step 528/1000 | Loss: 2.4335\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:41:32 INFO\u001b[0m Step 528/1000 | Loss: 2.6281\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:41:32 INFO\u001b[0m Step 528/1000 | Loss: 2.0817\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:41:32 INFO\u001b[0m Step 528/1000 | Loss: 2.2320\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:41:32 INFO\u001b[0m Step 528/1000 | Loss: 2.4898\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:41:32 INFO\u001b[0m Step 528/1000 | Loss: 2.4688\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:41:34 INFO\u001b[0m Step 529/1000 | Loss: 2.5347\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:41:34 INFO\u001b[0m Step 529/1000 | Loss: 2.0900\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:41:34 INFO\u001b[0m Step 529/1000 | Loss: 2.7506\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:41:34 INFO\u001b[0m Step 529/1000 | Loss: 2.9014\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:41:34 INFO\u001b[0m Step 529/1000 | Loss: 2.8386\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:41:34 INFO\u001b[0m Step 529/1000 | Loss: 2.5161\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:41:34 INFO\u001b[0m Step 529/1000 | Loss: 2.7854\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:41:34 INFO\u001b[0m Step 529/1000 | Loss: 2.4794\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:41:38 INFO\u001b[0m Step 530/1000 | Loss: 2.7307\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:41:38 INFO\u001b[0m Step 530/1000 | Loss: 3.6219\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:41:38 INFO\u001b[0m Step 530/1000 | Loss: 2.5726\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:41:38 INFO\u001b[0m Step 530/1000 | Loss: 2.4294\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:41:38 INFO\u001b[0m Step 530/1000 | Loss: 2.1652\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:41:38 INFO\u001b[0m Step 530/1000 | Loss: 2.1775\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:41:38 INFO\u001b[0m Step 530/1000 | Loss: 2.3248\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:41:38 INFO\u001b[0m Step 530/1000 | Loss: 2.7320\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:41:40 INFO\u001b[0m Step 531/1000 | Loss: 2.4471\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:41:40 INFO\u001b[0m Step 531/1000 | Loss: 2.3012\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:41:40 INFO\u001b[0m Step 531/1000 | Loss: 2.6651\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:41:40 INFO\u001b[0m Step 531/1000 | Loss: 2.1362\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:41:40 INFO\u001b[0m Step 531/1000 | Loss: 2.3991\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:41:40 INFO\u001b[0m Step 531/1000 | Loss: 2.1358\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:41:40 INFO\u001b[0m Step 531/1000 | Loss: 2.3128\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:41:40 INFO\u001b[0m Step 531/1000 | Loss: 2.3957\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:41:43 INFO\u001b[0m Step 532/1000 | Loss: 2.0445\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:41:43 INFO\u001b[0m Step 532/1000 | Loss: 2.3206\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:41:43 INFO\u001b[0m Step 532/1000 | Loss: 2.7808\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:41:43 INFO\u001b[0m Step 532/1000 | Loss: 2.6742\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:41:43 INFO\u001b[0m Step 532/1000 | Loss: 2.1400\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:41:43 INFO\u001b[0m Step 532/1000 | Loss: 2.3186\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:41:43 INFO\u001b[0m Step 532/1000 | Loss: 2.6354\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:41:43 INFO\u001b[0m Step 532/1000 | Loss: 2.6490\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:41:45 INFO\u001b[0m Step 533/1000 | Loss: 2.2543\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:41:45 INFO\u001b[0m Step 533/1000 | Loss: 2.9297\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:41:45 INFO\u001b[0m Step 533/1000 | Loss: 2.5079\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:41:45 INFO\u001b[0m Step 533/1000 | Loss: 2.4256\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:41:45 INFO\u001b[0m Step 533/1000 | Loss: 2.3694\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:41:45 INFO\u001b[0m Step 533/1000 | Loss: 2.2872\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:41:45 INFO\u001b[0m Step 533/1000 | Loss: 2.7284\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:41:45 INFO\u001b[0m Step 533/1000 | Loss: 2.3603\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:41:46 INFO\u001b[0m Step 534/1000 | Loss: 2.3421\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:41:46 INFO\u001b[0m Step 534/1000 | Loss: 2.9200\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:41:46 INFO\u001b[0m Step 534/1000 | Loss: 2.3601\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:41:46 INFO\u001b[0m Step 534/1000 | Loss: 2.3181\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:41:46 INFO\u001b[0m Step 534/1000 | Loss: 2.5755\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:41:46 INFO\u001b[0m Step 534/1000 | Loss: 2.0835\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:41:46 INFO\u001b[0m Step 534/1000 | Loss: 2.1082\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:41:46 INFO\u001b[0m Step 534/1000 | Loss: 2.7438\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:41:48 INFO\u001b[0m Step 535/1000 | Loss: 2.4458\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:41:48 INFO\u001b[0m Step 535/1000 | Loss: 2.2256\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:41:48 INFO\u001b[0m Step 535/1000 | Loss: 2.4752\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:41:48 INFO\u001b[0m Step 535/1000 | Loss: 2.5105\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:41:48 INFO\u001b[0m Step 535/1000 | Loss: 2.2860\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:41:48 INFO\u001b[0m Step 535/1000 | Loss: 2.1376\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:41:48 INFO\u001b[0m Step 535/1000 | Loss: 2.4929\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:41:48 INFO\u001b[0m Step 535/1000 | Loss: 2.2143\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:41:49 INFO\u001b[0m Step 536/1000 | Loss: 3.7833\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:41:49 INFO\u001b[0m Step 536/1000 | Loss: 2.6800\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:41:49 INFO\u001b[0m Step 536/1000 | Loss: 3.0503\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:41:49 INFO\u001b[0m Step 536/1000 | Loss: 2.1902\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:41:49 INFO\u001b[0m Step 536/1000 | Loss: 2.2875\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:41:49 INFO\u001b[0m Step 536/1000 | Loss: 2.7374\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:41:49 INFO\u001b[0m Step 536/1000 | Loss: 2.5212\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:41:49 INFO\u001b[0m Step 536/1000 | Loss: 2.7322\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:41:52 INFO\u001b[0m Step 537/1000 | Loss: 2.4440\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:41:52 INFO\u001b[0m Step 537/1000 | Loss: 2.8079\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:41:52 INFO\u001b[0m Step 537/1000 | Loss: 2.4405\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:41:52 INFO\u001b[0m Step 537/1000 | Loss: 2.7035\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:41:52 INFO\u001b[0m Step 537/1000 | Loss: 2.5971\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:41:52 INFO\u001b[0m Step 537/1000 | Loss: 2.3848\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:41:52 INFO\u001b[0m Step 537/1000 | Loss: 2.9634\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:41:52 INFO\u001b[0m Step 537/1000 | Loss: 2.2457\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:41:54 INFO\u001b[0m Step 538/1000 | Loss: 2.5509\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:41:54 INFO\u001b[0m Step 538/1000 | Loss: 2.3623\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:41:54 INFO\u001b[0m Step 538/1000 | Loss: 2.2275\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:41:54 INFO\u001b[0m Step 538/1000 | Loss: 2.3106\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:41:54 INFO\u001b[0m Step 538/1000 | Loss: 2.6036\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:41:54 INFO\u001b[0m Step 538/1000 | Loss: 2.4270\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:41:54 INFO\u001b[0m Step 538/1000 | Loss: 2.2145\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:41:54 INFO\u001b[0m Step 538/1000 | Loss: 2.1663\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:41:57 INFO\u001b[0m Step 539/1000 | Loss: 2.8914\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:41:57 INFO\u001b[0m Step 539/1000 | Loss: 2.5089\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:41:57 INFO\u001b[0m Step 539/1000 | Loss: 2.6908\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:41:57 INFO\u001b[0m Step 539/1000 | Loss: 2.1379\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:41:57 INFO\u001b[0m Step 539/1000 | Loss: 2.5008\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:41:57 INFO\u001b[0m Step 539/1000 | Loss: 2.4800\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:41:57 INFO\u001b[0m Step 539/1000 | Loss: 2.2467\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:41:57 INFO\u001b[0m Step 539/1000 | Loss: 2.7532\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:42:00 INFO\u001b[0m Step 540/1000 | Loss: 2.8669\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:42:00 INFO\u001b[0m Step 540/1000 | Loss: 2.7585\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:42:00 INFO\u001b[0m Step 540/1000 | Loss: 2.3109\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:42:00 INFO\u001b[0m Step 540/1000 | Loss: 2.4380\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:42:00 INFO\u001b[0m Step 540/1000 | Loss: 2.0287\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:42:00 INFO\u001b[0m Step 540/1000 | Loss: 2.6130\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:42:00 INFO\u001b[0m Step 540/1000 | Loss: 2.3507\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:42:00 INFO\u001b[0m Step 540/1000 | Loss: 3.0506\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:42:01 INFO\u001b[0m Step 541/1000 | Loss: 2.9378\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:42:01 INFO\u001b[0m Step 541/1000 | Loss: 2.5048\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:42:01 INFO\u001b[0m Step 541/1000 | Loss: 2.5701\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:42:01 INFO\u001b[0m Step 541/1000 | Loss: 2.7126\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:42:01 INFO\u001b[0m Step 541/1000 | Loss: 2.2882\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:42:01 INFO\u001b[0m Step 541/1000 | Loss: 2.9715\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:42:01 INFO\u001b[0m Step 541/1000 | Loss: 2.6911\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:42:01 INFO\u001b[0m Step 541/1000 | Loss: 2.4607\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:42:02 INFO\u001b[0m Step 542/1000 | Loss: 2.2706\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:42:02 INFO\u001b[0m Step 542/1000 | Loss: 2.9689\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:42:02 INFO\u001b[0m Step 542/1000 | Loss: 2.3154\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:42:02 INFO\u001b[0m Step 542/1000 | Loss: 2.5759\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:42:02 INFO\u001b[0m Step 542/1000 | Loss: 2.4157\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:42:02 INFO\u001b[0m Step 542/1000 | Loss: 2.4719\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:42:02 INFO\u001b[0m Step 542/1000 | Loss: 2.5441\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:42:02 INFO\u001b[0m Step 542/1000 | Loss: 2.8649\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:42:05 INFO\u001b[0m Step 543/1000 | Loss: 2.0978\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:42:05 INFO\u001b[0m Step 543/1000 | Loss: 2.1716\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:42:05 INFO\u001b[0m Step 543/1000 | Loss: 2.6231\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:42:05 INFO\u001b[0m Step 543/1000 | Loss: 2.1465\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:42:05 INFO\u001b[0m Step 543/1000 | Loss: 2.3076\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:42:05 INFO\u001b[0m Step 543/1000 | Loss: 2.8341\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:42:05 INFO\u001b[0m Step 543/1000 | Loss: 2.3343\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:42:05 INFO\u001b[0m Step 543/1000 | Loss: 2.7685\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:42:08 INFO\u001b[0m Step 544/1000 | Loss: 2.5996\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:42:08 INFO\u001b[0m Step 544/1000 | Loss: 2.8646\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:42:08 INFO\u001b[0m Step 544/1000 | Loss: 2.0432\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:42:08 INFO\u001b[0m Step 544/1000 | Loss: 2.7737\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:42:08 INFO\u001b[0m Step 544/1000 | Loss: 2.8814\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:42:08 INFO\u001b[0m Step 544/1000 | Loss: 3.2762\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:42:08 INFO\u001b[0m Step 544/1000 | Loss: 3.3450\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:42:08 INFO\u001b[0m Step 544/1000 | Loss: 2.6503\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:42:09 INFO\u001b[0m Step 545/1000 | Loss: 2.4389\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:42:09 INFO\u001b[0m Step 545/1000 | Loss: 2.3888\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:42:09 INFO\u001b[0m Step 545/1000 | Loss: 2.5009\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:42:09 INFO\u001b[0m Step 545/1000 | Loss: 2.9993\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:42:09 INFO\u001b[0m Step 545/1000 | Loss: 2.5425\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:42:09 INFO\u001b[0m Step 545/1000 | Loss: 2.7908\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:42:09 INFO\u001b[0m Step 545/1000 | Loss: 2.4159\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:42:09 INFO\u001b[0m Step 545/1000 | Loss: 2.3868\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:42:11 INFO\u001b[0m Step 546/1000 | Loss: 2.3489\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:42:11 INFO\u001b[0m Step 546/1000 | Loss: 2.9902\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:42:11 INFO\u001b[0m Step 546/1000 | Loss: 2.4384\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:42:11 INFO\u001b[0m Step 546/1000 | Loss: 2.7093\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:42:11 INFO\u001b[0m Step 546/1000 | Loss: 2.7254\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:42:11 INFO\u001b[0m Step 546/1000 | Loss: 2.4661\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:42:11 INFO\u001b[0m Step 546/1000 | Loss: 2.7564\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:42:11 INFO\u001b[0m Step 546/1000 | Loss: 2.1778\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:42:13 INFO\u001b[0m Step 547/1000 | Loss: 2.8655\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:42:13 INFO\u001b[0m Step 547/1000 | Loss: 2.7016\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:42:13 INFO\u001b[0m Step 547/1000 | Loss: 2.9854\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:42:13 INFO\u001b[0m Step 547/1000 | Loss: 2.5021\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:42:13 INFO\u001b[0m Step 547/1000 | Loss: 2.6037\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:42:13 INFO\u001b[0m Step 547/1000 | Loss: 2.6640\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:42:13 INFO\u001b[0m Step 547/1000 | Loss: 2.1901\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:42:13 INFO\u001b[0m Step 547/1000 | Loss: 2.7867\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:42:14 INFO\u001b[0m Step 548/1000 | Loss: 2.6073\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:42:14 INFO\u001b[0m Step 548/1000 | Loss: 2.6852\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:42:14 INFO\u001b[0m Step 548/1000 | Loss: 2.4943\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:42:14 INFO\u001b[0m Step 548/1000 | Loss: 2.4269\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:42:14 INFO\u001b[0m Step 548/1000 | Loss: 2.6397\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:42:14 INFO\u001b[0m Step 548/1000 | Loss: 2.0088\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:42:14 INFO\u001b[0m Step 548/1000 | Loss: 2.0077\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:42:14 INFO\u001b[0m Step 548/1000 | Loss: 2.4625\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:42:15 INFO\u001b[0m Step 549/1000 | Loss: 2.4601\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:42:15 INFO\u001b[0m Step 549/1000 | Loss: 3.1029\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:42:15 INFO\u001b[0m Step 549/1000 | Loss: 2.3165\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:42:15 INFO\u001b[0m Step 549/1000 | Loss: 2.6675\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:42:15 INFO\u001b[0m Step 549/1000 | Loss: 2.3572\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:42:15 INFO\u001b[0m Step 549/1000 | Loss: 2.5848\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:42:15 INFO\u001b[0m Step 549/1000 | Loss: 2.6625\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:42:15 INFO\u001b[0m Step 549/1000 | Loss: 2.9967\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:42:17 INFO\u001b[0m Step 550/1000 | Loss: 2.0517\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:42:17 INFO\u001b[0m Step 550/1000 | Loss: 2.4669\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:42:17 INFO\u001b[0m Step 550/1000 | Loss: 4.7715\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:42:17 INFO\u001b[0m Step 550/1000 | Loss: 1.9490\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:42:17 INFO\u001b[0m Step 550/1000 | Loss: 1.9703\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:42:17 INFO\u001b[0m Step 550/1000 | Loss: 2.3609\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:42:17 INFO\u001b[0m Step 550/1000 | Loss: 2.5982\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:42:17 INFO\u001b[0m Step 550/1000 | Loss: 2.7988\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:42:19 INFO\u001b[0m Step 551/1000 | Loss: 2.6071\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:42:19 INFO\u001b[0m Step 551/1000 | Loss: 2.3732\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:42:19 INFO\u001b[0m Step 551/1000 | Loss: 2.5746\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:42:19 INFO\u001b[0m Step 551/1000 | Loss: 2.3015\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:42:19 INFO\u001b[0m Step 551/1000 | Loss: 2.7271\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:42:19 INFO\u001b[0m Step 551/1000 | Loss: 2.7851\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:42:19 INFO\u001b[0m Step 551/1000 | Loss: 2.4604\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:42:19 INFO\u001b[0m Step 551/1000 | Loss: 2.3891\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:42:21 INFO\u001b[0m Step 552/1000 | Loss: 2.9785\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:42:21 INFO\u001b[0m Step 552/1000 | Loss: 2.3054\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:42:21 INFO\u001b[0m Step 552/1000 | Loss: 3.2839\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:42:21 INFO\u001b[0m Step 552/1000 | Loss: 2.1590\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:42:21 INFO\u001b[0m Step 552/1000 | Loss: 2.8865\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:42:21 INFO\u001b[0m Step 552/1000 | Loss: 2.5177\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:42:21 INFO\u001b[0m Step 552/1000 | Loss: 2.9662\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:42:21 INFO\u001b[0m Step 552/1000 | Loss: 2.6677\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:42:23 INFO\u001b[0m Step 553/1000 | Loss: 2.7952\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:42:23 INFO\u001b[0m Step 553/1000 | Loss: 2.3978\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:42:23 INFO\u001b[0m Step 553/1000 | Loss: 2.5029\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:42:23 INFO\u001b[0m Step 553/1000 | Loss: 2.5418\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:42:23 INFO\u001b[0m Step 553/1000 | Loss: 2.1572\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:42:23 INFO\u001b[0m Step 553/1000 | Loss: 2.9823\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:42:23 INFO\u001b[0m Step 553/1000 | Loss: 2.2594\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:42:23 INFO\u001b[0m Step 553/1000 | Loss: 2.4212\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:42:27 INFO\u001b[0m Step 554/1000 | Loss: 2.4728\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:42:27 INFO\u001b[0m Step 554/1000 | Loss: 2.5430\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:42:27 INFO\u001b[0m Step 554/1000 | Loss: 2.7896\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:42:27 INFO\u001b[0m Step 554/1000 | Loss: 2.6551\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:42:27 INFO\u001b[0m Step 554/1000 | Loss: 2.4760\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:42:27 INFO\u001b[0m Step 554/1000 | Loss: 2.4203\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:42:27 INFO\u001b[0m Step 554/1000 | Loss: 2.6220\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:42:27 INFO\u001b[0m Step 554/1000 | Loss: 2.5722\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:42:29 INFO\u001b[0m Step 555/1000 | Loss: 2.1216\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:42:29 INFO\u001b[0m Step 555/1000 | Loss: 2.6592\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:42:29 INFO\u001b[0m Step 555/1000 | Loss: 2.4343\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:42:29 INFO\u001b[0m Step 555/1000 | Loss: 2.1363\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:42:29 INFO\u001b[0m Step 555/1000 | Loss: 2.9301\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:42:29 INFO\u001b[0m Step 555/1000 | Loss: 2.4795\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:42:29 INFO\u001b[0m Step 555/1000 | Loss: 2.2125\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:42:29 INFO\u001b[0m Step 555/1000 | Loss: 2.8355\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:42:32 INFO\u001b[0m Step 556/1000 | Loss: 2.5029\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:42:32 INFO\u001b[0m Step 556/1000 | Loss: 2.6393\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:42:32 INFO\u001b[0m Step 556/1000 | Loss: 2.7435\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:42:32 INFO\u001b[0m Step 556/1000 | Loss: 2.2711\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:42:32 INFO\u001b[0m Step 556/1000 | Loss: 2.4730\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:42:32 INFO\u001b[0m Step 556/1000 | Loss: 2.7740\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:42:32 INFO\u001b[0m Step 556/1000 | Loss: 2.3004\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:42:32 INFO\u001b[0m Step 556/1000 | Loss: 2.6693\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:42:33 INFO\u001b[0m Step 557/1000 | Loss: 2.8543\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:42:33 INFO\u001b[0m Step 557/1000 | Loss: 2.5564\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:42:33 INFO\u001b[0m Step 557/1000 | Loss: 2.7254\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:42:33 INFO\u001b[0m Step 557/1000 | Loss: 2.4876\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:42:33 INFO\u001b[0m Step 557/1000 | Loss: 2.0870\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:42:33 INFO\u001b[0m Step 557/1000 | Loss: 2.2354\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:42:33 INFO\u001b[0m Step 557/1000 | Loss: 2.4722\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:42:33 INFO\u001b[0m Step 557/1000 | Loss: 2.4657\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:42:35 INFO\u001b[0m Step 558/1000 | Loss: 2.6178\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:42:35 INFO\u001b[0m Step 558/1000 | Loss: 2.6044\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:42:35 INFO\u001b[0m Step 558/1000 | Loss: 2.3406\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:42:35 INFO\u001b[0m Step 558/1000 | Loss: 2.7920\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:42:35 INFO\u001b[0m Step 558/1000 | Loss: 2.6975\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:42:35 INFO\u001b[0m Step 558/1000 | Loss: 2.7432\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:42:35 INFO\u001b[0m Step 558/1000 | Loss: 2.7947\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:42:35 INFO\u001b[0m Step 558/1000 | Loss: 2.5444\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:42:37 INFO\u001b[0m Step 559/1000 | Loss: 3.1656\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:42:37 INFO\u001b[0m Step 559/1000 | Loss: 2.4594\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:42:37 INFO\u001b[0m Step 559/1000 | Loss: 2.0157\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:42:37 INFO\u001b[0m Step 559/1000 | Loss: 2.5750\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:42:38 INFO\u001b[0m Step 559/1000 | Loss: 2.4331\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:42:38 INFO\u001b[0m Step 559/1000 | Loss: 2.6169\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:42:38 INFO\u001b[0m Step 559/1000 | Loss: 2.5581\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:42:38 INFO\u001b[0m Step 559/1000 | Loss: 2.1415\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:42:40 INFO\u001b[0m Step 560/1000 | Loss: 2.3983\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:42:40 INFO\u001b[0m Step 560/1000 | Loss: 3.2555\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:42:40 INFO\u001b[0m Step 560/1000 | Loss: 2.5195\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:42:40 INFO\u001b[0m Step 560/1000 | Loss: 2.6799\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:42:40 INFO\u001b[0m Step 560/1000 | Loss: 2.8005\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:42:40 INFO\u001b[0m Step 560/1000 | Loss: 2.4635\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:42:40 INFO\u001b[0m Step 560/1000 | Loss: 2.2002\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:42:40 INFO\u001b[0m Step 560/1000 | Loss: 2.4699\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:42:42 INFO\u001b[0m Step 561/1000 | Loss: 2.3674\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:42:42 INFO\u001b[0m Step 561/1000 | Loss: 2.3599\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:42:42 INFO\u001b[0m Step 561/1000 | Loss: 2.2823\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:42:42 INFO\u001b[0m Step 561/1000 | Loss: 2.3437\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:42:42 INFO\u001b[0m Step 561/1000 | Loss: 2.3502\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:42:42 INFO\u001b[0m Step 561/1000 | Loss: 2.5548\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:42:42 INFO\u001b[0m Step 561/1000 | Loss: 2.4794\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:42:42 INFO\u001b[0m Step 561/1000 | Loss: 2.6269\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:42:45 INFO\u001b[0m Step 562/1000 | Loss: 2.5139\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:42:45 INFO\u001b[0m Step 562/1000 | Loss: 2.2397\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:42:45 INFO\u001b[0m Step 562/1000 | Loss: 2.4543\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:42:45 INFO\u001b[0m Step 562/1000 | Loss: 2.5901\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:42:45 INFO\u001b[0m Step 562/1000 | Loss: 2.6873\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:42:45 INFO\u001b[0m Step 562/1000 | Loss: 2.7568\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:42:45 INFO\u001b[0m Step 562/1000 | Loss: 2.5520\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:42:45 INFO\u001b[0m Step 562/1000 | Loss: 2.0240\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:42:47 INFO\u001b[0m Step 563/1000 | Loss: 2.6380\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:42:47 INFO\u001b[0m Step 563/1000 | Loss: 2.8471\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:42:47 INFO\u001b[0m Step 563/1000 | Loss: 2.3391\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:42:47 INFO\u001b[0m Step 563/1000 | Loss: 2.5614\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:42:47 INFO\u001b[0m Step 563/1000 | Loss: 2.5774\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:42:47 INFO\u001b[0m Step 563/1000 | Loss: 2.2013\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:42:47 INFO\u001b[0m Step 563/1000 | Loss: 2.8282\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:42:47 INFO\u001b[0m Step 563/1000 | Loss: 2.8849\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:42:50 INFO\u001b[0m Step 564/1000 | Loss: 2.6806\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:42:50 INFO\u001b[0m Step 564/1000 | Loss: 3.0912\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:42:50 INFO\u001b[0m Step 564/1000 | Loss: 2.6381\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:42:50 INFO\u001b[0m Step 564/1000 | Loss: 2.5035\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:42:50 INFO\u001b[0m Step 564/1000 | Loss: 2.3366\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:42:50 INFO\u001b[0m Step 564/1000 | Loss: 2.7275\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:42:50 INFO\u001b[0m Step 564/1000 | Loss: 2.4825\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:42:50 INFO\u001b[0m Step 564/1000 | Loss: 2.8163\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:42:52 INFO\u001b[0m Step 565/1000 | Loss: 2.7936\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:42:52 INFO\u001b[0m Step 565/1000 | Loss: 2.4277\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:42:52 INFO\u001b[0m Step 565/1000 | Loss: 2.6214\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:42:52 INFO\u001b[0m Step 565/1000 | Loss: 2.7759\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:42:52 INFO\u001b[0m Step 565/1000 | Loss: 2.4875\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:42:52 INFO\u001b[0m Step 565/1000 | Loss: 3.1123\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:42:52 INFO\u001b[0m Step 565/1000 | Loss: 3.3360\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:42:52 INFO\u001b[0m Step 565/1000 | Loss: 2.6882\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:42:55 INFO\u001b[0m Step 566/1000 | Loss: 2.6333\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:42:55 INFO\u001b[0m Step 566/1000 | Loss: 2.1768\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:42:55 INFO\u001b[0m Step 566/1000 | Loss: 2.5725\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:42:55 INFO\u001b[0m Step 566/1000 | Loss: 2.2680\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:42:55 INFO\u001b[0m Step 566/1000 | Loss: 3.1304\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:42:55 INFO\u001b[0m Step 566/1000 | Loss: 2.5300\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:42:55 INFO\u001b[0m Step 566/1000 | Loss: 2.8352\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:42:55 INFO\u001b[0m Step 566/1000 | Loss: 2.2495\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:42:58 INFO\u001b[0m Step 567/1000 | Loss: 2.5194\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:42:58 INFO\u001b[0m Step 567/1000 | Loss: 2.6335\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:42:58 INFO\u001b[0m Step 567/1000 | Loss: 2.1041\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:42:58 INFO\u001b[0m Step 567/1000 | Loss: 2.8456\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:42:58 INFO\u001b[0m Step 567/1000 | Loss: 2.7962\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:42:58 INFO\u001b[0m Step 567/1000 | Loss: 2.2903\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:42:58 INFO\u001b[0m Step 567/1000 | Loss: 2.4099\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:42:58 INFO\u001b[0m Step 567/1000 | Loss: 2.5732\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:43:00 INFO\u001b[0m Step 568/1000 | Loss: 2.2237\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:43:00 INFO\u001b[0m Step 568/1000 | Loss: 2.1719\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:43:00 INFO\u001b[0m Step 568/1000 | Loss: 2.6115\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:43:00 INFO\u001b[0m Step 568/1000 | Loss: 2.3702\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:43:00 INFO\u001b[0m Step 568/1000 | Loss: 2.3190\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:43:00 INFO\u001b[0m Step 568/1000 | Loss: 3.3982\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:43:00 INFO\u001b[0m Step 568/1000 | Loss: 2.3576\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:43:00 INFO\u001b[0m Step 568/1000 | Loss: 2.2759\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:43:03 INFO\u001b[0m Step 569/1000 | Loss: 2.5330\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:43:03 INFO\u001b[0m Step 569/1000 | Loss: 2.7797\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:43:03 INFO\u001b[0m Step 569/1000 | Loss: 2.6062\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:43:03 INFO\u001b[0m Step 569/1000 | Loss: 2.5060\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:43:03 INFO\u001b[0m Step 569/1000 | Loss: 2.3705\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:43:03 INFO\u001b[0m Step 569/1000 | Loss: 2.3014\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:43:03 INFO\u001b[0m Step 569/1000 | Loss: 2.5381\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:43:03 INFO\u001b[0m Step 569/1000 | Loss: 2.5964\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:43:07 INFO\u001b[0m Step 570/1000 | Loss: 2.0323\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:43:07 INFO\u001b[0m Step 570/1000 | Loss: 2.6472\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:43:07 INFO\u001b[0m Step 570/1000 | Loss: 2.7719\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:43:07 INFO\u001b[0m Step 570/1000 | Loss: 2.7762\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:43:07 INFO\u001b[0m Step 570/1000 | Loss: 3.8634\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:43:07 INFO\u001b[0m Step 570/1000 | Loss: 2.2190\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:43:07 INFO\u001b[0m Step 570/1000 | Loss: 2.2179\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:43:07 INFO\u001b[0m Step 570/1000 | Loss: 2.3965\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:43:10 INFO\u001b[0m Step 571/1000 | Loss: 2.3437\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:43:10 INFO\u001b[0m Step 571/1000 | Loss: 2.6946\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:43:10 INFO\u001b[0m Step 571/1000 | Loss: 3.0547\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:43:10 INFO\u001b[0m Step 571/1000 | Loss: 2.9755\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:43:10 INFO\u001b[0m Step 571/1000 | Loss: 2.7082\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:43:10 INFO\u001b[0m Step 571/1000 | Loss: 1.9660\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:43:10 INFO\u001b[0m Step 571/1000 | Loss: 2.8690\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:43:10 INFO\u001b[0m Step 571/1000 | Loss: 2.3690\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:43:12 INFO\u001b[0m Step 572/1000 | Loss: 2.4379\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:43:12 INFO\u001b[0m Step 572/1000 | Loss: 2.7318\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:43:12 INFO\u001b[0m Step 572/1000 | Loss: 2.8350\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:43:12 INFO\u001b[0m Step 572/1000 | Loss: 2.1093\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:43:12 INFO\u001b[0m Step 572/1000 | Loss: 2.2341\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:43:12 INFO\u001b[0m Step 572/1000 | Loss: 2.4194\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:43:12 INFO\u001b[0m Step 572/1000 | Loss: 3.4872\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:43:12 INFO\u001b[0m Step 572/1000 | Loss: 2.0696\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:43:14 INFO\u001b[0m Step 573/1000 | Loss: 2.3332\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:43:14 INFO\u001b[0m Step 573/1000 | Loss: 2.0510\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:43:14 INFO\u001b[0m Step 573/1000 | Loss: 2.7935\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:43:14 INFO\u001b[0m Step 573/1000 | Loss: 1.9829\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:43:14 INFO\u001b[0m Step 573/1000 | Loss: 2.0973\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:43:14 INFO\u001b[0m Step 573/1000 | Loss: 2.0536\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:43:14 INFO\u001b[0m Step 573/1000 | Loss: 2.1671\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:43:14 INFO\u001b[0m Step 573/1000 | Loss: 2.0635\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:43:15 INFO\u001b[0m Step 574/1000 | Loss: 2.3844\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:43:15 INFO\u001b[0m Step 574/1000 | Loss: 2.0488\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:43:15 INFO\u001b[0m Step 574/1000 | Loss: 1.9482\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:43:15 INFO\u001b[0m Step 574/1000 | Loss: 2.1157\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:43:15 INFO\u001b[0m Step 574/1000 | Loss: 2.3871\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:43:15 INFO\u001b[0m Step 574/1000 | Loss: 2.2747\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:43:15 INFO\u001b[0m Step 574/1000 | Loss: 3.0547\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:43:15 INFO\u001b[0m Step 574/1000 | Loss: 3.0342\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:43:17 INFO\u001b[0m Step 575/1000 | Loss: 2.6016\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:43:17 INFO\u001b[0m Step 575/1000 | Loss: 2.4832\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:43:17 INFO\u001b[0m Step 575/1000 | Loss: 2.4574\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:43:17 INFO\u001b[0m Step 575/1000 | Loss: 2.4049\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:43:17 INFO\u001b[0m Step 575/1000 | Loss: 2.0207\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:43:17 INFO\u001b[0m Step 575/1000 | Loss: 2.8008\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:43:17 INFO\u001b[0m Step 575/1000 | Loss: 2.8374\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:43:17 INFO\u001b[0m Step 575/1000 | Loss: 2.4897\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:43:20 INFO\u001b[0m Step 576/1000 | Loss: 2.1078\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:43:20 INFO\u001b[0m Step 576/1000 | Loss: 2.8053\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:43:20 INFO\u001b[0m Step 576/1000 | Loss: 2.3258\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:43:20 INFO\u001b[0m Step 576/1000 | Loss: 3.0879\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:43:20 INFO\u001b[0m Step 576/1000 | Loss: 2.1240\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:43:20 INFO\u001b[0m Step 576/1000 | Loss: 2.1717\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:43:20 INFO\u001b[0m Step 576/1000 | Loss: 2.5143\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:43:20 INFO\u001b[0m Step 576/1000 | Loss: 2.2456\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:43:22 INFO\u001b[0m Step 577/1000 | Loss: 2.1842\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:43:22 INFO\u001b[0m Step 577/1000 | Loss: 2.4819\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:43:22 INFO\u001b[0m Step 577/1000 | Loss: 2.6884\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:43:22 INFO\u001b[0m Step 577/1000 | Loss: 2.4414\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:43:22 INFO\u001b[0m Step 577/1000 | Loss: 2.3018\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:43:22 INFO\u001b[0m Step 577/1000 | Loss: 2.2904\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:43:22 INFO\u001b[0m Step 577/1000 | Loss: 2.3776\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:43:22 INFO\u001b[0m Step 577/1000 | Loss: 2.5194\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:43:25 INFO\u001b[0m Step 578/1000 | Loss: 2.1024\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:43:25 INFO\u001b[0m Step 578/1000 | Loss: 2.6528\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:43:25 INFO\u001b[0m Step 578/1000 | Loss: 2.3125\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:43:25 INFO\u001b[0m Step 578/1000 | Loss: 2.5042\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:43:25 INFO\u001b[0m Step 578/1000 | Loss: 2.5501\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:43:25 INFO\u001b[0m Step 578/1000 | Loss: 2.3194\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:43:25 INFO\u001b[0m Step 578/1000 | Loss: 2.1868\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:43:25 INFO\u001b[0m Step 578/1000 | Loss: 2.5066\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:43:27 INFO\u001b[0m Step 579/1000 | Loss: 2.4836\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:43:27 INFO\u001b[0m Step 579/1000 | Loss: 2.6200\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:43:27 INFO\u001b[0m Step 579/1000 | Loss: 1.9248\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:43:27 INFO\u001b[0m Step 579/1000 | Loss: 2.5627\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:43:27 INFO\u001b[0m Step 579/1000 | Loss: 2.1434\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:43:27 INFO\u001b[0m Step 579/1000 | Loss: 2.6616\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:43:27 INFO\u001b[0m Step 579/1000 | Loss: 2.1078\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:43:27 INFO\u001b[0m Step 579/1000 | Loss: 2.0847\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:43:30 INFO\u001b[0m Step 580/1000 | Loss: 2.2007\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:43:30 INFO\u001b[0m Step 580/1000 | Loss: 2.4997\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:43:30 INFO\u001b[0m Step 580/1000 | Loss: 2.3236\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:43:30 INFO\u001b[0m Step 580/1000 | Loss: 1.9799\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:43:30 INFO\u001b[0m Step 580/1000 | Loss: 2.7635\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:43:30 INFO\u001b[0m Step 580/1000 | Loss: 2.6944\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:43:30 INFO\u001b[0m Step 580/1000 | Loss: 2.5043\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:43:30 INFO\u001b[0m Step 580/1000 | Loss: 2.2018\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:43:33 INFO\u001b[0m Step 581/1000 | Loss: 2.7328\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:43:33 INFO\u001b[0m Step 581/1000 | Loss: 2.5707\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:43:33 INFO\u001b[0m Step 581/1000 | Loss: 2.3559\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:43:33 INFO\u001b[0m Step 581/1000 | Loss: 2.6178\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:43:33 INFO\u001b[0m Step 581/1000 | Loss: 2.3901\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:43:33 INFO\u001b[0m Step 581/1000 | Loss: 2.5582\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:43:33 INFO\u001b[0m Step 581/1000 | Loss: 2.4559\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:43:33 INFO\u001b[0m Step 581/1000 | Loss: 2.7560\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:43:34 INFO\u001b[0m Step 582/1000 | Loss: 3.0147\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:43:34 INFO\u001b[0m Step 582/1000 | Loss: 2.4864\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:43:34 INFO\u001b[0m Step 582/1000 | Loss: 2.3666\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:43:34 INFO\u001b[0m Step 582/1000 | Loss: 2.3027\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:43:34 INFO\u001b[0m Step 582/1000 | Loss: 3.0711\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:43:34 INFO\u001b[0m Step 582/1000 | Loss: 3.0275\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:43:34 INFO\u001b[0m Step 582/1000 | Loss: 2.5268\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:43:34 INFO\u001b[0m Step 582/1000 | Loss: 2.1336\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:43:38 INFO\u001b[0m Step 583/1000 | Loss: 2.4853\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:43:38 INFO\u001b[0m Step 583/1000 | Loss: 2.1722\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:43:38 INFO\u001b[0m Step 583/1000 | Loss: 2.0706\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:43:38 INFO\u001b[0m Step 583/1000 | Loss: 3.0138\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:43:38 INFO\u001b[0m Step 583/1000 | Loss: 2.4766\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:43:38 INFO\u001b[0m Step 583/1000 | Loss: 2.5308\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:43:38 INFO\u001b[0m Step 583/1000 | Loss: 2.5669\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:43:38 INFO\u001b[0m Step 583/1000 | Loss: 2.0255\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:43:42 INFO\u001b[0m Step 584/1000 | Loss: 2.6701\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:43:42 INFO\u001b[0m Step 584/1000 | Loss: 2.0601\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:43:42 INFO\u001b[0m Step 584/1000 | Loss: 2.1052\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:43:42 INFO\u001b[0m Step 584/1000 | Loss: 2.1138\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:43:42 INFO\u001b[0m Step 584/1000 | Loss: 1.9658\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:43:42 INFO\u001b[0m Step 584/1000 | Loss: 2.4499\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:43:42 INFO\u001b[0m Step 584/1000 | Loss: 2.1151\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:43:42 INFO\u001b[0m Step 584/1000 | Loss: 2.8598\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:43:44 INFO\u001b[0m Step 585/1000 | Loss: 2.9141\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:43:44 INFO\u001b[0m Step 585/1000 | Loss: 2.5296\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:43:44 INFO\u001b[0m Step 585/1000 | Loss: 2.5230\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:43:44 INFO\u001b[0m Step 585/1000 | Loss: 2.8168\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:43:44 INFO\u001b[0m Step 585/1000 | Loss: 2.2276\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:43:44 INFO\u001b[0m Step 585/1000 | Loss: 2.5979\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:43:44 INFO\u001b[0m Step 585/1000 | Loss: 2.0426\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:43:44 INFO\u001b[0m Step 585/1000 | Loss: 2.0516\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:43:46 INFO\u001b[0m Step 586/1000 | Loss: 2.1390\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:43:46 INFO\u001b[0m Step 586/1000 | Loss: 2.4291\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:43:46 INFO\u001b[0m Step 586/1000 | Loss: 3.0174\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:43:46 INFO\u001b[0m Step 586/1000 | Loss: 1.9376\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:43:46 INFO\u001b[0m Step 586/1000 | Loss: 2.4116\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:43:46 INFO\u001b[0m Step 586/1000 | Loss: 2.2816\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:43:46 INFO\u001b[0m Step 586/1000 | Loss: 2.7377\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:43:46 INFO\u001b[0m Step 586/1000 | Loss: 2.0569\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:43:49 INFO\u001b[0m Step 587/1000 | Loss: 2.5949\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:43:49 INFO\u001b[0m Step 587/1000 | Loss: 2.4929\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:43:49 INFO\u001b[0m Step 587/1000 | Loss: 1.9961\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:43:49 INFO\u001b[0m Step 587/1000 | Loss: 2.3191\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:43:49 INFO\u001b[0m Step 587/1000 | Loss: 2.4770\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:43:49 INFO\u001b[0m Step 587/1000 | Loss: 2.9419\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:43:49 INFO\u001b[0m Step 587/1000 | Loss: 1.7302\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:43:49 INFO\u001b[0m Step 587/1000 | Loss: 2.5481\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:43:51 INFO\u001b[0m Step 588/1000 | Loss: 2.2207\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:43:51 INFO\u001b[0m Step 588/1000 | Loss: 3.1447\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:43:51 INFO\u001b[0m Step 588/1000 | Loss: 2.2067\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:43:51 INFO\u001b[0m Step 588/1000 | Loss: 2.4190\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:43:51 INFO\u001b[0m Step 588/1000 | Loss: 2.6638\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:43:51 INFO\u001b[0m Step 588/1000 | Loss: 2.1588\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:43:51 INFO\u001b[0m Step 588/1000 | Loss: 1.8227\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:43:51 INFO\u001b[0m Step 588/1000 | Loss: 2.3682\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:43:53 INFO\u001b[0m Step 589/1000 | Loss: 3.1063\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:43:53 INFO\u001b[0m Step 589/1000 | Loss: 2.0073\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:43:53 INFO\u001b[0m Step 589/1000 | Loss: 2.4067\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:43:53 INFO\u001b[0m Step 589/1000 | Loss: 2.5870\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:43:53 INFO\u001b[0m Step 589/1000 | Loss: 2.6895\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:43:53 INFO\u001b[0m Step 589/1000 | Loss: 2.8253\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:43:53 INFO\u001b[0m Step 589/1000 | Loss: 3.1528\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:43:53 INFO\u001b[0m Step 589/1000 | Loss: 2.0678\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:43:55 INFO\u001b[0m Step 590/1000 | Loss: 2.6601\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:43:55 INFO\u001b[0m Step 590/1000 | Loss: 1.8612\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:43:55 INFO\u001b[0m Step 590/1000 | Loss: 2.3412\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:43:55 INFO\u001b[0m Step 590/1000 | Loss: 2.2697\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:43:55 INFO\u001b[0m Step 590/1000 | Loss: 2.4981\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:43:55 INFO\u001b[0m Step 590/1000 | Loss: 2.2675\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:43:55 INFO\u001b[0m Step 590/1000 | Loss: 2.5907\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:43:55 INFO\u001b[0m Step 590/1000 | Loss: 2.9232\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:43:56 INFO\u001b[0m Step 591/1000 | Loss: 2.8513\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:43:56 INFO\u001b[0m Step 591/1000 | Loss: 2.6788\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:43:56 INFO\u001b[0m Step 591/1000 | Loss: 2.4802\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:43:56 INFO\u001b[0m Step 591/1000 | Loss: 2.2450\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:43:56 INFO\u001b[0m Step 591/1000 | Loss: 2.2493\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:43:56 INFO\u001b[0m Step 591/1000 | Loss: 2.6069\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:43:56 INFO\u001b[0m Step 591/1000 | Loss: 1.9157\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:43:56 INFO\u001b[0m Step 591/1000 | Loss: 2.7310\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:43:58 INFO\u001b[0m Step 592/1000 | Loss: 2.6464\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:43:58 INFO\u001b[0m Step 592/1000 | Loss: 2.8177\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:43:58 INFO\u001b[0m Step 592/1000 | Loss: 2.0665\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:43:58 INFO\u001b[0m Step 592/1000 | Loss: 2.5051\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:43:58 INFO\u001b[0m Step 592/1000 | Loss: 2.0097\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:43:58 INFO\u001b[0m Step 592/1000 | Loss: 2.2034\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:43:58 INFO\u001b[0m Step 592/1000 | Loss: 2.4428\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:43:58 INFO\u001b[0m Step 592/1000 | Loss: 2.7924\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:44:00 INFO\u001b[0m Step 593/1000 | Loss: 2.3737\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:44:00 INFO\u001b[0m Step 593/1000 | Loss: 2.5066\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:44:00 INFO\u001b[0m Step 593/1000 | Loss: 2.7495\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:44:00 INFO\u001b[0m Step 593/1000 | Loss: 3.0408\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:44:00 INFO\u001b[0m Step 593/1000 | Loss: 2.6481\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:44:00 INFO\u001b[0m Step 593/1000 | Loss: 2.5955\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:44:00 INFO\u001b[0m Step 593/1000 | Loss: 3.2229\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:44:00 INFO\u001b[0m Step 593/1000 | Loss: 2.6820\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:44:02 INFO\u001b[0m Step 594/1000 | Loss: 2.6059\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:44:02 INFO\u001b[0m Step 594/1000 | Loss: 2.6055\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:44:02 INFO\u001b[0m Step 594/1000 | Loss: 2.7158\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:44:02 INFO\u001b[0m Step 594/1000 | Loss: 2.5731\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:44:02 INFO\u001b[0m Step 594/1000 | Loss: 2.3241\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:44:02 INFO\u001b[0m Step 594/1000 | Loss: 2.3809\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:44:02 INFO\u001b[0m Step 594/1000 | Loss: 2.8068\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:44:02 INFO\u001b[0m Step 594/1000 | Loss: 1.9732\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:44:05 INFO\u001b[0m Step 595/1000 | Loss: 2.3820\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:44:05 INFO\u001b[0m Step 595/1000 | Loss: 2.4339\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:44:05 INFO\u001b[0m Step 595/1000 | Loss: 2.5107\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:44:05 INFO\u001b[0m Step 595/1000 | Loss: 2.8936\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:44:05 INFO\u001b[0m Step 595/1000 | Loss: 2.5275\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:44:05 INFO\u001b[0m Step 595/1000 | Loss: 2.4368\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:44:05 INFO\u001b[0m Step 595/1000 | Loss: 3.0479\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:44:05 INFO\u001b[0m Step 595/1000 | Loss: 2.4877\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:44:07 INFO\u001b[0m Step 596/1000 | Loss: 2.7240\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:44:07 INFO\u001b[0m Step 596/1000 | Loss: 1.8212\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:44:07 INFO\u001b[0m Step 596/1000 | Loss: 2.5281\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:44:07 INFO\u001b[0m Step 596/1000 | Loss: 2.3451\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:44:07 INFO\u001b[0m Step 596/1000 | Loss: 2.9234\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:44:07 INFO\u001b[0m Step 596/1000 | Loss: 2.6488\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:44:07 INFO\u001b[0m Step 596/1000 | Loss: 2.2004\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:44:07 INFO\u001b[0m Step 596/1000 | Loss: 3.1436\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:44:09 INFO\u001b[0m Step 597/1000 | Loss: 2.6337\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:44:09 INFO\u001b[0m Step 597/1000 | Loss: 2.4227\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:44:09 INFO\u001b[0m Step 597/1000 | Loss: 2.4872\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:44:09 INFO\u001b[0m Step 597/1000 | Loss: 2.7047\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:44:09 INFO\u001b[0m Step 597/1000 | Loss: 2.7386\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:44:09 INFO\u001b[0m Step 597/1000 | Loss: 3.1944\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:44:09 INFO\u001b[0m Step 597/1000 | Loss: 2.9579\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:44:09 INFO\u001b[0m Step 597/1000 | Loss: 2.8925\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:44:11 INFO\u001b[0m Step 598/1000 | Loss: 2.6667\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:44:11 INFO\u001b[0m Step 598/1000 | Loss: 2.2727\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:44:11 INFO\u001b[0m Step 598/1000 | Loss: 2.5198\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:44:11 INFO\u001b[0m Step 598/1000 | Loss: 2.0715\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:44:11 INFO\u001b[0m Step 598/1000 | Loss: 2.4607\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:44:11 INFO\u001b[0m Step 598/1000 | Loss: 2.7462\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:44:11 INFO\u001b[0m Step 598/1000 | Loss: 2.2851\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:44:11 INFO\u001b[0m Step 598/1000 | Loss: 2.2837\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:44:12 INFO\u001b[0m Step 599/1000 | Loss: 2.6597\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:44:12 INFO\u001b[0m Step 599/1000 | Loss: 2.8341\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:44:12 INFO\u001b[0m Step 599/1000 | Loss: 2.8308\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:44:12 INFO\u001b[0m Step 599/1000 | Loss: 2.5878\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:44:12 INFO\u001b[0m Step 599/1000 | Loss: 2.6208\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:44:12 INFO\u001b[0m Step 599/1000 | Loss: 2.6218\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:44:12 INFO\u001b[0m Step 599/1000 | Loss: 2.8318\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:44:12 INFO\u001b[0m Step 599/1000 | Loss: 2.3584\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:44:15 INFO\u001b[0m Step 600/1000 | Loss: 2.4496\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:44:15 INFO\u001b[0m Step 600/1000 | Loss: 3.2904\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:44:15 INFO\u001b[0m Step 600/1000 | Loss: 2.0563\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:44:15 INFO\u001b[0m Step 600/1000 | Loss: 1.8517\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:44:15 INFO\u001b[0m Step 600/1000 | Loss: 2.7427\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:44:15 INFO\u001b[0m Step 600/1000 | Loss: 2.3382\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:44:15 INFO\u001b[0m Step 600/1000 | Loss: 2.8029\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:44:15 INFO\u001b[0m Step 600/1000 | Loss: 2.7119\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:44:17 INFO\u001b[0m Step 601/1000 | Loss: 2.3888\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:44:17 INFO\u001b[0m Step 601/1000 | Loss: 2.4281\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:44:17 INFO\u001b[0m Step 601/1000 | Loss: 2.2550\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:44:17 INFO\u001b[0m Step 601/1000 | Loss: 2.7869\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:44:17 INFO\u001b[0m Step 601/1000 | Loss: 2.5448\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:44:17 INFO\u001b[0m Step 601/1000 | Loss: 2.2631\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:44:17 INFO\u001b[0m Step 601/1000 | Loss: 2.4715\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:44:17 INFO\u001b[0m Step 601/1000 | Loss: 2.3995\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:44:19 INFO\u001b[0m Step 602/1000 | Loss: 2.8917\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:44:19 INFO\u001b[0m Step 602/1000 | Loss: 1.9754\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:44:19 INFO\u001b[0m Step 602/1000 | Loss: 2.6316\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:44:19 INFO\u001b[0m Step 602/1000 | Loss: 2.4917\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:44:19 INFO\u001b[0m Step 602/1000 | Loss: 2.2712\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:44:19 INFO\u001b[0m Step 602/1000 | Loss: 2.2603\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:44:19 INFO\u001b[0m Step 602/1000 | Loss: 2.4473\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:44:19 INFO\u001b[0m Step 602/1000 | Loss: 2.2041\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:44:20 INFO\u001b[0m Step 603/1000 | Loss: 2.2598\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:44:20 INFO\u001b[0m Step 603/1000 | Loss: 2.2782\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:44:20 INFO\u001b[0m Step 603/1000 | Loss: 2.5189\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:44:20 INFO\u001b[0m Step 603/1000 | Loss: 2.7091\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:44:20 INFO\u001b[0m Step 603/1000 | Loss: 2.3324\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:44:20 INFO\u001b[0m Step 603/1000 | Loss: 3.0295\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:44:20 INFO\u001b[0m Step 603/1000 | Loss: 2.6956\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:44:20 INFO\u001b[0m Step 603/1000 | Loss: 2.6601\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:44:22 INFO\u001b[0m Step 604/1000 | Loss: 2.3280\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:44:22 INFO\u001b[0m Step 604/1000 | Loss: 2.5524\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:44:22 INFO\u001b[0m Step 604/1000 | Loss: 2.6342\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:44:22 INFO\u001b[0m Step 604/1000 | Loss: 2.5008\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:44:22 INFO\u001b[0m Step 604/1000 | Loss: 2.5657\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:44:22 INFO\u001b[0m Step 604/1000 | Loss: 2.5922\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:44:22 INFO\u001b[0m Step 604/1000 | Loss: 2.3784\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:44:22 INFO\u001b[0m Step 604/1000 | Loss: 2.2014\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:44:24 INFO\u001b[0m Step 605/1000 | Loss: 2.0151\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:44:24 INFO\u001b[0m Step 605/1000 | Loss: 2.5551\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:44:24 INFO\u001b[0m Step 605/1000 | Loss: 2.5998\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:44:24 INFO\u001b[0m Step 605/1000 | Loss: 2.0201\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:44:24 INFO\u001b[0m Step 605/1000 | Loss: 2.0777\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:44:24 INFO\u001b[0m Step 605/1000 | Loss: 2.6591\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:44:24 INFO\u001b[0m Step 605/1000 | Loss: 2.9499\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:44:24 INFO\u001b[0m Step 605/1000 | Loss: 2.4186\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:44:26 INFO\u001b[0m Step 606/1000 | Loss: 2.1820\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:44:26 INFO\u001b[0m Step 606/1000 | Loss: 2.6358\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:44:26 INFO\u001b[0m Step 606/1000 | Loss: 3.0876\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:44:26 INFO\u001b[0m Step 606/1000 | Loss: 3.0979\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:44:26 INFO\u001b[0m Step 606/1000 | Loss: 2.0195\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:44:26 INFO\u001b[0m Step 606/1000 | Loss: 2.5001\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:44:26 INFO\u001b[0m Step 606/1000 | Loss: 2.6058\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:44:26 INFO\u001b[0m Step 606/1000 | Loss: 2.4399\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:44:27 INFO\u001b[0m Step 607/1000 | Loss: 2.6540\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:44:27 INFO\u001b[0m Step 607/1000 | Loss: 2.1529\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:44:27 INFO\u001b[0m Step 607/1000 | Loss: 2.6344\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:44:27 INFO\u001b[0m Step 607/1000 | Loss: 2.2410\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:44:27 INFO\u001b[0m Step 607/1000 | Loss: 2.6330\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:44:27 INFO\u001b[0m Step 607/1000 | Loss: 2.9325\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:44:27 INFO\u001b[0m Step 607/1000 | Loss: 2.3235\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:44:27 INFO\u001b[0m Step 607/1000 | Loss: 2.5610\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:44:28 INFO\u001b[0m Step 608/1000 | Loss: 2.2761\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:44:28 INFO\u001b[0m Step 608/1000 | Loss: 2.6187\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:44:28 INFO\u001b[0m Step 608/1000 | Loss: 1.9525\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:44:28 INFO\u001b[0m Step 608/1000 | Loss: 2.3455\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:44:28 INFO\u001b[0m Step 608/1000 | Loss: 2.7380\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:44:28 INFO\u001b[0m Step 608/1000 | Loss: 2.3583\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:44:28 INFO\u001b[0m Step 608/1000 | Loss: 2.7102\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:44:28 INFO\u001b[0m Step 608/1000 | Loss: 2.6020\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:44:31 INFO\u001b[0m Step 609/1000 | Loss: 2.9588\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:44:31 INFO\u001b[0m Step 609/1000 | Loss: 1.8344\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:44:31 INFO\u001b[0m Step 609/1000 | Loss: 2.7639\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:44:31 INFO\u001b[0m Step 609/1000 | Loss: 2.4294\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:44:31 INFO\u001b[0m Step 609/1000 | Loss: 2.2581\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:44:31 INFO\u001b[0m Step 609/1000 | Loss: 3.1051\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:44:31 INFO\u001b[0m Step 609/1000 | Loss: 2.6439\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:44:31 INFO\u001b[0m Step 609/1000 | Loss: 3.0683\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:44:34 INFO\u001b[0m Step 610/1000 | Loss: 2.5713\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:44:34 INFO\u001b[0m Step 610/1000 | Loss: 2.6293\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:44:34 INFO\u001b[0m Step 610/1000 | Loss: 3.1871\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:44:34 INFO\u001b[0m Step 610/1000 | Loss: 2.7096\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:44:34 INFO\u001b[0m Step 610/1000 | Loss: 2.4274\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:44:34 INFO\u001b[0m Step 610/1000 | Loss: 2.2618\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:44:34 INFO\u001b[0m Step 610/1000 | Loss: 2.5833\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:44:34 INFO\u001b[0m Step 610/1000 | Loss: 2.2543\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:44:38 INFO\u001b[0m Step 611/1000 | Loss: 2.4327\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:44:38 INFO\u001b[0m Step 611/1000 | Loss: 2.0384\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:44:38 INFO\u001b[0m Step 611/1000 | Loss: 2.4385\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:44:38 INFO\u001b[0m Step 611/1000 | Loss: 2.4444\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:44:38 INFO\u001b[0m Step 611/1000 | Loss: 2.4862\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:44:38 INFO\u001b[0m Step 611/1000 | Loss: 2.8580\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:44:38 INFO\u001b[0m Step 611/1000 | Loss: 2.7818\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:44:38 INFO\u001b[0m Step 611/1000 | Loss: 2.4117\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:44:40 INFO\u001b[0m Step 612/1000 | Loss: 2.5233\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:44:40 INFO\u001b[0m Step 612/1000 | Loss: 2.6498\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:44:40 INFO\u001b[0m Step 612/1000 | Loss: 2.8945\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:44:40 INFO\u001b[0m Step 612/1000 | Loss: 2.4399\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:44:40 INFO\u001b[0m Step 612/1000 | Loss: 2.4566\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:44:40 INFO\u001b[0m Step 612/1000 | Loss: 2.8365\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:44:40 INFO\u001b[0m Step 612/1000 | Loss: 3.0106\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:44:40 INFO\u001b[0m Step 612/1000 | Loss: 2.5024\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:44:42 INFO\u001b[0m Step 613/1000 | Loss: 2.2748\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:44:42 INFO\u001b[0m Step 613/1000 | Loss: 2.7388\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:44:42 INFO\u001b[0m Step 613/1000 | Loss: 2.6504\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:44:42 INFO\u001b[0m Step 613/1000 | Loss: 2.2763\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:44:42 INFO\u001b[0m Step 613/1000 | Loss: 2.1751\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:44:42 INFO\u001b[0m Step 613/1000 | Loss: 2.4421\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:44:42 INFO\u001b[0m Step 613/1000 | Loss: 2.6218\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:44:42 INFO\u001b[0m Step 613/1000 | Loss: 2.7446\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:44:44 INFO\u001b[0m Step 614/1000 | Loss: 2.7537\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:44:44 INFO\u001b[0m Step 614/1000 | Loss: 2.6560\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:44:44 INFO\u001b[0m Step 614/1000 | Loss: 2.5926\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:44:44 INFO\u001b[0m Step 614/1000 | Loss: 2.3861\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:44:44 INFO\u001b[0m Step 614/1000 | Loss: 3.1619\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:44:44 INFO\u001b[0m Step 614/1000 | Loss: 2.7819\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:44:44 INFO\u001b[0m Step 614/1000 | Loss: 2.5230\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:44:44 INFO\u001b[0m Step 614/1000 | Loss: 2.7014\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:44:46 INFO\u001b[0m Step 615/1000 | Loss: 2.5255\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:44:46 INFO\u001b[0m Step 615/1000 | Loss: 2.3954\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:44:46 INFO\u001b[0m Step 615/1000 | Loss: 2.4726\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:44:46 INFO\u001b[0m Step 615/1000 | Loss: 2.6101\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:44:46 INFO\u001b[0m Step 615/1000 | Loss: 2.6922\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:44:46 INFO\u001b[0m Step 615/1000 | Loss: 2.6469\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:44:46 INFO\u001b[0m Step 615/1000 | Loss: 3.1301\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:44:46 INFO\u001b[0m Step 615/1000 | Loss: 3.6528\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:44:48 INFO\u001b[0m Step 616/1000 | Loss: 2.1786\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:44:48 INFO\u001b[0m Step 616/1000 | Loss: 2.3750\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:44:48 INFO\u001b[0m Step 616/1000 | Loss: 2.8493\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:44:48 INFO\u001b[0m Step 616/1000 | Loss: 2.9964\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:44:48 INFO\u001b[0m Step 616/1000 | Loss: 2.1736\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:44:48 INFO\u001b[0m Step 616/1000 | Loss: 2.5315\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:44:48 INFO\u001b[0m Step 616/1000 | Loss: 2.4243\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:44:48 INFO\u001b[0m Step 616/1000 | Loss: 2.6447\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:44:50 INFO\u001b[0m Step 617/1000 | Loss: 2.0555\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:44:50 INFO\u001b[0m Step 617/1000 | Loss: 1.8435\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:44:50 INFO\u001b[0m Step 617/1000 | Loss: 2.7291\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:44:50 INFO\u001b[0m Step 617/1000 | Loss: 3.1180\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:44:50 INFO\u001b[0m Step 617/1000 | Loss: 2.8918\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:44:50 INFO\u001b[0m Step 617/1000 | Loss: 2.3505\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:44:50 INFO\u001b[0m Step 617/1000 | Loss: 2.7457\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:44:50 INFO\u001b[0m Step 617/1000 | Loss: 2.4054\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:44:53 INFO\u001b[0m Step 618/1000 | Loss: 2.4191\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:44:53 INFO\u001b[0m Step 618/1000 | Loss: 2.9728\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:44:53 INFO\u001b[0m Step 618/1000 | Loss: 2.1969\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:44:53 INFO\u001b[0m Step 618/1000 | Loss: 2.1860\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:44:53 INFO\u001b[0m Step 618/1000 | Loss: 2.0503\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:44:53 INFO\u001b[0m Step 618/1000 | Loss: 2.4700\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:44:53 INFO\u001b[0m Step 618/1000 | Loss: 2.1035\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:44:53 INFO\u001b[0m Step 618/1000 | Loss: 3.5248\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:44:55 INFO\u001b[0m Step 619/1000 | Loss: 2.2903\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:44:55 INFO\u001b[0m Step 619/1000 | Loss: 2.1063\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:44:55 INFO\u001b[0m Step 619/1000 | Loss: 2.4191\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:44:55 INFO\u001b[0m Step 619/1000 | Loss: 2.5914\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:44:55 INFO\u001b[0m Step 619/1000 | Loss: 2.2480\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:44:55 INFO\u001b[0m Step 619/1000 | Loss: 2.5609\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:44:55 INFO\u001b[0m Step 619/1000 | Loss: 2.6945\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:44:55 INFO\u001b[0m Step 619/1000 | Loss: 2.6269\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:44:59 INFO\u001b[0m Step 620/1000 | Loss: 2.2230\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:44:59 INFO\u001b[0m Step 620/1000 | Loss: 2.4563\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:44:59 INFO\u001b[0m Step 620/1000 | Loss: 2.2835\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:44:59 INFO\u001b[0m Step 620/1000 | Loss: 2.8776\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:44:59 INFO\u001b[0m Step 620/1000 | Loss: 2.5276\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:44:59 INFO\u001b[0m Step 620/1000 | Loss: 2.4537\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:44:59 INFO\u001b[0m Step 620/1000 | Loss: 2.5364\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:44:59 INFO\u001b[0m Step 620/1000 | Loss: 2.5578\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:45:03 INFO\u001b[0m Step 621/1000 | Loss: 2.2669\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:45:03 INFO\u001b[0m Step 621/1000 | Loss: 2.4470\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:45:03 INFO\u001b[0m Step 621/1000 | Loss: 2.1053\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:45:03 INFO\u001b[0m Step 621/1000 | Loss: 2.6580\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:45:03 INFO\u001b[0m Step 621/1000 | Loss: 2.4701\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:45:03 INFO\u001b[0m Step 621/1000 | Loss: 2.4429\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:45:03 INFO\u001b[0m Step 621/1000 | Loss: 2.6031\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:45:03 INFO\u001b[0m Step 621/1000 | Loss: 2.6747\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:45:06 INFO\u001b[0m Step 622/1000 | Loss: 2.1929\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:45:06 INFO\u001b[0m Step 622/1000 | Loss: 2.6231\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:45:06 INFO\u001b[0m Step 622/1000 | Loss: 2.9013\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:45:06 INFO\u001b[0m Step 622/1000 | Loss: 2.2411\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:45:06 INFO\u001b[0m Step 622/1000 | Loss: 2.0699\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:45:06 INFO\u001b[0m Step 622/1000 | Loss: 2.2593\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:45:06 INFO\u001b[0m Step 622/1000 | Loss: 2.5050\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:45:06 INFO\u001b[0m Step 622/1000 | Loss: 1.9891\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:45:10 INFO\u001b[0m Step 623/1000 | Loss: 2.0887\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:45:10 INFO\u001b[0m Step 623/1000 | Loss: 2.6631\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:45:10 INFO\u001b[0m Step 623/1000 | Loss: 2.0230\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:45:10 INFO\u001b[0m Step 623/1000 | Loss: 2.4297\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:45:10 INFO\u001b[0m Step 623/1000 | Loss: 2.3389\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:45:10 INFO\u001b[0m Step 623/1000 | Loss: 2.5079\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:45:10 INFO\u001b[0m Step 623/1000 | Loss: 1.9650\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:45:10 INFO\u001b[0m Step 623/1000 | Loss: 2.4274\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:45:12 INFO\u001b[0m Step 624/1000 | Loss: 2.5908\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:45:12 INFO\u001b[0m Step 624/1000 | Loss: 1.9892\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:45:12 INFO\u001b[0m Step 624/1000 | Loss: 2.1340\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:45:12 INFO\u001b[0m Step 624/1000 | Loss: 2.5332\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:45:12 INFO\u001b[0m Step 624/1000 | Loss: 1.9429\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:45:12 INFO\u001b[0m Step 624/1000 | Loss: 2.1880\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:45:12 INFO\u001b[0m Step 624/1000 | Loss: 2.1913\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:45:12 INFO\u001b[0m Step 624/1000 | Loss: 2.4237\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:45:15 INFO\u001b[0m Step 625/1000 | Loss: 2.3403\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:45:15 INFO\u001b[0m Step 625/1000 | Loss: 2.9435\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:45:15 INFO\u001b[0m Step 625/1000 | Loss: 2.2310\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:45:15 INFO\u001b[0m Step 625/1000 | Loss: 2.4745\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:45:15 INFO\u001b[0m Step 625/1000 | Loss: 2.4822\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:45:15 INFO\u001b[0m Step 625/1000 | Loss: 2.9170\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:45:15 INFO\u001b[0m Step 625/1000 | Loss: 2.0620\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:45:15 INFO\u001b[0m Step 625/1000 | Loss: 2.3513\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:45:17 INFO\u001b[0m Step 626/1000 | Loss: 2.4652\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:45:17 INFO\u001b[0m Step 626/1000 | Loss: 2.2574\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:45:17 INFO\u001b[0m Step 626/1000 | Loss: 2.3348\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:45:17 INFO\u001b[0m Step 626/1000 | Loss: 2.5501\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:45:17 INFO\u001b[0m Step 626/1000 | Loss: 2.4590\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:45:17 INFO\u001b[0m Step 626/1000 | Loss: 2.5603\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:45:17 INFO\u001b[0m Step 626/1000 | Loss: 2.6128\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:45:17 INFO\u001b[0m Step 626/1000 | Loss: 2.9328\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:45:19 INFO\u001b[0m Step 627/1000 | Loss: 3.0516\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:45:19 INFO\u001b[0m Step 627/1000 | Loss: 2.7361\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:45:19 INFO\u001b[0m Step 627/1000 | Loss: 2.6842\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:45:19 INFO\u001b[0m Step 627/1000 | Loss: 3.3347\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:45:19 INFO\u001b[0m Step 627/1000 | Loss: 2.3095\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:45:19 INFO\u001b[0m Step 627/1000 | Loss: 2.4620\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:45:19 INFO\u001b[0m Step 627/1000 | Loss: 2.5988\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:45:19 INFO\u001b[0m Step 627/1000 | Loss: 2.2338\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:45:21 INFO\u001b[0m Step 628/1000 | Loss: 2.5580\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:45:21 INFO\u001b[0m Step 628/1000 | Loss: 1.9336\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:45:21 INFO\u001b[0m Step 628/1000 | Loss: 2.4472\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:45:21 INFO\u001b[0m Step 628/1000 | Loss: 2.5162\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:45:21 INFO\u001b[0m Step 628/1000 | Loss: 2.3319\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:45:21 INFO\u001b[0m Step 628/1000 | Loss: 2.6203\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:45:21 INFO\u001b[0m Step 628/1000 | Loss: 2.0098\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:45:21 INFO\u001b[0m Step 628/1000 | Loss: 2.1448\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:45:23 INFO\u001b[0m Step 629/1000 | Loss: 2.1633\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:45:23 INFO\u001b[0m Step 629/1000 | Loss: 2.0491\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:45:23 INFO\u001b[0m Step 629/1000 | Loss: 2.5643\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:45:23 INFO\u001b[0m Step 629/1000 | Loss: 2.5519\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:45:23 INFO\u001b[0m Step 629/1000 | Loss: 2.3704\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:45:23 INFO\u001b[0m Step 629/1000 | Loss: 2.3314\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:45:23 INFO\u001b[0m Step 629/1000 | Loss: 2.5496\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:45:23 INFO\u001b[0m Step 629/1000 | Loss: 2.5570\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:45:24 INFO\u001b[0m Step 630/1000 | Loss: 2.4707\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:45:24 INFO\u001b[0m Step 630/1000 | Loss: 2.2657\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:45:24 INFO\u001b[0m Step 630/1000 | Loss: 2.3468\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:45:24 INFO\u001b[0m Step 630/1000 | Loss: 2.1574\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:45:24 INFO\u001b[0m Step 630/1000 | Loss: 2.4226\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:45:24 INFO\u001b[0m Step 630/1000 | Loss: 2.5316\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:45:24 INFO\u001b[0m Step 630/1000 | Loss: 2.6526\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:45:24 INFO\u001b[0m Step 630/1000 | Loss: 2.3828\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:45:26 INFO\u001b[0m Step 631/1000 | Loss: 2.7338\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:45:26 INFO\u001b[0m Step 631/1000 | Loss: 2.5367\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:45:26 INFO\u001b[0m Step 631/1000 | Loss: 2.8601\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:45:26 INFO\u001b[0m Step 631/1000 | Loss: 2.1335\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:45:26 INFO\u001b[0m Step 631/1000 | Loss: 2.6234\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:45:26 INFO\u001b[0m Step 631/1000 | Loss: 2.2259\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:45:26 INFO\u001b[0m Step 631/1000 | Loss: 2.6532\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:45:26 INFO\u001b[0m Step 631/1000 | Loss: 2.2126\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:45:28 INFO\u001b[0m Step 632/1000 | Loss: 2.3031\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:45:28 INFO\u001b[0m Step 632/1000 | Loss: 2.1187\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:45:28 INFO\u001b[0m Step 632/1000 | Loss: 2.9137\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:45:28 INFO\u001b[0m Step 632/1000 | Loss: 2.5246\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:45:28 INFO\u001b[0m Step 632/1000 | Loss: 2.2459\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:45:28 INFO\u001b[0m Step 632/1000 | Loss: 2.1258\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:45:28 INFO\u001b[0m Step 632/1000 | Loss: 2.4919\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:45:28 INFO\u001b[0m Step 632/1000 | Loss: 2.4622\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:45:30 INFO\u001b[0m Step 633/1000 | Loss: 2.4601\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:45:30 INFO\u001b[0m Step 633/1000 | Loss: 2.5604\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:45:30 INFO\u001b[0m Step 633/1000 | Loss: 2.6692\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:45:30 INFO\u001b[0m Step 633/1000 | Loss: 2.4123\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:45:30 INFO\u001b[0m Step 633/1000 | Loss: 2.3885\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:45:30 INFO\u001b[0m Step 633/1000 | Loss: 3.5280\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:45:30 INFO\u001b[0m Step 633/1000 | Loss: 2.4278\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:45:30 INFO\u001b[0m Step 633/1000 | Loss: 2.0807\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:45:31 INFO\u001b[0m Step 634/1000 | Loss: 2.6215\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:45:31 INFO\u001b[0m Step 634/1000 | Loss: 2.9522\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:45:31 INFO\u001b[0m Step 634/1000 | Loss: 2.6699\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:45:31 INFO\u001b[0m Step 634/1000 | Loss: 2.4158\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:45:31 INFO\u001b[0m Step 634/1000 | Loss: 2.1351\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:45:31 INFO\u001b[0m Step 634/1000 | Loss: 2.2495\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:45:31 INFO\u001b[0m Step 634/1000 | Loss: 2.2464\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:45:31 INFO\u001b[0m Step 634/1000 | Loss: 2.6638\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:45:35 INFO\u001b[0m Step 635/1000 | Loss: 2.0947\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:45:35 INFO\u001b[0m Step 635/1000 | Loss: 2.3396\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:45:35 INFO\u001b[0m Step 635/1000 | Loss: 2.3462\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:45:35 INFO\u001b[0m Step 635/1000 | Loss: 2.0248\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:45:35 INFO\u001b[0m Step 635/1000 | Loss: 2.3353\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:45:35 INFO\u001b[0m Step 635/1000 | Loss: 2.2464\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:45:35 INFO\u001b[0m Step 635/1000 | Loss: 2.7033\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:45:35 INFO\u001b[0m Step 635/1000 | Loss: 2.8312\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:45:38 INFO\u001b[0m Step 636/1000 | Loss: 2.8512\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:45:38 INFO\u001b[0m Step 636/1000 | Loss: 6.5163\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:45:38 INFO\u001b[0m Step 636/1000 | Loss: 2.2524\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:45:38 INFO\u001b[0m Step 636/1000 | Loss: 2.7525\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:45:38 INFO\u001b[0m Step 636/1000 | Loss: 2.9759\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:45:38 INFO\u001b[0m Step 636/1000 | Loss: 2.4600\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:45:38 INFO\u001b[0m Step 636/1000 | Loss: 2.5978\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:45:38 INFO\u001b[0m Step 636/1000 | Loss: 2.8009\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:45:39 INFO\u001b[0m Step 637/1000 | Loss: 2.2297\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:45:39 INFO\u001b[0m Step 637/1000 | Loss: 2.3632\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:45:39 INFO\u001b[0m Step 637/1000 | Loss: 2.1410\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:45:39 INFO\u001b[0m Step 637/1000 | Loss: 2.5369\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:45:39 INFO\u001b[0m Step 637/1000 | Loss: 2.5895\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:45:39 INFO\u001b[0m Step 637/1000 | Loss: 2.1223\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:45:39 INFO\u001b[0m Step 637/1000 | Loss: 2.8668\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:45:39 INFO\u001b[0m Step 637/1000 | Loss: 2.6894\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:45:42 INFO\u001b[0m Step 638/1000 | Loss: 2.6105\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:45:42 INFO\u001b[0m Step 638/1000 | Loss: 2.6489\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:45:42 INFO\u001b[0m Step 638/1000 | Loss: 2.5333\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:45:42 INFO\u001b[0m Step 638/1000 | Loss: 2.2743\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:45:42 INFO\u001b[0m Step 638/1000 | Loss: 2.3734\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:45:42 INFO\u001b[0m Step 638/1000 | Loss: 2.5304\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:45:42 INFO\u001b[0m Step 638/1000 | Loss: 1.9385\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:45:42 INFO\u001b[0m Step 638/1000 | Loss: 3.2146\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:45:43 INFO\u001b[0m Step 639/1000 | Loss: 2.2156\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:45:43 INFO\u001b[0m Step 639/1000 | Loss: 2.1365\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:45:43 INFO\u001b[0m Step 639/1000 | Loss: 3.3266\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:45:43 INFO\u001b[0m Step 639/1000 | Loss: 2.2523\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:45:43 INFO\u001b[0m Step 639/1000 | Loss: 2.4416\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:45:43 INFO\u001b[0m Step 639/1000 | Loss: 2.2679\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:45:43 INFO\u001b[0m Step 639/1000 | Loss: 2.7070\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:45:43 INFO\u001b[0m Step 639/1000 | Loss: 2.4174\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:45:45 INFO\u001b[0m Step 640/1000 | Loss: 2.1097\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:45:45 INFO\u001b[0m Step 640/1000 | Loss: 2.8647\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:45:45 INFO\u001b[0m Step 640/1000 | Loss: 3.1347\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:45:45 INFO\u001b[0m Step 640/1000 | Loss: 2.7720\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:45:45 INFO\u001b[0m Step 640/1000 | Loss: 2.7749\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:45:45 INFO\u001b[0m Step 640/1000 | Loss: 2.6614\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:45:45 INFO\u001b[0m Step 640/1000 | Loss: 2.5469\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:45:45 INFO\u001b[0m Step 640/1000 | Loss: 2.4852\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:45:49 INFO\u001b[0m Step 641/1000 | Loss: 2.1633\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:45:49 INFO\u001b[0m Step 641/1000 | Loss: 2.8935\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:45:49 INFO\u001b[0m Step 641/1000 | Loss: 2.5439\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:45:49 INFO\u001b[0m Step 641/1000 | Loss: 2.1451\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:45:49 INFO\u001b[0m Step 641/1000 | Loss: 2.3450\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:45:49 INFO\u001b[0m Step 641/1000 | Loss: 2.9648\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:45:49 INFO\u001b[0m Step 641/1000 | Loss: 2.4177\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:45:49 INFO\u001b[0m Step 641/1000 | Loss: 2.6795\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:45:52 INFO\u001b[0m Step 642/1000 | Loss: 1.9233\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:45:52 INFO\u001b[0m Step 642/1000 | Loss: 2.3189\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:45:52 INFO\u001b[0m Step 642/1000 | Loss: 2.9756\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:45:52 INFO\u001b[0m Step 642/1000 | Loss: 2.7369\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:45:52 INFO\u001b[0m Step 642/1000 | Loss: 2.5694\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:45:52 INFO\u001b[0m Step 642/1000 | Loss: 2.4269\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:45:52 INFO\u001b[0m Step 642/1000 | Loss: 3.3086\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:45:52 INFO\u001b[0m Step 642/1000 | Loss: 2.1247\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:45:53 INFO\u001b[0m Step 643/1000 | Loss: 2.7085\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:45:53 INFO\u001b[0m Step 643/1000 | Loss: 3.2893\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:45:53 INFO\u001b[0m Step 643/1000 | Loss: 2.5969\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:45:53 INFO\u001b[0m Step 643/1000 | Loss: 2.7661\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:45:53 INFO\u001b[0m Step 643/1000 | Loss: 2.1724\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:45:53 INFO\u001b[0m Step 643/1000 | Loss: 2.3234\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:45:53 INFO\u001b[0m Step 643/1000 | Loss: 2.6106\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:45:53 INFO\u001b[0m Step 643/1000 | Loss: 2.2310\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:45:54 INFO\u001b[0m Step 644/1000 | Loss: 3.0461\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:45:54 INFO\u001b[0m Step 644/1000 | Loss: 2.6009\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:45:54 INFO\u001b[0m Step 644/1000 | Loss: 3.0440\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:45:54 INFO\u001b[0m Step 644/1000 | Loss: 2.7803\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:45:54 INFO\u001b[0m Step 644/1000 | Loss: 2.7641\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:45:54 INFO\u001b[0m Step 644/1000 | Loss: 2.7678\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:45:54 INFO\u001b[0m Step 644/1000 | Loss: 2.5044\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:45:54 INFO\u001b[0m Step 644/1000 | Loss: 2.5291\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:45:55 INFO\u001b[0m Step 645/1000 | Loss: 2.6754\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:45:55 INFO\u001b[0m Step 645/1000 | Loss: 1.9898\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:45:55 INFO\u001b[0m Step 645/1000 | Loss: 2.5631\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:45:55 INFO\u001b[0m Step 645/1000 | Loss: 2.3103\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:45:55 INFO\u001b[0m Step 645/1000 | Loss: 2.6056\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:45:55 INFO\u001b[0m Step 645/1000 | Loss: 2.5455\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:45:55 INFO\u001b[0m Step 645/1000 | Loss: 2.4653\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:45:55 INFO\u001b[0m Step 645/1000 | Loss: 2.9332\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:45:57 INFO\u001b[0m Step 646/1000 | Loss: 2.5456\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:45:57 INFO\u001b[0m Step 646/1000 | Loss: 3.0169\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:45:57 INFO\u001b[0m Step 646/1000 | Loss: 2.7184\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:45:57 INFO\u001b[0m Step 646/1000 | Loss: 2.6165\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:45:57 INFO\u001b[0m Step 646/1000 | Loss: 2.4354\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:45:57 INFO\u001b[0m Step 646/1000 | Loss: 2.4013\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:45:57 INFO\u001b[0m Step 646/1000 | Loss: 2.8902\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:45:57 INFO\u001b[0m Step 646/1000 | Loss: 3.4933\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:45:59 INFO\u001b[0m Step 647/1000 | Loss: 2.5415\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:45:59 INFO\u001b[0m Step 647/1000 | Loss: 2.9615\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:45:59 INFO\u001b[0m Step 647/1000 | Loss: 2.6673\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:45:59 INFO\u001b[0m Step 647/1000 | Loss: 3.8105\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:45:59 INFO\u001b[0m Step 647/1000 | Loss: 2.4061\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:45:59 INFO\u001b[0m Step 647/1000 | Loss: 2.1552\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:45:59 INFO\u001b[0m Step 647/1000 | Loss: 2.0305\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:45:59 INFO\u001b[0m Step 647/1000 | Loss: 2.2132\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:02 INFO\u001b[0m Step 648/1000 | Loss: 3.2417\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:02 INFO\u001b[0m Step 648/1000 | Loss: 3.0615\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:02 INFO\u001b[0m Step 648/1000 | Loss: 3.1249\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:02 INFO\u001b[0m Step 648/1000 | Loss: 2.6393\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:02 INFO\u001b[0m Step 648/1000 | Loss: 3.1741\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:02 INFO\u001b[0m Step 648/1000 | Loss: 2.5525\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:02 INFO\u001b[0m Step 648/1000 | Loss: 2.1127\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:02 INFO\u001b[0m Step 648/1000 | Loss: 2.4744\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:04 INFO\u001b[0m Step 649/1000 | Loss: 2.7707\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:04 INFO\u001b[0m Step 649/1000 | Loss: 3.1898\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:04 INFO\u001b[0m Step 649/1000 | Loss: 3.1208\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:04 INFO\u001b[0m Step 649/1000 | Loss: 2.4678\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:04 INFO\u001b[0m Step 649/1000 | Loss: 2.4785\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:04 INFO\u001b[0m Step 649/1000 | Loss: 2.6839\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:04 INFO\u001b[0m Step 649/1000 | Loss: 2.9640\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:04 INFO\u001b[0m Step 649/1000 | Loss: 2.5420\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:06 INFO\u001b[0m Step 650/1000 | Loss: 2.0984\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:06 INFO\u001b[0m Step 650/1000 | Loss: 2.6993\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:06 INFO\u001b[0m Step 650/1000 | Loss: 2.8104\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:06 INFO\u001b[0m Step 650/1000 | Loss: 2.5842\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:06 INFO\u001b[0m Step 650/1000 | Loss: 2.9012\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:06 INFO\u001b[0m Step 650/1000 | Loss: 3.6534\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:06 INFO\u001b[0m Step 650/1000 | Loss: 2.6711\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:06 INFO\u001b[0m Step 650/1000 | Loss: 2.3440\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:07 INFO\u001b[0m Step 651/1000 | Loss: 3.2065\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:07 INFO\u001b[0m Step 651/1000 | Loss: 2.9113\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:07 INFO\u001b[0m Step 651/1000 | Loss: 2.8720\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:07 INFO\u001b[0m Step 651/1000 | Loss: 2.6715\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:07 INFO\u001b[0m Step 651/1000 | Loss: 2.8551\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:07 INFO\u001b[0m Step 651/1000 | Loss: 2.7647\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:07 INFO\u001b[0m Step 651/1000 | Loss: 2.8416\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:07 INFO\u001b[0m Step 651/1000 | Loss: 2.7068\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:11 INFO\u001b[0m Step 652/1000 | Loss: 2.4396\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:11 INFO\u001b[0m Step 652/1000 | Loss: 3.1811\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:11 INFO\u001b[0m Step 652/1000 | Loss: 2.8625\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:11 INFO\u001b[0m Step 652/1000 | Loss: 3.6363\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:11 INFO\u001b[0m Step 652/1000 | Loss: 2.8963\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:11 INFO\u001b[0m Step 652/1000 | Loss: 2.9529\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:11 INFO\u001b[0m Step 652/1000 | Loss: 2.3177\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:11 INFO\u001b[0m Step 652/1000 | Loss: 2.9731\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:12 INFO\u001b[0m Step 653/1000 | Loss: 3.0567\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:12 INFO\u001b[0m Step 653/1000 | Loss: 3.0865\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:12 INFO\u001b[0m Step 653/1000 | Loss: 2.4494\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:12 INFO\u001b[0m Step 653/1000 | Loss: 2.9110\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:12 INFO\u001b[0m Step 653/1000 | Loss: 3.6837\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:12 INFO\u001b[0m Step 653/1000 | Loss: 3.7320\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:12 INFO\u001b[0m Step 653/1000 | Loss: 2.3841\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:12 INFO\u001b[0m Step 653/1000 | Loss: 2.6074\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:14 INFO\u001b[0m Step 654/1000 | Loss: 2.7280\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:14 INFO\u001b[0m Step 654/1000 | Loss: 2.7529\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:14 INFO\u001b[0m Step 654/1000 | Loss: 2.6980\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:14 INFO\u001b[0m Step 654/1000 | Loss: 2.6071\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:14 INFO\u001b[0m Step 654/1000 | Loss: 2.3881\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:14 INFO\u001b[0m Step 654/1000 | Loss: 3.3103\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:14 INFO\u001b[0m Step 654/1000 | Loss: 2.4561\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:14 INFO\u001b[0m Step 654/1000 | Loss: 2.9966\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:15 INFO\u001b[0m Step 655/1000 | Loss: 2.9653\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:15 INFO\u001b[0m Step 655/1000 | Loss: 1.9632\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:15 INFO\u001b[0m Step 655/1000 | Loss: 2.9932\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:15 INFO\u001b[0m Step 655/1000 | Loss: 2.5740\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:15 INFO\u001b[0m Step 655/1000 | Loss: 2.4421\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:15 INFO\u001b[0m Step 655/1000 | Loss: 3.1865\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:15 INFO\u001b[0m Step 655/1000 | Loss: 2.7349\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:15 INFO\u001b[0m Step 655/1000 | Loss: 2.1977\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:18 INFO\u001b[0m Step 656/1000 | Loss: 2.6967\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:18 INFO\u001b[0m Step 656/1000 | Loss: 2.9225\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:18 INFO\u001b[0m Step 656/1000 | Loss: 2.5923\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:18 INFO\u001b[0m Step 656/1000 | Loss: 2.9662\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:18 INFO\u001b[0m Step 656/1000 | Loss: 2.0947\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:18 INFO\u001b[0m Step 656/1000 | Loss: 3.0432\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:18 INFO\u001b[0m Step 656/1000 | Loss: 2.6014\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:18 INFO\u001b[0m Step 656/1000 | Loss: 3.1463\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:21 INFO\u001b[0m Step 657/1000 | Loss: 2.6726\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:21 INFO\u001b[0m Step 657/1000 | Loss: 2.8236\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:21 INFO\u001b[0m Step 657/1000 | Loss: 3.2316\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:21 INFO\u001b[0m Step 657/1000 | Loss: 2.9908\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:21 INFO\u001b[0m Step 657/1000 | Loss: 2.4634\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:21 INFO\u001b[0m Step 657/1000 | Loss: 2.0077\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:21 INFO\u001b[0m Step 657/1000 | Loss: 3.1174\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:21 INFO\u001b[0m Step 657/1000 | Loss: 2.2663\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:22 INFO\u001b[0m Step 658/1000 | Loss: 2.2921\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:22 INFO\u001b[0m Step 658/1000 | Loss: 2.4972\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:22 INFO\u001b[0m Step 658/1000 | Loss: 2.2476\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:22 INFO\u001b[0m Step 658/1000 | Loss: 2.2374\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:22 INFO\u001b[0m Step 658/1000 | Loss: 2.7398\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:22 INFO\u001b[0m Step 658/1000 | Loss: 2.7753\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:22 INFO\u001b[0m Step 658/1000 | Loss: 2.8148\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:22 INFO\u001b[0m Step 658/1000 | Loss: 2.5925\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:23 INFO\u001b[0m Step 659/1000 | Loss: 1.9651\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:23 INFO\u001b[0m Step 659/1000 | Loss: 2.4775\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:23 INFO\u001b[0m Step 659/1000 | Loss: 2.5881\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:23 INFO\u001b[0m Step 659/1000 | Loss: 2.6008\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:23 INFO\u001b[0m Step 659/1000 | Loss: 2.4410\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:23 INFO\u001b[0m Step 659/1000 | Loss: 2.6191\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:23 INFO\u001b[0m Step 659/1000 | Loss: 2.5055\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:23 INFO\u001b[0m Step 659/1000 | Loss: 2.3776\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:25 INFO\u001b[0m Step 660/1000 | Loss: 2.8604\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:25 INFO\u001b[0m Step 660/1000 | Loss: 2.7201\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:25 INFO\u001b[0m Step 660/1000 | Loss: 3.0009\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:25 INFO\u001b[0m Step 660/1000 | Loss: 1.8433\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:25 INFO\u001b[0m Step 660/1000 | Loss: 2.4170\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:25 INFO\u001b[0m Step 660/1000 | Loss: 2.6609\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:25 INFO\u001b[0m Step 660/1000 | Loss: 2.8698\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:25 INFO\u001b[0m Step 660/1000 | Loss: 2.0662\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:28 INFO\u001b[0m Step 661/1000 | Loss: 2.4273\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:28 INFO\u001b[0m Step 661/1000 | Loss: 2.5002\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:28 INFO\u001b[0m Step 661/1000 | Loss: 2.1185\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:28 INFO\u001b[0m Step 661/1000 | Loss: 2.3409\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:28 INFO\u001b[0m Step 661/1000 | Loss: 2.7618\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:28 INFO\u001b[0m Step 661/1000 | Loss: 2.8318\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:28 INFO\u001b[0m Step 661/1000 | Loss: 2.3859\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:28 INFO\u001b[0m Step 661/1000 | Loss: 2.7511\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:29 INFO\u001b[0m Step 662/1000 | Loss: 2.0556\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:29 INFO\u001b[0m Step 662/1000 | Loss: 1.5934\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:29 INFO\u001b[0m Step 662/1000 | Loss: 2.6462\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:29 INFO\u001b[0m Step 662/1000 | Loss: 2.2386\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:29 INFO\u001b[0m Step 662/1000 | Loss: 1.9234\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:29 INFO\u001b[0m Step 662/1000 | Loss: 2.4468\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:29 INFO\u001b[0m Step 662/1000 | Loss: 1.8668\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:29 INFO\u001b[0m Step 662/1000 | Loss: 2.3601\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:30 INFO\u001b[0m Step 663/1000 | Loss: 2.2385\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:30 INFO\u001b[0m Step 663/1000 | Loss: 2.6223\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:30 INFO\u001b[0m Step 663/1000 | Loss: 2.2297\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:30 INFO\u001b[0m Step 663/1000 | Loss: 2.8921\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:30 INFO\u001b[0m Step 663/1000 | Loss: 2.2534\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:30 INFO\u001b[0m Step 663/1000 | Loss: 2.9512\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:30 INFO\u001b[0m Step 663/1000 | Loss: 1.9772\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:30 INFO\u001b[0m Step 663/1000 | Loss: 2.6822\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:30 INFO\u001b[0m Step 664/1000 | Loss: 2.6636\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:30 INFO\u001b[0m Step 664/1000 | Loss: 2.8197\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:30 INFO\u001b[0m Step 664/1000 | Loss: 2.6832\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:30 INFO\u001b[0m Step 664/1000 | Loss: 1.8946\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:30 INFO\u001b[0m Step 664/1000 | Loss: 2.3107\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:30 INFO\u001b[0m Step 664/1000 | Loss: 2.2323\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:30 INFO\u001b[0m Step 664/1000 | Loss: 2.8851\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:30 INFO\u001b[0m Step 664/1000 | Loss: 2.5101\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:30 INFO\u001b[0m Step 665/1000 | Loss: 2.5854\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:30 INFO\u001b[0m Step 665/1000 | Loss: 2.3353\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:30 INFO\u001b[0m Step 665/1000 | Loss: 2.4541\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:30 INFO\u001b[0m Step 665/1000 | Loss: 2.7889\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:30 INFO\u001b[0m Step 665/1000 | Loss: 2.4451\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:30 INFO\u001b[0m Step 665/1000 | Loss: 2.5952\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:30 INFO\u001b[0m Step 665/1000 | Loss: 2.4018\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:30 INFO\u001b[0m Step 665/1000 | Loss: 2.8822\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:31 INFO\u001b[0m Step 666/1000 | Loss: 2.5834\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:31 INFO\u001b[0m Step 666/1000 | Loss: 2.8900\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:31 INFO\u001b[0m Step 666/1000 | Loss: 2.7811\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:31 INFO\u001b[0m Step 666/1000 | Loss: 2.4454\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:31 INFO\u001b[0m Step 666/1000 | Loss: 2.5031\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:31 INFO\u001b[0m Step 666/1000 | Loss: 2.4630\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:31 INFO\u001b[0m Step 666/1000 | Loss: 2.1086\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:31 INFO\u001b[0m Step 666/1000 | Loss: 2.1275\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:31 INFO\u001b[0m Step 667/1000 | Loss: 2.5269\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:31 INFO\u001b[0m Step 667/1000 | Loss: 2.5441\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:31 INFO\u001b[0m Step 667/1000 | Loss: 2.7345\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:31 INFO\u001b[0m Step 667/1000 | Loss: 2.4887\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:31 INFO\u001b[0m Step 667/1000 | Loss: 2.9695\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:31 INFO\u001b[0m Step 667/1000 | Loss: 2.6022\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:31 INFO\u001b[0m Step 667/1000 | Loss: 2.5957\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:31 INFO\u001b[0m Step 667/1000 | Loss: 2.5557\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:32 INFO\u001b[0m Step 668/1000 | Loss: 2.6729\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:32 INFO\u001b[0m Step 668/1000 | Loss: 2.4297\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:32 INFO\u001b[0m Step 668/1000 | Loss: 2.2874\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:32 INFO\u001b[0m Step 668/1000 | Loss: 2.5724\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:32 INFO\u001b[0m Step 668/1000 | Loss: 2.9059\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:32 INFO\u001b[0m Step 668/1000 | Loss: 2.8770\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:32 INFO\u001b[0m Step 668/1000 | Loss: 2.4483\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:32 INFO\u001b[0m Step 668/1000 | Loss: 2.8598\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:32 INFO\u001b[0m Step 669/1000 | Loss: 2.8774\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:32 INFO\u001b[0m Step 669/1000 | Loss: 2.8125\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:32 INFO\u001b[0m Step 669/1000 | Loss: 2.6109\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:32 INFO\u001b[0m Step 669/1000 | Loss: 2.1826\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:32 INFO\u001b[0m Step 669/1000 | Loss: 2.2573\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:32 INFO\u001b[0m Step 669/1000 | Loss: 2.5624\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:32 INFO\u001b[0m Step 669/1000 | Loss: 3.1038\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:32 INFO\u001b[0m Step 669/1000 | Loss: 2.3185\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:32 INFO\u001b[0m Step 670/1000 | Loss: 2.0985\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:32 INFO\u001b[0m Step 670/1000 | Loss: 2.5706\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:32 INFO\u001b[0m Step 670/1000 | Loss: 2.7395\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:32 INFO\u001b[0m Step 670/1000 | Loss: 2.7380\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:32 INFO\u001b[0m Step 670/1000 | Loss: 3.0422\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:32 INFO\u001b[0m Step 670/1000 | Loss: 2.7272\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:32 INFO\u001b[0m Step 670/1000 | Loss: 2.5944\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:32 INFO\u001b[0m Step 670/1000 | Loss: 2.3375\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:33 INFO\u001b[0m Step 671/1000 | Loss: 3.4962\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:33 INFO\u001b[0m Step 671/1000 | Loss: 2.2962\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:33 INFO\u001b[0m Step 671/1000 | Loss: 2.0301\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:33 INFO\u001b[0m Step 671/1000 | Loss: 2.8506\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:33 INFO\u001b[0m Step 671/1000 | Loss: 2.9614\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:33 INFO\u001b[0m Step 671/1000 | Loss: 3.0318\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:33 INFO\u001b[0m Step 671/1000 | Loss: 3.1847\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:33 INFO\u001b[0m Step 671/1000 | Loss: 2.4576\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:33 INFO\u001b[0m Step 672/1000 | Loss: 2.6082\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:33 INFO\u001b[0m Step 672/1000 | Loss: 2.6645\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:33 INFO\u001b[0m Step 672/1000 | Loss: 2.8625\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:33 INFO\u001b[0m Step 672/1000 | Loss: 2.7902\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:33 INFO\u001b[0m Step 672/1000 | Loss: 1.8807\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:33 INFO\u001b[0m Step 672/1000 | Loss: 2.7885\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:33 INFO\u001b[0m Step 672/1000 | Loss: 2.0391\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:33 INFO\u001b[0m Step 672/1000 | Loss: 2.3818\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:34 INFO\u001b[0m Step 673/1000 | Loss: 2.3894\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:34 INFO\u001b[0m Step 673/1000 | Loss: 2.2716\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:34 INFO\u001b[0m Step 673/1000 | Loss: 2.3749\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:34 INFO\u001b[0m Step 673/1000 | Loss: 2.5801\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:34 INFO\u001b[0m Step 673/1000 | Loss: 2.7689\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:34 INFO\u001b[0m Step 673/1000 | Loss: 2.9091\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:34 INFO\u001b[0m Step 673/1000 | Loss: 2.3913\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:34 INFO\u001b[0m Step 673/1000 | Loss: 2.7467\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:34 INFO\u001b[0m Step 674/1000 | Loss: 2.4342\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:34 INFO\u001b[0m Step 674/1000 | Loss: 1.8433\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:34 INFO\u001b[0m Step 674/1000 | Loss: 2.8274\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:34 INFO\u001b[0m Step 674/1000 | Loss: 3.3985\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:34 INFO\u001b[0m Step 674/1000 | Loss: 2.2936\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:34 INFO\u001b[0m Step 674/1000 | Loss: 2.3345\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:34 INFO\u001b[0m Step 674/1000 | Loss: 2.4378\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:34 INFO\u001b[0m Step 674/1000 | Loss: 2.3278\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:34 INFO\u001b[0m Step 675/1000 | Loss: 2.3556\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:34 INFO\u001b[0m Step 675/1000 | Loss: 2.2588\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:34 INFO\u001b[0m Step 675/1000 | Loss: 2.7714\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:34 INFO\u001b[0m Step 675/1000 | Loss: 2.6013\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:34 INFO\u001b[0m Step 675/1000 | Loss: 2.4844\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:34 INFO\u001b[0m Step 675/1000 | Loss: 2.4329\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:34 INFO\u001b[0m Step 675/1000 | Loss: 2.3730\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:34 INFO\u001b[0m Step 675/1000 | Loss: 2.3896\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:35 INFO\u001b[0m Step 676/1000 | Loss: 2.6920\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:35 INFO\u001b[0m Step 676/1000 | Loss: 2.2283\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:35 INFO\u001b[0m Step 676/1000 | Loss: 2.1031\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:35 INFO\u001b[0m Step 676/1000 | Loss: 2.5653\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:35 INFO\u001b[0m Step 676/1000 | Loss: 2.1272\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:35 INFO\u001b[0m Step 676/1000 | Loss: 2.2189\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:35 INFO\u001b[0m Step 676/1000 | Loss: 2.6997\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:35 INFO\u001b[0m Step 676/1000 | Loss: 2.7295\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:35 INFO\u001b[0m Step 677/1000 | Loss: 2.2724\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:35 INFO\u001b[0m Step 677/1000 | Loss: 2.6796\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:35 INFO\u001b[0m Step 677/1000 | Loss: 2.3264\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:35 INFO\u001b[0m Step 677/1000 | Loss: 2.3900\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:35 INFO\u001b[0m Step 677/1000 | Loss: 2.3959\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:35 INFO\u001b[0m Step 677/1000 | Loss: 2.8744\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:35 INFO\u001b[0m Step 677/1000 | Loss: 2.7916\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:35 INFO\u001b[0m Step 677/1000 | Loss: 1.8904\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:36 INFO\u001b[0m Step 678/1000 | Loss: 2.8591\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:36 INFO\u001b[0m Step 678/1000 | Loss: 2.0792\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:36 INFO\u001b[0m Step 678/1000 | Loss: 2.3815\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:36 INFO\u001b[0m Step 678/1000 | Loss: 2.3127\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:36 INFO\u001b[0m Step 678/1000 | Loss: 2.3648\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:36 INFO\u001b[0m Step 678/1000 | Loss: 2.3441\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:36 INFO\u001b[0m Step 678/1000 | Loss: 2.6193\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:36 INFO\u001b[0m Step 678/1000 | Loss: 2.5332\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:36 INFO\u001b[0m Step 679/1000 | Loss: 2.3071\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:36 INFO\u001b[0m Step 679/1000 | Loss: 2.1236\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:36 INFO\u001b[0m Step 679/1000 | Loss: 2.2220\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:36 INFO\u001b[0m Step 679/1000 | Loss: 2.1642\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:36 INFO\u001b[0m Step 679/1000 | Loss: 2.6443\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:36 INFO\u001b[0m Step 679/1000 | Loss: 2.2280\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:36 INFO\u001b[0m Step 679/1000 | Loss: 2.1714\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:36 INFO\u001b[0m Step 679/1000 | Loss: 2.5842\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:36 INFO\u001b[0m Step 680/1000 | Loss: 2.2054\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:36 INFO\u001b[0m Step 680/1000 | Loss: 1.9091\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:36 INFO\u001b[0m Step 680/1000 | Loss: 2.0035\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:36 INFO\u001b[0m Step 680/1000 | Loss: 2.4723\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:36 INFO\u001b[0m Step 680/1000 | Loss: 2.6823\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:36 INFO\u001b[0m Step 680/1000 | Loss: 2.5238\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:36 INFO\u001b[0m Step 680/1000 | Loss: 2.6172\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:36 INFO\u001b[0m Step 680/1000 | Loss: 2.4133\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:37 INFO\u001b[0m Step 681/1000 | Loss: 2.1732\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:37 INFO\u001b[0m Step 681/1000 | Loss: 2.9018\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:37 INFO\u001b[0m Step 681/1000 | Loss: 2.2665\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:37 INFO\u001b[0m Step 681/1000 | Loss: 2.2552\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:37 INFO\u001b[0m Step 681/1000 | Loss: 2.1038\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:37 INFO\u001b[0m Step 681/1000 | Loss: 1.9887\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:37 INFO\u001b[0m Step 681/1000 | Loss: 2.1135\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:37 INFO\u001b[0m Step 681/1000 | Loss: 2.3195\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:37 INFO\u001b[0m Step 682/1000 | Loss: 2.5581\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:37 INFO\u001b[0m Step 682/1000 | Loss: 2.3628\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:37 INFO\u001b[0m Step 682/1000 | Loss: 2.3313\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:37 INFO\u001b[0m Step 682/1000 | Loss: 2.3438\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:37 INFO\u001b[0m Step 682/1000 | Loss: 2.7776\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:37 INFO\u001b[0m Step 682/1000 | Loss: 2.4643\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:37 INFO\u001b[0m Step 682/1000 | Loss: 1.8986\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:37 INFO\u001b[0m Step 682/1000 | Loss: 2.5578\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:38 INFO\u001b[0m Step 683/1000 | Loss: 2.6490\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:38 INFO\u001b[0m Step 683/1000 | Loss: 2.5772\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:38 INFO\u001b[0m Step 683/1000 | Loss: 2.2196\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:38 INFO\u001b[0m Step 683/1000 | Loss: 2.7538\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:38 INFO\u001b[0m Step 683/1000 | Loss: 2.2486\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:38 INFO\u001b[0m Step 683/1000 | Loss: 2.3622\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:38 INFO\u001b[0m Step 683/1000 | Loss: 2.4131\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:38 INFO\u001b[0m Step 683/1000 | Loss: 2.3769\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:38 INFO\u001b[0m Step 684/1000 | Loss: 2.2333\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:38 INFO\u001b[0m Step 684/1000 | Loss: 2.0170\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:38 INFO\u001b[0m Step 684/1000 | Loss: 2.2403\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:38 INFO\u001b[0m Step 684/1000 | Loss: 2.3835\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:38 INFO\u001b[0m Step 684/1000 | Loss: 2.2820\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:38 INFO\u001b[0m Step 684/1000 | Loss: 2.5102\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:38 INFO\u001b[0m Step 684/1000 | Loss: 2.6266\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:38 INFO\u001b[0m Step 684/1000 | Loss: 2.5741\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:39 INFO\u001b[0m Step 685/1000 | Loss: 2.3721\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:39 INFO\u001b[0m Step 685/1000 | Loss: 2.8788\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:39 INFO\u001b[0m Step 685/1000 | Loss: 2.3428\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:39 INFO\u001b[0m Step 685/1000 | Loss: 2.7610\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:39 INFO\u001b[0m Step 685/1000 | Loss: 2.1249\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:39 INFO\u001b[0m Step 685/1000 | Loss: 2.6823\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:39 INFO\u001b[0m Step 685/1000 | Loss: 2.5135\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:39 INFO\u001b[0m Step 685/1000 | Loss: 2.5986\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:39 INFO\u001b[0m Step 686/1000 | Loss: 2.3534\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:39 INFO\u001b[0m Step 686/1000 | Loss: 1.9517\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:39 INFO\u001b[0m Step 686/1000 | Loss: 2.5935\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:39 INFO\u001b[0m Step 686/1000 | Loss: 2.1291\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:39 INFO\u001b[0m Step 686/1000 | Loss: 2.0103\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:39 INFO\u001b[0m Step 686/1000 | Loss: 2.0285\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:39 INFO\u001b[0m Step 686/1000 | Loss: 2.7358\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:39 INFO\u001b[0m Step 686/1000 | Loss: 2.5175\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:39 INFO\u001b[0m Step 687/1000 | Loss: 2.6923\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:39 INFO\u001b[0m Step 687/1000 | Loss: 2.5078\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:39 INFO\u001b[0m Step 687/1000 | Loss: 3.0863\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:39 INFO\u001b[0m Step 687/1000 | Loss: 2.0606\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:39 INFO\u001b[0m Step 687/1000 | Loss: 3.2611\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:39 INFO\u001b[0m Step 687/1000 | Loss: 2.8508\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:39 INFO\u001b[0m Step 687/1000 | Loss: 2.0914\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:39 INFO\u001b[0m Step 687/1000 | Loss: 2.7752\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:40 INFO\u001b[0m Step 688/1000 | Loss: 2.0735\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:40 INFO\u001b[0m Step 688/1000 | Loss: 2.3770\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:40 INFO\u001b[0m Step 688/1000 | Loss: 2.4301\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:40 INFO\u001b[0m Step 688/1000 | Loss: 2.5212\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:40 INFO\u001b[0m Step 688/1000 | Loss: 2.2296\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:40 INFO\u001b[0m Step 688/1000 | Loss: 2.2160\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:40 INFO\u001b[0m Step 688/1000 | Loss: 2.8852\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:40 INFO\u001b[0m Step 688/1000 | Loss: 2.4709\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:40 INFO\u001b[0m Step 689/1000 | Loss: 2.3311\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:40 INFO\u001b[0m Step 689/1000 | Loss: 2.3765\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:40 INFO\u001b[0m Step 689/1000 | Loss: 2.6840\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:40 INFO\u001b[0m Step 689/1000 | Loss: 2.3660\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:40 INFO\u001b[0m Step 689/1000 | Loss: 2.3552\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:40 INFO\u001b[0m Step 689/1000 | Loss: 2.2770\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:40 INFO\u001b[0m Step 689/1000 | Loss: 2.4032\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:40 INFO\u001b[0m Step 689/1000 | Loss: 2.3580\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:41 INFO\u001b[0m Step 690/1000 | Loss: 2.2029\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:41 INFO\u001b[0m Step 690/1000 | Loss: 3.4244\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:41 INFO\u001b[0m Step 690/1000 | Loss: 1.9532\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:41 INFO\u001b[0m Step 690/1000 | Loss: 2.2951\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:41 INFO\u001b[0m Step 690/1000 | Loss: 2.0256\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:41 INFO\u001b[0m Step 690/1000 | Loss: 2.1554\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:41 INFO\u001b[0m Step 690/1000 | Loss: 2.2691\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:41 INFO\u001b[0m Step 690/1000 | Loss: 2.5592\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:41 INFO\u001b[0m Step 691/1000 | Loss: 3.0855\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:41 INFO\u001b[0m Step 691/1000 | Loss: 1.8679\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:41 INFO\u001b[0m Step 691/1000 | Loss: 2.6149\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:41 INFO\u001b[0m Step 691/1000 | Loss: 2.4468\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:41 INFO\u001b[0m Step 691/1000 | Loss: 2.1835\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:41 INFO\u001b[0m Step 691/1000 | Loss: 1.9989\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:41 INFO\u001b[0m Step 691/1000 | Loss: 1.7860\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:41 INFO\u001b[0m Step 691/1000 | Loss: 3.2925\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:41 INFO\u001b[0m Step 692/1000 | Loss: 2.4239\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:41 INFO\u001b[0m Step 692/1000 | Loss: 2.2176\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:41 INFO\u001b[0m Step 692/1000 | Loss: 2.6635\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:41 INFO\u001b[0m Step 692/1000 | Loss: 2.8345\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:41 INFO\u001b[0m Step 692/1000 | Loss: 2.7028\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:41 INFO\u001b[0m Step 692/1000 | Loss: 2.3828\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:41 INFO\u001b[0m Step 692/1000 | Loss: 2.5087\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:41 INFO\u001b[0m Step 692/1000 | Loss: 2.3047\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:42 INFO\u001b[0m Step 693/1000 | Loss: 2.5457\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:42 INFO\u001b[0m Step 693/1000 | Loss: 2.2190\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:42 INFO\u001b[0m Step 693/1000 | Loss: 2.9254\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:42 INFO\u001b[0m Step 693/1000 | Loss: 2.7298\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:42 INFO\u001b[0m Step 693/1000 | Loss: 2.1079\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:42 INFO\u001b[0m Step 693/1000 | Loss: 2.6111\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:42 INFO\u001b[0m Step 693/1000 | Loss: 2.1517\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:42 INFO\u001b[0m Step 693/1000 | Loss: 2.5721\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:42 INFO\u001b[0m Step 694/1000 | Loss: 2.2501\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:42 INFO\u001b[0m Step 694/1000 | Loss: 2.5949\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:42 INFO\u001b[0m Step 694/1000 | Loss: 3.0851\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:42 INFO\u001b[0m Step 694/1000 | Loss: 2.1767\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:42 INFO\u001b[0m Step 694/1000 | Loss: 2.1834\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:42 INFO\u001b[0m Step 694/1000 | Loss: 2.2871\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:42 INFO\u001b[0m Step 694/1000 | Loss: 2.8191\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:42 INFO\u001b[0m Step 694/1000 | Loss: 2.3211\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:43 INFO\u001b[0m Step 695/1000 | Loss: 2.7625\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:43 INFO\u001b[0m Step 695/1000 | Loss: 2.6330\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:43 INFO\u001b[0m Step 695/1000 | Loss: 2.8695\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:43 INFO\u001b[0m Step 695/1000 | Loss: 2.5423\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:43 INFO\u001b[0m Step 695/1000 | Loss: 2.0989\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:43 INFO\u001b[0m Step 695/1000 | Loss: 2.3201\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:43 INFO\u001b[0m Step 695/1000 | Loss: 2.1760\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:43 INFO\u001b[0m Step 695/1000 | Loss: 2.2145\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:43 INFO\u001b[0m Step 696/1000 | Loss: 2.3496\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:43 INFO\u001b[0m Step 696/1000 | Loss: 2.2721\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:43 INFO\u001b[0m Step 696/1000 | Loss: 2.7103\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:43 INFO\u001b[0m Step 696/1000 | Loss: 2.7337\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:43 INFO\u001b[0m Step 696/1000 | Loss: 2.4179\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:43 INFO\u001b[0m Step 696/1000 | Loss: 2.0602\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:43 INFO\u001b[0m Step 696/1000 | Loss: 2.0013\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:43 INFO\u001b[0m Step 696/1000 | Loss: 2.6998\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:43 INFO\u001b[0m Step 697/1000 | Loss: 2.4212\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:43 INFO\u001b[0m Step 697/1000 | Loss: 1.8193\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:43 INFO\u001b[0m Step 697/1000 | Loss: 2.5855\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:43 INFO\u001b[0m Step 697/1000 | Loss: 2.4784\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:43 INFO\u001b[0m Step 697/1000 | Loss: 2.2623\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:43 INFO\u001b[0m Step 697/1000 | Loss: 2.9245\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:43 INFO\u001b[0m Step 697/1000 | Loss: 2.2860\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:43 INFO\u001b[0m Step 697/1000 | Loss: 3.5209\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:44 INFO\u001b[0m Step 698/1000 | Loss: 2.5516\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:44 INFO\u001b[0m Step 698/1000 | Loss: 1.9632\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:44 INFO\u001b[0m Step 698/1000 | Loss: 2.3112\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:44 INFO\u001b[0m Step 698/1000 | Loss: 2.4046\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:44 INFO\u001b[0m Step 698/1000 | Loss: 2.2298\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:44 INFO\u001b[0m Step 698/1000 | Loss: 2.0423\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:44 INFO\u001b[0m Step 698/1000 | Loss: 2.1553\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:44 INFO\u001b[0m Step 698/1000 | Loss: 2.9022\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:44 INFO\u001b[0m Step 699/1000 | Loss: 2.5749\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:44 INFO\u001b[0m Step 699/1000 | Loss: 2.4797\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:44 INFO\u001b[0m Step 699/1000 | Loss: 2.4363\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:44 INFO\u001b[0m Step 699/1000 | Loss: 2.6873\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:44 INFO\u001b[0m Step 699/1000 | Loss: 2.7754\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:44 INFO\u001b[0m Step 699/1000 | Loss: 2.7894\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:44 INFO\u001b[0m Step 699/1000 | Loss: 2.4569\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:44 INFO\u001b[0m Step 699/1000 | Loss: 1.9193\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:45 INFO\u001b[0m Step 700/1000 | Loss: 2.1859\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:45 INFO\u001b[0m Step 700/1000 | Loss: 2.4786\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:45 INFO\u001b[0m Step 700/1000 | Loss: 2.9851\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:45 INFO\u001b[0m Step 700/1000 | Loss: 2.0931\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:45 INFO\u001b[0m Step 700/1000 | Loss: 2.2268\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:45 INFO\u001b[0m Step 700/1000 | Loss: 2.7890\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:45 INFO\u001b[0m Step 700/1000 | Loss: 2.2901\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:45 INFO\u001b[0m Step 700/1000 | Loss: 2.2096\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:45 INFO\u001b[0m Step 701/1000 | Loss: 2.5045\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:45 INFO\u001b[0m Step 701/1000 | Loss: 2.4821\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:45 INFO\u001b[0m Step 701/1000 | Loss: 2.3825\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:45 INFO\u001b[0m Step 701/1000 | Loss: 2.5436\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:45 INFO\u001b[0m Step 701/1000 | Loss: 2.4296\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:45 INFO\u001b[0m Step 701/1000 | Loss: 2.4273\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:45 INFO\u001b[0m Step 701/1000 | Loss: 2.5030\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:45 INFO\u001b[0m Step 701/1000 | Loss: 2.3467\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:45 INFO\u001b[0m Step 702/1000 | Loss: 2.3399\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:45 INFO\u001b[0m Step 702/1000 | Loss: 2.2524\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:45 INFO\u001b[0m Step 702/1000 | Loss: 2.1678\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:45 INFO\u001b[0m Step 702/1000 | Loss: 2.0943\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:45 INFO\u001b[0m Step 702/1000 | Loss: 3.6045\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:45 INFO\u001b[0m Step 702/1000 | Loss: 2.1426\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:45 INFO\u001b[0m Step 702/1000 | Loss: 2.3280\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:45 INFO\u001b[0m Step 702/1000 | Loss: 2.3235\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:46 INFO\u001b[0m Step 703/1000 | Loss: 2.1238\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:46 INFO\u001b[0m Step 703/1000 | Loss: 2.3242\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:46 INFO\u001b[0m Step 703/1000 | Loss: 2.4682\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:46 INFO\u001b[0m Step 703/1000 | Loss: 2.5456\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:46 INFO\u001b[0m Step 703/1000 | Loss: 2.1885\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:46 INFO\u001b[0m Step 703/1000 | Loss: 2.5493\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:46 INFO\u001b[0m Step 703/1000 | Loss: 2.4913\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:46 INFO\u001b[0m Step 703/1000 | Loss: 2.3427\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:46 INFO\u001b[0m Step 704/1000 | Loss: 2.2217\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:46 INFO\u001b[0m Step 704/1000 | Loss: 2.1297\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:46 INFO\u001b[0m Step 704/1000 | Loss: 2.1308\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:46 INFO\u001b[0m Step 704/1000 | Loss: 3.0702\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:46 INFO\u001b[0m Step 704/1000 | Loss: 2.6836\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:46 INFO\u001b[0m Step 704/1000 | Loss: 2.4798\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:46 INFO\u001b[0m Step 704/1000 | Loss: 2.6914\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:46 INFO\u001b[0m Step 704/1000 | Loss: 2.4822\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:47 INFO\u001b[0m Step 705/1000 | Loss: 2.2927\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:47 INFO\u001b[0m Step 705/1000 | Loss: 2.1264\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:47 INFO\u001b[0m Step 705/1000 | Loss: 2.3817\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:47 INFO\u001b[0m Step 705/1000 | Loss: 2.4215\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:47 INFO\u001b[0m Step 705/1000 | Loss: 2.4706\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:47 INFO\u001b[0m Step 705/1000 | Loss: 3.0365\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:47 INFO\u001b[0m Step 705/1000 | Loss: 2.1340\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:47 INFO\u001b[0m Step 705/1000 | Loss: 2.0291\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:47 INFO\u001b[0m Step 706/1000 | Loss: 2.3801\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:47 INFO\u001b[0m Step 706/1000 | Loss: 2.5875\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:47 INFO\u001b[0m Step 706/1000 | Loss: 2.7274\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:47 INFO\u001b[0m Step 706/1000 | Loss: 1.7962\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:47 INFO\u001b[0m Step 706/1000 | Loss: 2.8250\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:47 INFO\u001b[0m Step 706/1000 | Loss: 2.3712\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:47 INFO\u001b[0m Step 706/1000 | Loss: 2.6063\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:47 INFO\u001b[0m Step 706/1000 | Loss: 2.5702\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:47 INFO\u001b[0m Step 707/1000 | Loss: 2.6155\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:47 INFO\u001b[0m Step 707/1000 | Loss: 2.9792\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:47 INFO\u001b[0m Step 707/1000 | Loss: 2.3749\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:47 INFO\u001b[0m Step 707/1000 | Loss: 2.6180\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:47 INFO\u001b[0m Step 707/1000 | Loss: 2.3655\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:47 INFO\u001b[0m Step 707/1000 | Loss: 3.1155\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:47 INFO\u001b[0m Step 707/1000 | Loss: 2.1321\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:47 INFO\u001b[0m Step 707/1000 | Loss: 2.3755\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:48 INFO\u001b[0m Step 708/1000 | Loss: 3.2907\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:48 INFO\u001b[0m Step 708/1000 | Loss: 2.5752\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:48 INFO\u001b[0m Step 708/1000 | Loss: 2.3239\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:48 INFO\u001b[0m Step 708/1000 | Loss: 2.5241\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:48 INFO\u001b[0m Step 708/1000 | Loss: 2.1810\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:48 INFO\u001b[0m Step 708/1000 | Loss: 2.9478\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:48 INFO\u001b[0m Step 708/1000 | Loss: 1.8588\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:48 INFO\u001b[0m Step 708/1000 | Loss: 2.5514\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:48 INFO\u001b[0m Step 709/1000 | Loss: 2.4599\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:48 INFO\u001b[0m Step 709/1000 | Loss: 2.3864\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:48 INFO\u001b[0m Step 709/1000 | Loss: 2.3473\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:48 INFO\u001b[0m Step 709/1000 | Loss: 2.0859\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:48 INFO\u001b[0m Step 709/1000 | Loss: 2.3598\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:48 INFO\u001b[0m Step 709/1000 | Loss: 2.2754\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:48 INFO\u001b[0m Step 709/1000 | Loss: 2.6573\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:48 INFO\u001b[0m Step 709/1000 | Loss: 2.9008\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:49 INFO\u001b[0m Step 710/1000 | Loss: 2.3978\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:49 INFO\u001b[0m Step 710/1000 | Loss: 2.0398\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:49 INFO\u001b[0m Step 710/1000 | Loss: 2.4225\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:49 INFO\u001b[0m Step 710/1000 | Loss: 2.4752\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:49 INFO\u001b[0m Step 710/1000 | Loss: 2.4402\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:49 INFO\u001b[0m Step 710/1000 | Loss: 2.3187\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:49 INFO\u001b[0m Step 710/1000 | Loss: 2.2888\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:49 INFO\u001b[0m Step 710/1000 | Loss: 2.0028\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:49 INFO\u001b[0m Step 711/1000 | Loss: 2.4629\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:49 INFO\u001b[0m Step 711/1000 | Loss: 2.6788\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:49 INFO\u001b[0m Step 711/1000 | Loss: 2.3098\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:49 INFO\u001b[0m Step 711/1000 | Loss: 3.4035\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:49 INFO\u001b[0m Step 711/1000 | Loss: 1.8963\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:49 INFO\u001b[0m Step 711/1000 | Loss: 2.5180\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:49 INFO\u001b[0m Step 711/1000 | Loss: 2.2334\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:49 INFO\u001b[0m Step 711/1000 | Loss: 2.3641\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:49 INFO\u001b[0m Step 712/1000 | Loss: 2.2535\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:49 INFO\u001b[0m Step 712/1000 | Loss: 2.2275\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:49 INFO\u001b[0m Step 712/1000 | Loss: 2.7595\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:49 INFO\u001b[0m Step 712/1000 | Loss: 2.3696\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:49 INFO\u001b[0m Step 712/1000 | Loss: 2.7113\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:49 INFO\u001b[0m Step 712/1000 | Loss: 2.5528\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:49 INFO\u001b[0m Step 712/1000 | Loss: 2.8633\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:49 INFO\u001b[0m Step 712/1000 | Loss: 2.6332\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:50 INFO\u001b[0m Step 713/1000 | Loss: 2.1895\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:50 INFO\u001b[0m Step 713/1000 | Loss: 2.0847\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:50 INFO\u001b[0m Step 713/1000 | Loss: 2.2873\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:50 INFO\u001b[0m Step 713/1000 | Loss: 2.5195\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:50 INFO\u001b[0m Step 713/1000 | Loss: 1.8722\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:50 INFO\u001b[0m Step 713/1000 | Loss: 2.0079\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:50 INFO\u001b[0m Step 713/1000 | Loss: 2.6895\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:50 INFO\u001b[0m Step 713/1000 | Loss: 2.4372\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:50 INFO\u001b[0m Step 714/1000 | Loss: 2.6019\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:50 INFO\u001b[0m Step 714/1000 | Loss: 2.6076\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:50 INFO\u001b[0m Step 714/1000 | Loss: 2.5421\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:50 INFO\u001b[0m Step 714/1000 | Loss: 2.0296\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:50 INFO\u001b[0m Step 714/1000 | Loss: 2.2685\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:50 INFO\u001b[0m Step 714/1000 | Loss: 2.2467\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:50 INFO\u001b[0m Step 714/1000 | Loss: 2.2265\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:50 INFO\u001b[0m Step 714/1000 | Loss: 2.6850\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:51 INFO\u001b[0m Step 715/1000 | Loss: 1.9780\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:51 INFO\u001b[0m Step 715/1000 | Loss: 2.1772\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:51 INFO\u001b[0m Step 715/1000 | Loss: 2.4905\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:51 INFO\u001b[0m Step 715/1000 | Loss: 2.2230\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:51 INFO\u001b[0m Step 715/1000 | Loss: 2.2915\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:51 INFO\u001b[0m Step 715/1000 | Loss: 1.9819\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:51 INFO\u001b[0m Step 715/1000 | Loss: 2.1998\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:51 INFO\u001b[0m Step 715/1000 | Loss: 2.1871\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:51 INFO\u001b[0m Step 716/1000 | Loss: 2.2663\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:51 INFO\u001b[0m Step 716/1000 | Loss: 3.2827\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:51 INFO\u001b[0m Step 716/1000 | Loss: 2.4790\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:51 INFO\u001b[0m Step 716/1000 | Loss: 2.2071\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:51 INFO\u001b[0m Step 716/1000 | Loss: 2.3439\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:51 INFO\u001b[0m Step 716/1000 | Loss: 2.3815\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:51 INFO\u001b[0m Step 716/1000 | Loss: 2.1352\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:51 INFO\u001b[0m Step 716/1000 | Loss: 2.5454\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:51 INFO\u001b[0m Step 717/1000 | Loss: 2.2767\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:51 INFO\u001b[0m Step 717/1000 | Loss: 2.3301\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:51 INFO\u001b[0m Step 717/1000 | Loss: 2.4961\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:51 INFO\u001b[0m Step 717/1000 | Loss: 2.5734\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:51 INFO\u001b[0m Step 717/1000 | Loss: 2.3275\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:51 INFO\u001b[0m Step 717/1000 | Loss: 2.3072\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:51 INFO\u001b[0m Step 717/1000 | Loss: 2.3661\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:51 INFO\u001b[0m Step 717/1000 | Loss: 2.7023\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:52 INFO\u001b[0m Step 718/1000 | Loss: 2.0333\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:52 INFO\u001b[0m Step 718/1000 | Loss: 1.9243\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:52 INFO\u001b[0m Step 718/1000 | Loss: 2.4140\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:52 INFO\u001b[0m Step 718/1000 | Loss: 2.5874\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:52 INFO\u001b[0m Step 718/1000 | Loss: 2.0300\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:52 INFO\u001b[0m Step 718/1000 | Loss: 2.5625\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:52 INFO\u001b[0m Step 718/1000 | Loss: 2.1886\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:52 INFO\u001b[0m Step 718/1000 | Loss: 2.3912\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:52 INFO\u001b[0m Step 719/1000 | Loss: 2.3723\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:52 INFO\u001b[0m Step 719/1000 | Loss: 1.8310\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:52 INFO\u001b[0m Step 719/1000 | Loss: 2.4589\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:52 INFO\u001b[0m Step 719/1000 | Loss: 1.9113\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:52 INFO\u001b[0m Step 719/1000 | Loss: 2.2736\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:52 INFO\u001b[0m Step 719/1000 | Loss: 1.8987\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:52 INFO\u001b[0m Step 719/1000 | Loss: 2.6728\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:52 INFO\u001b[0m Step 719/1000 | Loss: 2.6616\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:53 INFO\u001b[0m Step 720/1000 | Loss: 1.7635\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:53 INFO\u001b[0m Step 720/1000 | Loss: 2.8302\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:53 INFO\u001b[0m Step 720/1000 | Loss: 2.1851\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:53 INFO\u001b[0m Step 720/1000 | Loss: 2.4836\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:53 INFO\u001b[0m Step 720/1000 | Loss: 2.1326\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:53 INFO\u001b[0m Step 720/1000 | Loss: 2.7108\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:53 INFO\u001b[0m Step 720/1000 | Loss: 2.5665\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:53 INFO\u001b[0m Step 720/1000 | Loss: 2.3712\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:53 INFO\u001b[0m Step 721/1000 | Loss: 2.0965\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:53 INFO\u001b[0m Step 721/1000 | Loss: 2.4998\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:53 INFO\u001b[0m Step 721/1000 | Loss: 2.2298\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:53 INFO\u001b[0m Step 721/1000 | Loss: 1.7831\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:53 INFO\u001b[0m Step 721/1000 | Loss: 2.2699\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:53 INFO\u001b[0m Step 721/1000 | Loss: 2.3947\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:53 INFO\u001b[0m Step 721/1000 | Loss: 2.3191\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:53 INFO\u001b[0m Step 721/1000 | Loss: 2.1830\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:53 INFO\u001b[0m Step 722/1000 | Loss: 2.1263\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:53 INFO\u001b[0m Step 722/1000 | Loss: 2.3012\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:53 INFO\u001b[0m Step 722/1000 | Loss: 2.3479\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:53 INFO\u001b[0m Step 722/1000 | Loss: 1.8391\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:53 INFO\u001b[0m Step 722/1000 | Loss: 2.3910\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:53 INFO\u001b[0m Step 722/1000 | Loss: 2.2310\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:53 INFO\u001b[0m Step 722/1000 | Loss: 2.4587\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:53 INFO\u001b[0m Step 722/1000 | Loss: 2.5495\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:54 INFO\u001b[0m Step 723/1000 | Loss: 2.5208\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:54 INFO\u001b[0m Step 723/1000 | Loss: 2.3727\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:54 INFO\u001b[0m Step 723/1000 | Loss: 2.1891\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:54 INFO\u001b[0m Step 723/1000 | Loss: 1.9806\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:54 INFO\u001b[0m Step 723/1000 | Loss: 2.2001\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:54 INFO\u001b[0m Step 723/1000 | Loss: 2.6245\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:54 INFO\u001b[0m Step 723/1000 | Loss: 2.4772\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:54 INFO\u001b[0m Step 723/1000 | Loss: 2.0206\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:54 INFO\u001b[0m Step 724/1000 | Loss: 2.9753\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:54 INFO\u001b[0m Step 724/1000 | Loss: 2.3356\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:54 INFO\u001b[0m Step 724/1000 | Loss: 1.9987\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:54 INFO\u001b[0m Step 724/1000 | Loss: 2.3131\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:54 INFO\u001b[0m Step 724/1000 | Loss: 2.6113\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:54 INFO\u001b[0m Step 724/1000 | Loss: 1.5350\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:54 INFO\u001b[0m Step 724/1000 | Loss: 2.3511\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:54 INFO\u001b[0m Step 724/1000 | Loss: 2.9841\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:55 INFO\u001b[0m Step 725/1000 | Loss: 2.3303\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:55 INFO\u001b[0m Step 725/1000 | Loss: 1.8835\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:55 INFO\u001b[0m Step 725/1000 | Loss: 2.2536\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:55 INFO\u001b[0m Step 725/1000 | Loss: 2.2463\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:55 INFO\u001b[0m Step 725/1000 | Loss: 2.7438\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:55 INFO\u001b[0m Step 725/1000 | Loss: 2.4954\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:55 INFO\u001b[0m Step 725/1000 | Loss: 1.9849\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:55 INFO\u001b[0m Step 725/1000 | Loss: 2.2107\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:55 INFO\u001b[0m Step 726/1000 | Loss: 1.9572\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:55 INFO\u001b[0m Step 726/1000 | Loss: 2.3693\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:55 INFO\u001b[0m Step 726/1000 | Loss: 2.1286\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:55 INFO\u001b[0m Step 726/1000 | Loss: 2.8252\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:55 INFO\u001b[0m Step 726/1000 | Loss: 3.1788\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:55 INFO\u001b[0m Step 726/1000 | Loss: 2.2013\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:55 INFO\u001b[0m Step 726/1000 | Loss: 2.0460\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:55 INFO\u001b[0m Step 726/1000 | Loss: 2.0656\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:55 INFO\u001b[0m Step 727/1000 | Loss: 2.7507\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:55 INFO\u001b[0m Step 727/1000 | Loss: 2.2055\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:55 INFO\u001b[0m Step 727/1000 | Loss: 2.2905\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:55 INFO\u001b[0m Step 727/1000 | Loss: 2.0914\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:55 INFO\u001b[0m Step 727/1000 | Loss: 2.0140\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:55 INFO\u001b[0m Step 727/1000 | Loss: 1.8308\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:55 INFO\u001b[0m Step 727/1000 | Loss: 2.2192\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:55 INFO\u001b[0m Step 727/1000 | Loss: 2.6675\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:56 INFO\u001b[0m Step 728/1000 | Loss: 2.7234\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:56 INFO\u001b[0m Step 728/1000 | Loss: 2.4542\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:56 INFO\u001b[0m Step 728/1000 | Loss: 2.4455\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:56 INFO\u001b[0m Step 728/1000 | Loss: 2.4330\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:56 INFO\u001b[0m Step 728/1000 | Loss: 2.8589\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:56 INFO\u001b[0m Step 728/1000 | Loss: 2.3191\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:56 INFO\u001b[0m Step 728/1000 | Loss: 2.1238\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:56 INFO\u001b[0m Step 728/1000 | Loss: 2.2652\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:56 INFO\u001b[0m Step 729/1000 | Loss: 2.3747\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:56 INFO\u001b[0m Step 729/1000 | Loss: 1.9752\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:56 INFO\u001b[0m Step 729/1000 | Loss: 2.1622\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:56 INFO\u001b[0m Step 729/1000 | Loss: 2.1730\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:56 INFO\u001b[0m Step 729/1000 | Loss: 1.8711\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:56 INFO\u001b[0m Step 729/1000 | Loss: 2.3544\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:56 INFO\u001b[0m Step 729/1000 | Loss: 2.4286\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:56 INFO\u001b[0m Step 729/1000 | Loss: 2.0774\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:57 INFO\u001b[0m Step 730/1000 | Loss: 1.9402\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:57 INFO\u001b[0m Step 730/1000 | Loss: 2.1248\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:57 INFO\u001b[0m Step 730/1000 | Loss: 2.3194\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:57 INFO\u001b[0m Step 730/1000 | Loss: 2.1795\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:57 INFO\u001b[0m Step 730/1000 | Loss: 1.8482\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:57 INFO\u001b[0m Step 730/1000 | Loss: 2.8668\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:57 INFO\u001b[0m Step 730/1000 | Loss: 2.8895\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:57 INFO\u001b[0m Step 730/1000 | Loss: 2.8100\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:57 INFO\u001b[0m Step 731/1000 | Loss: 2.1829\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:57 INFO\u001b[0m Step 731/1000 | Loss: 1.7598\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:57 INFO\u001b[0m Step 731/1000 | Loss: 2.3095\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:57 INFO\u001b[0m Step 731/1000 | Loss: 2.1891\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:57 INFO\u001b[0m Step 731/1000 | Loss: 2.1369\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:57 INFO\u001b[0m Step 731/1000 | Loss: 2.4817\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:57 INFO\u001b[0m Step 731/1000 | Loss: 1.9883\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:57 INFO\u001b[0m Step 731/1000 | Loss: 2.0990\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:57 INFO\u001b[0m Step 732/1000 | Loss: 2.3886\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:57 INFO\u001b[0m Step 732/1000 | Loss: 1.9864\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:57 INFO\u001b[0m Step 732/1000 | Loss: 1.9462\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:57 INFO\u001b[0m Step 732/1000 | Loss: 2.4938\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:57 INFO\u001b[0m Step 732/1000 | Loss: 2.0015\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:57 INFO\u001b[0m Step 732/1000 | Loss: 2.3003\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:57 INFO\u001b[0m Step 732/1000 | Loss: 2.0615\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:57 INFO\u001b[0m Step 732/1000 | Loss: 2.1313\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:58 INFO\u001b[0m Step 733/1000 | Loss: 2.4293\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:58 INFO\u001b[0m Step 733/1000 | Loss: 2.3816\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:58 INFO\u001b[0m Step 733/1000 | Loss: 2.5715\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:58 INFO\u001b[0m Step 733/1000 | Loss: 2.3677\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:58 INFO\u001b[0m Step 733/1000 | Loss: 2.3826\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:58 INFO\u001b[0m Step 733/1000 | Loss: 2.2594\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:58 INFO\u001b[0m Step 733/1000 | Loss: 2.4368\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:58 INFO\u001b[0m Step 733/1000 | Loss: 2.4331\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:58 INFO\u001b[0m Step 734/1000 | Loss: 2.0017\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:58 INFO\u001b[0m Step 734/1000 | Loss: 1.7145\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:58 INFO\u001b[0m Step 734/1000 | Loss: 2.0097\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:58 INFO\u001b[0m Step 734/1000 | Loss: 2.4154\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:58 INFO\u001b[0m Step 734/1000 | Loss: 2.2800\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:58 INFO\u001b[0m Step 734/1000 | Loss: 2.1659\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:58 INFO\u001b[0m Step 734/1000 | Loss: 2.2447\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:58 INFO\u001b[0m Step 734/1000 | Loss: 2.4313\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:59 INFO\u001b[0m Step 735/1000 | Loss: 1.9593\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:59 INFO\u001b[0m Step 735/1000 | Loss: 2.4258\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:59 INFO\u001b[0m Step 735/1000 | Loss: 2.3593\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:59 INFO\u001b[0m Step 735/1000 | Loss: 2.4753\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:59 INFO\u001b[0m Step 735/1000 | Loss: 2.3917\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:59 INFO\u001b[0m Step 735/1000 | Loss: 2.4242\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:59 INFO\u001b[0m Step 735/1000 | Loss: 2.5511\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:59 INFO\u001b[0m Step 735/1000 | Loss: 2.0042\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:46:59 INFO\u001b[0m Step 736/1000 | Loss: 2.2613\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:46:59 INFO\u001b[0m Step 736/1000 | Loss: 2.5211\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:46:59 INFO\u001b[0m Step 736/1000 | Loss: 2.3592\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:46:59 INFO\u001b[0m Step 736/1000 | Loss: 1.8076\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:46:59 INFO\u001b[0m Step 736/1000 | Loss: 2.6313\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:46:59 INFO\u001b[0m Step 736/1000 | Loss: 1.9430\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:46:59 INFO\u001b[0m Step 736/1000 | Loss: 2.0493\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:46:59 INFO\u001b[0m Step 736/1000 | Loss: 2.1683\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:00 INFO\u001b[0m Step 737/1000 | Loss: 2.2272\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:00 INFO\u001b[0m Step 737/1000 | Loss: 1.8726\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:00 INFO\u001b[0m Step 737/1000 | Loss: 1.9206\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:00 INFO\u001b[0m Step 737/1000 | Loss: 1.6636\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:00 INFO\u001b[0m Step 737/1000 | Loss: 2.1260\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:00 INFO\u001b[0m Step 737/1000 | Loss: 2.5587\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:00 INFO\u001b[0m Step 737/1000 | Loss: 2.0388\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:00 INFO\u001b[0m Step 737/1000 | Loss: 1.9444\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:00 INFO\u001b[0m Step 738/1000 | Loss: 2.4338\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:00 INFO\u001b[0m Step 738/1000 | Loss: 1.9481\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:00 INFO\u001b[0m Step 738/1000 | Loss: 2.1299\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:00 INFO\u001b[0m Step 738/1000 | Loss: 2.1844\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:00 INFO\u001b[0m Step 738/1000 | Loss: 2.2488\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:00 INFO\u001b[0m Step 738/1000 | Loss: 1.7051\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:00 INFO\u001b[0m Step 738/1000 | Loss: 2.4251\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:00 INFO\u001b[0m Step 738/1000 | Loss: 1.8230\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:00 INFO\u001b[0m Step 739/1000 | Loss: 2.2200\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:00 INFO\u001b[0m Step 739/1000 | Loss: 2.1481\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:00 INFO\u001b[0m Step 739/1000 | Loss: 1.9611\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:00 INFO\u001b[0m Step 739/1000 | Loss: 2.2323\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:00 INFO\u001b[0m Step 739/1000 | Loss: 2.3079\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:00 INFO\u001b[0m Step 739/1000 | Loss: 1.9374\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:00 INFO\u001b[0m Step 739/1000 | Loss: 2.0672\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:00 INFO\u001b[0m Step 739/1000 | Loss: 2.5523\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:01 INFO\u001b[0m Step 740/1000 | Loss: 2.2042\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:01 INFO\u001b[0m Step 740/1000 | Loss: 2.5646\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:01 INFO\u001b[0m Step 740/1000 | Loss: 2.1962\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:01 INFO\u001b[0m Step 740/1000 | Loss: 2.2599\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:01 INFO\u001b[0m Step 740/1000 | Loss: 2.1589\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:01 INFO\u001b[0m Step 740/1000 | Loss: 2.0865\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:01 INFO\u001b[0m Step 740/1000 | Loss: 2.1018\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:01 INFO\u001b[0m Step 740/1000 | Loss: 2.9420\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:01 INFO\u001b[0m Step 741/1000 | Loss: 1.9210\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:01 INFO\u001b[0m Step 741/1000 | Loss: 2.2052\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:01 INFO\u001b[0m Step 741/1000 | Loss: 2.4052\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:01 INFO\u001b[0m Step 741/1000 | Loss: 2.1406\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:01 INFO\u001b[0m Step 741/1000 | Loss: 1.9580\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:01 INFO\u001b[0m Step 741/1000 | Loss: 2.1383\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:01 INFO\u001b[0m Step 741/1000 | Loss: 1.9396\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:01 INFO\u001b[0m Step 741/1000 | Loss: 2.1376\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:02 INFO\u001b[0m Step 742/1000 | Loss: 2.0933\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:02 INFO\u001b[0m Step 742/1000 | Loss: 1.5310\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:02 INFO\u001b[0m Step 742/1000 | Loss: 2.0055\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:02 INFO\u001b[0m Step 742/1000 | Loss: 1.6037\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:02 INFO\u001b[0m Step 742/1000 | Loss: 2.3100\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:02 INFO\u001b[0m Step 742/1000 | Loss: 2.4289\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:02 INFO\u001b[0m Step 742/1000 | Loss: 2.4407\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:02 INFO\u001b[0m Step 742/1000 | Loss: 2.5458\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:02 INFO\u001b[0m Step 743/1000 | Loss: 1.8918\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:02 INFO\u001b[0m Step 743/1000 | Loss: 2.1290\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:02 INFO\u001b[0m Step 743/1000 | Loss: 2.1177\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:02 INFO\u001b[0m Step 743/1000 | Loss: 2.0551\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:02 INFO\u001b[0m Step 743/1000 | Loss: 3.3594\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:02 INFO\u001b[0m Step 743/1000 | Loss: 2.5700\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:02 INFO\u001b[0m Step 743/1000 | Loss: 2.2207\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:02 INFO\u001b[0m Step 743/1000 | Loss: 2.3337\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:02 INFO\u001b[0m Step 744/1000 | Loss: 2.0140\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:02 INFO\u001b[0m Step 744/1000 | Loss: 2.5748\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:02 INFO\u001b[0m Step 744/1000 | Loss: 1.9941\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:02 INFO\u001b[0m Step 744/1000 | Loss: 2.1922\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:02 INFO\u001b[0m Step 744/1000 | Loss: 1.7586\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:02 INFO\u001b[0m Step 744/1000 | Loss: 2.3817\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:02 INFO\u001b[0m Step 744/1000 | Loss: 2.4642\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:02 INFO\u001b[0m Step 744/1000 | Loss: 1.9854\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:03 INFO\u001b[0m Step 745/1000 | Loss: 2.5014\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:03 INFO\u001b[0m Step 745/1000 | Loss: 2.4108\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:03 INFO\u001b[0m Step 745/1000 | Loss: 2.1578\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:03 INFO\u001b[0m Step 745/1000 | Loss: 1.9077\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:03 INFO\u001b[0m Step 745/1000 | Loss: 1.8790\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:03 INFO\u001b[0m Step 745/1000 | Loss: 2.2195\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:03 INFO\u001b[0m Step 745/1000 | Loss: 2.1105\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:03 INFO\u001b[0m Step 745/1000 | Loss: 2.1903\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:03 INFO\u001b[0m Step 746/1000 | Loss: 1.9445\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:03 INFO\u001b[0m Step 746/1000 | Loss: 2.0429\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:03 INFO\u001b[0m Step 746/1000 | Loss: 2.2156\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:03 INFO\u001b[0m Step 746/1000 | Loss: 2.1654\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:03 INFO\u001b[0m Step 746/1000 | Loss: 1.8051\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:03 INFO\u001b[0m Step 746/1000 | Loss: 2.3994\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:03 INFO\u001b[0m Step 746/1000 | Loss: 2.3905\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:03 INFO\u001b[0m Step 746/1000 | Loss: 2.3339\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:04 INFO\u001b[0m Step 747/1000 | Loss: 2.1737\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:04 INFO\u001b[0m Step 747/1000 | Loss: 2.1157\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:04 INFO\u001b[0m Step 747/1000 | Loss: 2.3382\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:04 INFO\u001b[0m Step 747/1000 | Loss: 2.0225\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:04 INFO\u001b[0m Step 747/1000 | Loss: 2.2179\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:04 INFO\u001b[0m Step 747/1000 | Loss: 1.9529\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:04 INFO\u001b[0m Step 747/1000 | Loss: 1.8001\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:04 INFO\u001b[0m Step 747/1000 | Loss: 2.5903\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:04 INFO\u001b[0m Step 748/1000 | Loss: 2.3836\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:04 INFO\u001b[0m Step 748/1000 | Loss: 2.3254\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:04 INFO\u001b[0m Step 748/1000 | Loss: 1.9834\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:04 INFO\u001b[0m Step 748/1000 | Loss: 2.7313\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:04 INFO\u001b[0m Step 748/1000 | Loss: 2.4261\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:04 INFO\u001b[0m Step 748/1000 | Loss: 2.1989\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:04 INFO\u001b[0m Step 748/1000 | Loss: 2.2722\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:04 INFO\u001b[0m Step 748/1000 | Loss: 2.1484\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:04 INFO\u001b[0m Step 749/1000 | Loss: 2.2803\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:04 INFO\u001b[0m Step 749/1000 | Loss: 2.3305\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:04 INFO\u001b[0m Step 749/1000 | Loss: 2.0754\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:04 INFO\u001b[0m Step 749/1000 | Loss: 2.3195\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:04 INFO\u001b[0m Step 749/1000 | Loss: 1.9106\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:04 INFO\u001b[0m Step 749/1000 | Loss: 2.1844\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:04 INFO\u001b[0m Step 749/1000 | Loss: 2.1775\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:04 INFO\u001b[0m Step 749/1000 | Loss: 2.5392\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:05 INFO\u001b[0m Step 750/1000 | Loss: 2.1701\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:05 INFO\u001b[0m Step 750/1000 | Loss: 2.0943\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:05 INFO\u001b[0m Step 750/1000 | Loss: 2.0644\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:05 INFO\u001b[0m Step 750/1000 | Loss: 2.1850\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:05 INFO\u001b[0m Step 750/1000 | Loss: 2.1794\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:05 INFO\u001b[0m Step 750/1000 | Loss: 2.2631\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:05 INFO\u001b[0m Step 750/1000 | Loss: 1.9600\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:05 INFO\u001b[0m Step 750/1000 | Loss: 1.8991\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:05 INFO\u001b[0m Step 751/1000 | Loss: 2.4379\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:05 INFO\u001b[0m Step 751/1000 | Loss: 1.9539\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:05 INFO\u001b[0m Step 751/1000 | Loss: 1.9383\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:05 INFO\u001b[0m Step 751/1000 | Loss: 2.0053\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:05 INFO\u001b[0m Step 751/1000 | Loss: 2.0286\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:05 INFO\u001b[0m Step 751/1000 | Loss: 2.0885\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:05 INFO\u001b[0m Step 751/1000 | Loss: 2.4125\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:05 INFO\u001b[0m Step 751/1000 | Loss: 1.9793\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:06 INFO\u001b[0m Step 752/1000 | Loss: 2.3669\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:06 INFO\u001b[0m Step 752/1000 | Loss: 2.0784\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:06 INFO\u001b[0m Step 752/1000 | Loss: 2.3357\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:06 INFO\u001b[0m Step 752/1000 | Loss: 2.2659\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:06 INFO\u001b[0m Step 752/1000 | Loss: 1.9420\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:06 INFO\u001b[0m Step 752/1000 | Loss: 1.9676\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:06 INFO\u001b[0m Step 752/1000 | Loss: 2.1996\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:06 INFO\u001b[0m Step 752/1000 | Loss: 2.4968\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:06 INFO\u001b[0m Step 753/1000 | Loss: 2.7087\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:06 INFO\u001b[0m Step 753/1000 | Loss: 2.5195\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:06 INFO\u001b[0m Step 753/1000 | Loss: 2.3711\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:06 INFO\u001b[0m Step 753/1000 | Loss: 2.5572\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:06 INFO\u001b[0m Step 753/1000 | Loss: 2.3570\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:06 INFO\u001b[0m Step 753/1000 | Loss: 2.6553\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:06 INFO\u001b[0m Step 753/1000 | Loss: 2.3940\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:06 INFO\u001b[0m Step 753/1000 | Loss: 2.5669\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:06 INFO\u001b[0m Step 754/1000 | Loss: 2.1328\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:06 INFO\u001b[0m Step 754/1000 | Loss: 2.7628\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:06 INFO\u001b[0m Step 754/1000 | Loss: 2.3126\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:06 INFO\u001b[0m Step 754/1000 | Loss: 2.7696\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:06 INFO\u001b[0m Step 754/1000 | Loss: 2.1143\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:06 INFO\u001b[0m Step 754/1000 | Loss: 2.0761\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:06 INFO\u001b[0m Step 754/1000 | Loss: 2.4065\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:06 INFO\u001b[0m Step 754/1000 | Loss: 2.0195\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:07 INFO\u001b[0m Step 755/1000 | Loss: 2.5171\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:07 INFO\u001b[0m Step 755/1000 | Loss: 1.9493\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:07 INFO\u001b[0m Step 755/1000 | Loss: 2.4743\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:07 INFO\u001b[0m Step 755/1000 | Loss: 2.3886\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:07 INFO\u001b[0m Step 755/1000 | Loss: 2.1817\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:07 INFO\u001b[0m Step 755/1000 | Loss: 1.8764\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:07 INFO\u001b[0m Step 755/1000 | Loss: 2.0135\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:07 INFO\u001b[0m Step 755/1000 | Loss: 1.9901\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:07 INFO\u001b[0m Step 756/1000 | Loss: 2.1163\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:07 INFO\u001b[0m Step 756/1000 | Loss: 2.4990\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:07 INFO\u001b[0m Step 756/1000 | Loss: 2.1031\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:07 INFO\u001b[0m Step 756/1000 | Loss: 1.9975\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:07 INFO\u001b[0m Step 756/1000 | Loss: 2.3209\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:07 INFO\u001b[0m Step 756/1000 | Loss: 2.3469\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:07 INFO\u001b[0m Step 756/1000 | Loss: 2.4541\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:07 INFO\u001b[0m Step 756/1000 | Loss: 2.3951\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:08 INFO\u001b[0m Step 757/1000 | Loss: 2.2594\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:08 INFO\u001b[0m Step 757/1000 | Loss: 2.0481\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:08 INFO\u001b[0m Step 757/1000 | Loss: 2.1023\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:08 INFO\u001b[0m Step 757/1000 | Loss: 2.3679\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:08 INFO\u001b[0m Step 757/1000 | Loss: 2.1304\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:08 INFO\u001b[0m Step 757/1000 | Loss: 1.9533\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:08 INFO\u001b[0m Step 757/1000 | Loss: 2.2075\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:08 INFO\u001b[0m Step 757/1000 | Loss: 2.2039\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:08 INFO\u001b[0m Step 758/1000 | Loss: 2.5103\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:08 INFO\u001b[0m Step 758/1000 | Loss: 2.1292\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:08 INFO\u001b[0m Step 758/1000 | Loss: 2.1577\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:08 INFO\u001b[0m Step 758/1000 | Loss: 2.0924\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:08 INFO\u001b[0m Step 758/1000 | Loss: 2.3847\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:08 INFO\u001b[0m Step 758/1000 | Loss: 2.0828\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:08 INFO\u001b[0m Step 758/1000 | Loss: 2.1330\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:08 INFO\u001b[0m Step 758/1000 | Loss: 1.9588\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:08 INFO\u001b[0m Step 759/1000 | Loss: 2.1052\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:08 INFO\u001b[0m Step 759/1000 | Loss: 1.9505\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:08 INFO\u001b[0m Step 759/1000 | Loss: 2.0299\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:08 INFO\u001b[0m Step 759/1000 | Loss: 2.3067\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:08 INFO\u001b[0m Step 759/1000 | Loss: 1.9313\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:08 INFO\u001b[0m Step 759/1000 | Loss: 2.6455\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:08 INFO\u001b[0m Step 759/1000 | Loss: 1.7605\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:08 INFO\u001b[0m Step 759/1000 | Loss: 2.8321\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:09 INFO\u001b[0m Step 760/1000 | Loss: 1.7491\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:09 INFO\u001b[0m Step 760/1000 | Loss: 2.2575\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:09 INFO\u001b[0m Step 760/1000 | Loss: 2.0296\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:09 INFO\u001b[0m Step 760/1000 | Loss: 2.2289\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:09 INFO\u001b[0m Step 760/1000 | Loss: 1.7937\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:09 INFO\u001b[0m Step 760/1000 | Loss: 1.8543\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:09 INFO\u001b[0m Step 760/1000 | Loss: 2.7368\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:09 INFO\u001b[0m Step 760/1000 | Loss: 2.5552\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:09 INFO\u001b[0m Step 761/1000 | Loss: 1.9727\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:09 INFO\u001b[0m Step 761/1000 | Loss: 1.9198\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:09 INFO\u001b[0m Step 761/1000 | Loss: 2.1077\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:09 INFO\u001b[0m Step 761/1000 | Loss: 2.1626\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:09 INFO\u001b[0m Step 761/1000 | Loss: 2.4619\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:09 INFO\u001b[0m Step 761/1000 | Loss: 2.5929\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:09 INFO\u001b[0m Step 761/1000 | Loss: 2.3610\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:09 INFO\u001b[0m Step 761/1000 | Loss: 2.0933\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:10 INFO\u001b[0m Step 762/1000 | Loss: 2.3690\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:10 INFO\u001b[0m Step 762/1000 | Loss: 2.1479\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:10 INFO\u001b[0m Step 762/1000 | Loss: 2.2711\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:10 INFO\u001b[0m Step 762/1000 | Loss: 2.0643\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:10 INFO\u001b[0m Step 762/1000 | Loss: 1.8125\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:10 INFO\u001b[0m Step 762/1000 | Loss: 1.7411\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:10 INFO\u001b[0m Step 762/1000 | Loss: 2.2679\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:10 INFO\u001b[0m Step 762/1000 | Loss: 2.2958\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:10 INFO\u001b[0m Step 763/1000 | Loss: 2.1992\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:10 INFO\u001b[0m Step 763/1000 | Loss: 1.8654\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:10 INFO\u001b[0m Step 763/1000 | Loss: 2.5265\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:10 INFO\u001b[0m Step 763/1000 | Loss: 2.0031\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:10 INFO\u001b[0m Step 763/1000 | Loss: 2.3815\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:10 INFO\u001b[0m Step 763/1000 | Loss: 2.2045\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:10 INFO\u001b[0m Step 763/1000 | Loss: 2.2672\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:10 INFO\u001b[0m Step 763/1000 | Loss: 2.1505\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:11 INFO\u001b[0m Step 764/1000 | Loss: 2.4103\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:11 INFO\u001b[0m Step 764/1000 | Loss: 2.1487\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:11 INFO\u001b[0m Step 764/1000 | Loss: 2.3955\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:11 INFO\u001b[0m Step 764/1000 | Loss: 1.9804\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:11 INFO\u001b[0m Step 764/1000 | Loss: 2.1452\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:11 INFO\u001b[0m Step 764/1000 | Loss: 2.4731\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:11 INFO\u001b[0m Step 764/1000 | Loss: 2.4557\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:11 INFO\u001b[0m Step 764/1000 | Loss: 2.3922\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:11 INFO\u001b[0m Step 765/1000 | Loss: 2.1226\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:11 INFO\u001b[0m Step 765/1000 | Loss: 2.5526\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:11 INFO\u001b[0m Step 765/1000 | Loss: 2.6213\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:11 INFO\u001b[0m Step 765/1000 | Loss: 1.8194\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:11 INFO\u001b[0m Step 765/1000 | Loss: 2.5350\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:11 INFO\u001b[0m Step 765/1000 | Loss: 2.2904\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:11 INFO\u001b[0m Step 765/1000 | Loss: 2.1261\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:11 INFO\u001b[0m Step 765/1000 | Loss: 2.1774\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:11 INFO\u001b[0m Step 766/1000 | Loss: 2.5356\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:11 INFO\u001b[0m Step 766/1000 | Loss: 2.4312\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:11 INFO\u001b[0m Step 766/1000 | Loss: 2.5967\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:11 INFO\u001b[0m Step 766/1000 | Loss: 2.2023\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:11 INFO\u001b[0m Step 766/1000 | Loss: 2.1273\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:11 INFO\u001b[0m Step 766/1000 | Loss: 2.7237\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:11 INFO\u001b[0m Step 766/1000 | Loss: 2.1331\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:11 INFO\u001b[0m Step 766/1000 | Loss: 2.3149\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:12 INFO\u001b[0m Step 767/1000 | Loss: 1.9243\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:12 INFO\u001b[0m Step 767/1000 | Loss: 2.4700\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:12 INFO\u001b[0m Step 767/1000 | Loss: 1.8753\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:12 INFO\u001b[0m Step 767/1000 | Loss: 2.3824\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:12 INFO\u001b[0m Step 767/1000 | Loss: 2.1804\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:12 INFO\u001b[0m Step 767/1000 | Loss: 2.7385\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:12 INFO\u001b[0m Step 767/1000 | Loss: 1.8816\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:12 INFO\u001b[0m Step 767/1000 | Loss: 2.3624\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:12 INFO\u001b[0m Step 768/1000 | Loss: 1.9699\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:12 INFO\u001b[0m Step 768/1000 | Loss: 2.0587\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:12 INFO\u001b[0m Step 768/1000 | Loss: 2.2136\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:12 INFO\u001b[0m Step 768/1000 | Loss: 2.2914\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:12 INFO\u001b[0m Step 768/1000 | Loss: 2.5975\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:12 INFO\u001b[0m Step 768/1000 | Loss: 2.4719\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:12 INFO\u001b[0m Step 768/1000 | Loss: 2.3204\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:12 INFO\u001b[0m Step 768/1000 | Loss: 2.1508\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:13 INFO\u001b[0m Step 769/1000 | Loss: 2.2098\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:13 INFO\u001b[0m Step 769/1000 | Loss: 1.8138\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:13 INFO\u001b[0m Step 769/1000 | Loss: 2.2621\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:13 INFO\u001b[0m Step 769/1000 | Loss: 2.0714\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:13 INFO\u001b[0m Step 769/1000 | Loss: 2.1309\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:13 INFO\u001b[0m Step 769/1000 | Loss: 2.6159\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:13 INFO\u001b[0m Step 769/1000 | Loss: 2.3501\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:13 INFO\u001b[0m Step 769/1000 | Loss: 2.5707\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:13 INFO\u001b[0m Step 770/1000 | Loss: 2.6057\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:13 INFO\u001b[0m Step 770/1000 | Loss: 2.1863\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:13 INFO\u001b[0m Step 770/1000 | Loss: 2.8882\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:13 INFO\u001b[0m Step 770/1000 | Loss: 1.9773\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:13 INFO\u001b[0m Step 770/1000 | Loss: 2.2249\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:13 INFO\u001b[0m Step 770/1000 | Loss: 2.3635\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:13 INFO\u001b[0m Step 770/1000 | Loss: 2.1803\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:13 INFO\u001b[0m Step 770/1000 | Loss: 2.1581\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:13 INFO\u001b[0m Step 771/1000 | Loss: 2.6688\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:13 INFO\u001b[0m Step 771/1000 | Loss: 2.0757\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:13 INFO\u001b[0m Step 771/1000 | Loss: 2.3664\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:13 INFO\u001b[0m Step 771/1000 | Loss: 2.2927\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:13 INFO\u001b[0m Step 771/1000 | Loss: 2.2288\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:13 INFO\u001b[0m Step 771/1000 | Loss: 2.1588\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:13 INFO\u001b[0m Step 771/1000 | Loss: 2.0439\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:13 INFO\u001b[0m Step 771/1000 | Loss: 2.2822\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:14 INFO\u001b[0m Step 772/1000 | Loss: 2.2166\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:14 INFO\u001b[0m Step 772/1000 | Loss: 1.9981\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:14 INFO\u001b[0m Step 772/1000 | Loss: 2.0946\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:14 INFO\u001b[0m Step 772/1000 | Loss: 2.2749\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:14 INFO\u001b[0m Step 772/1000 | Loss: 2.5567\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:14 INFO\u001b[0m Step 772/1000 | Loss: 2.7997\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:14 INFO\u001b[0m Step 772/1000 | Loss: 2.0360\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:14 INFO\u001b[0m Step 772/1000 | Loss: 2.7558\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:14 INFO\u001b[0m Step 773/1000 | Loss: 2.4322\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:14 INFO\u001b[0m Step 773/1000 | Loss: 1.9236\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:14 INFO\u001b[0m Step 773/1000 | Loss: 2.4135\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:14 INFO\u001b[0m Step 773/1000 | Loss: 2.5948\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:14 INFO\u001b[0m Step 773/1000 | Loss: 2.2437\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:14 INFO\u001b[0m Step 773/1000 | Loss: 2.3872\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:14 INFO\u001b[0m Step 773/1000 | Loss: 2.3544\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:14 INFO\u001b[0m Step 773/1000 | Loss: 2.4857\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:15 INFO\u001b[0m Step 774/1000 | Loss: 1.9567\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:15 INFO\u001b[0m Step 774/1000 | Loss: 2.0773\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:15 INFO\u001b[0m Step 774/1000 | Loss: 2.7207\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:15 INFO\u001b[0m Step 774/1000 | Loss: 1.9355\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:15 INFO\u001b[0m Step 774/1000 | Loss: 2.1344\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:15 INFO\u001b[0m Step 774/1000 | Loss: 2.5336\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:15 INFO\u001b[0m Step 774/1000 | Loss: 2.1263\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:15 INFO\u001b[0m Step 774/1000 | Loss: 1.8645\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:15 INFO\u001b[0m Step 775/1000 | Loss: 1.8909\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:15 INFO\u001b[0m Step 775/1000 | Loss: 2.4501\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:15 INFO\u001b[0m Step 775/1000 | Loss: 2.1270\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:15 INFO\u001b[0m Step 775/1000 | Loss: 2.2266\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:15 INFO\u001b[0m Step 775/1000 | Loss: 2.2656\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:15 INFO\u001b[0m Step 775/1000 | Loss: 2.0757\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:15 INFO\u001b[0m Step 775/1000 | Loss: 2.1720\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:15 INFO\u001b[0m Step 775/1000 | Loss: 2.0550\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:15 INFO\u001b[0m Step 776/1000 | Loss: 2.6783\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:15 INFO\u001b[0m Step 776/1000 | Loss: 2.0379\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:15 INFO\u001b[0m Step 776/1000 | Loss: 2.2267\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:15 INFO\u001b[0m Step 776/1000 | Loss: 1.9899\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:15 INFO\u001b[0m Step 776/1000 | Loss: 1.4748\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:15 INFO\u001b[0m Step 776/1000 | Loss: 1.8123\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:15 INFO\u001b[0m Step 776/1000 | Loss: 1.8407\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:15 INFO\u001b[0m Step 776/1000 | Loss: 1.8952\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:16 INFO\u001b[0m Step 777/1000 | Loss: 2.0219\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:16 INFO\u001b[0m Step 777/1000 | Loss: 2.2588\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:16 INFO\u001b[0m Step 777/1000 | Loss: 2.1192\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:16 INFO\u001b[0m Step 777/1000 | Loss: 2.5297\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:16 INFO\u001b[0m Step 777/1000 | Loss: 2.2011\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:16 INFO\u001b[0m Step 777/1000 | Loss: 2.1872\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:16 INFO\u001b[0m Step 777/1000 | Loss: 1.7955\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:16 INFO\u001b[0m Step 777/1000 | Loss: 1.8430\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:16 INFO\u001b[0m Step 778/1000 | Loss: 2.6843\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:16 INFO\u001b[0m Step 778/1000 | Loss: 2.0492\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:16 INFO\u001b[0m Step 778/1000 | Loss: 2.1527\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:16 INFO\u001b[0m Step 778/1000 | Loss: 1.8092\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:16 INFO\u001b[0m Step 778/1000 | Loss: 1.8966\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:16 INFO\u001b[0m Step 778/1000 | Loss: 1.7704\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:16 INFO\u001b[0m Step 778/1000 | Loss: 2.1527\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:16 INFO\u001b[0m Step 778/1000 | Loss: 1.9245\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:17 INFO\u001b[0m Step 779/1000 | Loss: 2.2029\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:17 INFO\u001b[0m Step 779/1000 | Loss: 2.7508\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:17 INFO\u001b[0m Step 779/1000 | Loss: 2.3088\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:17 INFO\u001b[0m Step 779/1000 | Loss: 1.7077\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:17 INFO\u001b[0m Step 779/1000 | Loss: 2.2285\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:17 INFO\u001b[0m Step 779/1000 | Loss: 2.3796\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:17 INFO\u001b[0m Step 779/1000 | Loss: 2.2329\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:17 INFO\u001b[0m Step 779/1000 | Loss: 1.8332\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:17 INFO\u001b[0m Step 780/1000 | Loss: 2.4434\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:17 INFO\u001b[0m Step 780/1000 | Loss: 1.8619\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:17 INFO\u001b[0m Step 780/1000 | Loss: 2.1942\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:17 INFO\u001b[0m Step 780/1000 | Loss: 1.8996\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:17 INFO\u001b[0m Step 780/1000 | Loss: 2.3081\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:17 INFO\u001b[0m Step 780/1000 | Loss: 2.2429\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:17 INFO\u001b[0m Step 780/1000 | Loss: 2.0046\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:17 INFO\u001b[0m Step 780/1000 | Loss: 2.3731\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:17 INFO\u001b[0m Step 781/1000 | Loss: 1.8716\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:17 INFO\u001b[0m Step 781/1000 | Loss: 1.6949\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:17 INFO\u001b[0m Step 781/1000 | Loss: 2.2583\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:17 INFO\u001b[0m Step 781/1000 | Loss: 2.8810\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:17 INFO\u001b[0m Step 781/1000 | Loss: 2.2667\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:17 INFO\u001b[0m Step 781/1000 | Loss: 1.8775\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:17 INFO\u001b[0m Step 781/1000 | Loss: 2.0207\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:17 INFO\u001b[0m Step 781/1000 | Loss: 2.1321\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:18 INFO\u001b[0m Step 782/1000 | Loss: 1.9272\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:18 INFO\u001b[0m Step 782/1000 | Loss: 2.2429\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:18 INFO\u001b[0m Step 782/1000 | Loss: 1.9624\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:18 INFO\u001b[0m Step 782/1000 | Loss: 2.0333\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:18 INFO\u001b[0m Step 782/1000 | Loss: 2.1876\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:18 INFO\u001b[0m Step 782/1000 | Loss: 1.9615\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:18 INFO\u001b[0m Step 782/1000 | Loss: 2.0127\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:18 INFO\u001b[0m Step 782/1000 | Loss: 2.8817\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:18 INFO\u001b[0m Step 783/1000 | Loss: 2.2255\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:18 INFO\u001b[0m Step 783/1000 | Loss: 1.9055\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:18 INFO\u001b[0m Step 783/1000 | Loss: 2.3738\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:18 INFO\u001b[0m Step 783/1000 | Loss: 2.0389\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:18 INFO\u001b[0m Step 783/1000 | Loss: 2.1819\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:18 INFO\u001b[0m Step 783/1000 | Loss: 2.0660\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:18 INFO\u001b[0m Step 783/1000 | Loss: 2.2848\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:18 INFO\u001b[0m Step 783/1000 | Loss: 2.0197\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:19 INFO\u001b[0m Step 784/1000 | Loss: 2.0198\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:19 INFO\u001b[0m Step 784/1000 | Loss: 2.1039\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:19 INFO\u001b[0m Step 784/1000 | Loss: 2.4695\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:19 INFO\u001b[0m Step 784/1000 | Loss: 2.4140\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:19 INFO\u001b[0m Step 784/1000 | Loss: 2.3406\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:19 INFO\u001b[0m Step 784/1000 | Loss: 1.8770\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:19 INFO\u001b[0m Step 784/1000 | Loss: 1.8106\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:19 INFO\u001b[0m Step 784/1000 | Loss: 2.5071\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:19 INFO\u001b[0m Step 785/1000 | Loss: 2.2159\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:19 INFO\u001b[0m Step 785/1000 | Loss: 2.3784\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:19 INFO\u001b[0m Step 785/1000 | Loss: 1.9953\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:19 INFO\u001b[0m Step 785/1000 | Loss: 2.1617\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:19 INFO\u001b[0m Step 785/1000 | Loss: 1.9716\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:19 INFO\u001b[0m Step 785/1000 | Loss: 2.0487\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:19 INFO\u001b[0m Step 785/1000 | Loss: 1.7284\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:19 INFO\u001b[0m Step 785/1000 | Loss: 1.6947\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:19 INFO\u001b[0m Step 786/1000 | Loss: 1.9696\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:19 INFO\u001b[0m Step 786/1000 | Loss: 2.0646\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:19 INFO\u001b[0m Step 786/1000 | Loss: 2.3301\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:19 INFO\u001b[0m Step 786/1000 | Loss: 2.3538\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:19 INFO\u001b[0m Step 786/1000 | Loss: 1.7190\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:19 INFO\u001b[0m Step 786/1000 | Loss: 1.9631\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:19 INFO\u001b[0m Step 786/1000 | Loss: 1.9828\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:19 INFO\u001b[0m Step 786/1000 | Loss: 2.0986\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:20 INFO\u001b[0m Step 787/1000 | Loss: 1.4241\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:20 INFO\u001b[0m Step 787/1000 | Loss: 1.7392\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:20 INFO\u001b[0m Step 787/1000 | Loss: 2.3797\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:20 INFO\u001b[0m Step 787/1000 | Loss: 2.2306\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:20 INFO\u001b[0m Step 787/1000 | Loss: 2.0011\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:20 INFO\u001b[0m Step 787/1000 | Loss: 2.3139\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:20 INFO\u001b[0m Step 787/1000 | Loss: 2.0363\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:20 INFO\u001b[0m Step 787/1000 | Loss: 2.1620\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:20 INFO\u001b[0m Step 788/1000 | Loss: 1.9345\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:20 INFO\u001b[0m Step 788/1000 | Loss: 2.5627\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:20 INFO\u001b[0m Step 788/1000 | Loss: 1.9973\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:20 INFO\u001b[0m Step 788/1000 | Loss: 1.9148\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:20 INFO\u001b[0m Step 788/1000 | Loss: 2.1931\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:20 INFO\u001b[0m Step 788/1000 | Loss: 2.3797\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:20 INFO\u001b[0m Step 788/1000 | Loss: 1.8978\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:20 INFO\u001b[0m Step 788/1000 | Loss: 2.2202\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:21 INFO\u001b[0m Step 789/1000 | Loss: 2.4847\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:21 INFO\u001b[0m Step 789/1000 | Loss: 2.4071\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:21 INFO\u001b[0m Step 789/1000 | Loss: 1.9951\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:21 INFO\u001b[0m Step 789/1000 | Loss: 1.8879\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:21 INFO\u001b[0m Step 789/1000 | Loss: 2.2502\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:21 INFO\u001b[0m Step 789/1000 | Loss: 2.0806\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:21 INFO\u001b[0m Step 789/1000 | Loss: 1.8674\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:21 INFO\u001b[0m Step 789/1000 | Loss: 2.2909\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:21 INFO\u001b[0m Step 790/1000 | Loss: 2.0812\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:21 INFO\u001b[0m Step 790/1000 | Loss: 1.7689\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:21 INFO\u001b[0m Step 790/1000 | Loss: 2.0551\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:21 INFO\u001b[0m Step 790/1000 | Loss: 2.0548\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:21 INFO\u001b[0m Step 790/1000 | Loss: 1.9936\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:21 INFO\u001b[0m Step 790/1000 | Loss: 2.3605\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:21 INFO\u001b[0m Step 790/1000 | Loss: 2.2335\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:21 INFO\u001b[0m Step 790/1000 | Loss: 2.1238\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:21 INFO\u001b[0m Step 791/1000 | Loss: 2.5206\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:21 INFO\u001b[0m Step 791/1000 | Loss: 1.9853\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:21 INFO\u001b[0m Step 791/1000 | Loss: 2.1307\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:21 INFO\u001b[0m Step 791/1000 | Loss: 2.4555\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:21 INFO\u001b[0m Step 791/1000 | Loss: 1.7884\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:21 INFO\u001b[0m Step 791/1000 | Loss: 2.1185\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:21 INFO\u001b[0m Step 791/1000 | Loss: 2.0899\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:21 INFO\u001b[0m Step 791/1000 | Loss: 2.8628\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:22 INFO\u001b[0m Step 792/1000 | Loss: 2.9518\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:22 INFO\u001b[0m Step 792/1000 | Loss: 1.8227\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:22 INFO\u001b[0m Step 792/1000 | Loss: 1.8084\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:22 INFO\u001b[0m Step 792/1000 | Loss: 2.1707\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:22 INFO\u001b[0m Step 792/1000 | Loss: 2.2906\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:22 INFO\u001b[0m Step 792/1000 | Loss: 1.9872\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:22 INFO\u001b[0m Step 792/1000 | Loss: 1.7446\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:22 INFO\u001b[0m Step 792/1000 | Loss: 1.9854\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:22 INFO\u001b[0m Step 793/1000 | Loss: 2.0955\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:22 INFO\u001b[0m Step 793/1000 | Loss: 2.2276\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:22 INFO\u001b[0m Step 793/1000 | Loss: 1.8112\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:22 INFO\u001b[0m Step 793/1000 | Loss: 2.1984\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:22 INFO\u001b[0m Step 793/1000 | Loss: 2.1466\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:22 INFO\u001b[0m Step 793/1000 | Loss: 2.0798\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:22 INFO\u001b[0m Step 793/1000 | Loss: 1.8166\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:22 INFO\u001b[0m Step 793/1000 | Loss: 1.7929\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:23 INFO\u001b[0m Step 794/1000 | Loss: 2.2495\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:23 INFO\u001b[0m Step 794/1000 | Loss: 2.1744\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:23 INFO\u001b[0m Step 794/1000 | Loss: 2.1482\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:23 INFO\u001b[0m Step 794/1000 | Loss: 2.4654\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:23 INFO\u001b[0m Step 794/1000 | Loss: 2.0911\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:23 INFO\u001b[0m Step 794/1000 | Loss: 1.8540\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:23 INFO\u001b[0m Step 794/1000 | Loss: 2.0001\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:23 INFO\u001b[0m Step 794/1000 | Loss: 2.2866\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:23 INFO\u001b[0m Step 795/1000 | Loss: 1.8249\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:23 INFO\u001b[0m Step 795/1000 | Loss: 2.1665\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:23 INFO\u001b[0m Step 795/1000 | Loss: 2.1186\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:23 INFO\u001b[0m Step 795/1000 | Loss: 2.5364\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:23 INFO\u001b[0m Step 795/1000 | Loss: 2.2653\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:23 INFO\u001b[0m Step 795/1000 | Loss: 2.0805\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:23 INFO\u001b[0m Step 795/1000 | Loss: 1.8387\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:23 INFO\u001b[0m Step 795/1000 | Loss: 2.4191\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:23 INFO\u001b[0m Step 796/1000 | Loss: 2.1375\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:23 INFO\u001b[0m Step 796/1000 | Loss: 2.4404\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:23 INFO\u001b[0m Step 796/1000 | Loss: 1.8278\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:23 INFO\u001b[0m Step 796/1000 | Loss: 2.0418\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:23 INFO\u001b[0m Step 796/1000 | Loss: 2.0853\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:23 INFO\u001b[0m Step 796/1000 | Loss: 1.8449\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:23 INFO\u001b[0m Step 796/1000 | Loss: 2.2605\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:23 INFO\u001b[0m Step 796/1000 | Loss: 1.8649\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:24 INFO\u001b[0m Step 797/1000 | Loss: 2.3963\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:24 INFO\u001b[0m Step 797/1000 | Loss: 2.2686\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:24 INFO\u001b[0m Step 797/1000 | Loss: 2.0386\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:24 INFO\u001b[0m Step 797/1000 | Loss: 2.3476\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:24 INFO\u001b[0m Step 797/1000 | Loss: 2.6706\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:24 INFO\u001b[0m Step 797/1000 | Loss: 2.5163\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:24 INFO\u001b[0m Step 797/1000 | Loss: 1.8325\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:24 INFO\u001b[0m Step 797/1000 | Loss: 1.6011\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:24 INFO\u001b[0m Step 798/1000 | Loss: 2.5570\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:24 INFO\u001b[0m Step 798/1000 | Loss: 1.9365\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:24 INFO\u001b[0m Step 798/1000 | Loss: 1.9871\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:24 INFO\u001b[0m Step 798/1000 | Loss: 2.0184\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:24 INFO\u001b[0m Step 798/1000 | Loss: 1.9533\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:24 INFO\u001b[0m Step 798/1000 | Loss: 2.1301\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:24 INFO\u001b[0m Step 798/1000 | Loss: 2.3014\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:24 INFO\u001b[0m Step 798/1000 | Loss: 1.9597\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:25 INFO\u001b[0m Step 799/1000 | Loss: 2.2216\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:25 INFO\u001b[0m Step 799/1000 | Loss: 2.3229\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:25 INFO\u001b[0m Step 799/1000 | Loss: 2.3151\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:25 INFO\u001b[0m Step 799/1000 | Loss: 2.4129\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:25 INFO\u001b[0m Step 799/1000 | Loss: 1.8326\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:25 INFO\u001b[0m Step 799/1000 | Loss: 2.2004\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:25 INFO\u001b[0m Step 799/1000 | Loss: 2.3512\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:25 INFO\u001b[0m Step 799/1000 | Loss: 2.3786\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:25 INFO\u001b[0m Step 800/1000 | Loss: 1.7604\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:25 INFO\u001b[0m Step 800/1000 | Loss: 1.9975\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:25 INFO\u001b[0m Step 800/1000 | Loss: 2.3726\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:25 INFO\u001b[0m Step 800/1000 | Loss: 2.5407\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:25 INFO\u001b[0m Step 800/1000 | Loss: 2.6159\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:25 INFO\u001b[0m Step 800/1000 | Loss: 2.3469\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:25 INFO\u001b[0m Step 800/1000 | Loss: 2.1613\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:25 INFO\u001b[0m Step 800/1000 | Loss: 2.1016\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:25 INFO\u001b[0m Step 801/1000 | Loss: 2.1534\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:25 INFO\u001b[0m Step 801/1000 | Loss: 2.1849\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:25 INFO\u001b[0m Step 801/1000 | Loss: 1.7499\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:25 INFO\u001b[0m Step 801/1000 | Loss: 3.0478\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:25 INFO\u001b[0m Step 801/1000 | Loss: 1.8107\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:25 INFO\u001b[0m Step 801/1000 | Loss: 2.1598\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:25 INFO\u001b[0m Step 801/1000 | Loss: 1.8839\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:25 INFO\u001b[0m Step 801/1000 | Loss: 2.1818\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:26 INFO\u001b[0m Step 802/1000 | Loss: 2.1182\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:26 INFO\u001b[0m Step 802/1000 | Loss: 2.0231\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:26 INFO\u001b[0m Step 802/1000 | Loss: 1.9256\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:26 INFO\u001b[0m Step 802/1000 | Loss: 2.3900\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:26 INFO\u001b[0m Step 802/1000 | Loss: 1.9617\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:26 INFO\u001b[0m Step 802/1000 | Loss: 2.1350\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:26 INFO\u001b[0m Step 802/1000 | Loss: 1.8882\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:26 INFO\u001b[0m Step 802/1000 | Loss: 2.4087\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:26 INFO\u001b[0m Step 803/1000 | Loss: 2.0587\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:26 INFO\u001b[0m Step 803/1000 | Loss: 2.8356\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:26 INFO\u001b[0m Step 803/1000 | Loss: 1.9128\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:26 INFO\u001b[0m Step 803/1000 | Loss: 2.1480\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:26 INFO\u001b[0m Step 803/1000 | Loss: 2.1269\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:26 INFO\u001b[0m Step 803/1000 | Loss: 2.0360\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:26 INFO\u001b[0m Step 803/1000 | Loss: 2.1851\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:26 INFO\u001b[0m Step 803/1000 | Loss: 2.8167\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:27 INFO\u001b[0m Step 804/1000 | Loss: 2.0060\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:27 INFO\u001b[0m Step 804/1000 | Loss: 1.6196\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:27 INFO\u001b[0m Step 804/1000 | Loss: 2.3354\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:27 INFO\u001b[0m Step 804/1000 | Loss: 1.8852\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:27 INFO\u001b[0m Step 804/1000 | Loss: 2.3607\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:27 INFO\u001b[0m Step 804/1000 | Loss: 2.4557\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:27 INFO\u001b[0m Step 804/1000 | Loss: 2.6504\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:27 INFO\u001b[0m Step 804/1000 | Loss: 2.1393\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:27 INFO\u001b[0m Step 805/1000 | Loss: 1.8841\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:27 INFO\u001b[0m Step 805/1000 | Loss: 2.1249\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:27 INFO\u001b[0m Step 805/1000 | Loss: 2.4794\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:27 INFO\u001b[0m Step 805/1000 | Loss: 1.8435\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:27 INFO\u001b[0m Step 805/1000 | Loss: 2.8971\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:27 INFO\u001b[0m Step 805/1000 | Loss: 2.4681\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:27 INFO\u001b[0m Step 805/1000 | Loss: 1.9240\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:27 INFO\u001b[0m Step 805/1000 | Loss: 2.2146\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:27 INFO\u001b[0m Step 806/1000 | Loss: 2.0340\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:27 INFO\u001b[0m Step 806/1000 | Loss: 1.8597\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:27 INFO\u001b[0m Step 806/1000 | Loss: 2.1559\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:27 INFO\u001b[0m Step 806/1000 | Loss: 2.5027\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:27 INFO\u001b[0m Step 806/1000 | Loss: 2.2558\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:27 INFO\u001b[0m Step 806/1000 | Loss: 2.8751\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:27 INFO\u001b[0m Step 806/1000 | Loss: 2.2181\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:27 INFO\u001b[0m Step 806/1000 | Loss: 2.0283\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:28 INFO\u001b[0m Step 807/1000 | Loss: 2.1819\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:28 INFO\u001b[0m Step 807/1000 | Loss: 2.0201\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:28 INFO\u001b[0m Step 807/1000 | Loss: 1.9191\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:28 INFO\u001b[0m Step 807/1000 | Loss: 2.0336\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:28 INFO\u001b[0m Step 807/1000 | Loss: 2.5257\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:28 INFO\u001b[0m Step 807/1000 | Loss: 1.8197\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:28 INFO\u001b[0m Step 807/1000 | Loss: 2.2787\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:28 INFO\u001b[0m Step 807/1000 | Loss: 2.1750\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:28 INFO\u001b[0m Step 808/1000 | Loss: 2.3063\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:28 INFO\u001b[0m Step 808/1000 | Loss: 2.0661\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:28 INFO\u001b[0m Step 808/1000 | Loss: 2.0877\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:28 INFO\u001b[0m Step 808/1000 | Loss: 2.4223\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:28 INFO\u001b[0m Step 808/1000 | Loss: 2.0527\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:28 INFO\u001b[0m Step 808/1000 | Loss: 2.0814\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:28 INFO\u001b[0m Step 808/1000 | Loss: 1.7324\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:28 INFO\u001b[0m Step 808/1000 | Loss: 2.3711\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:29 INFO\u001b[0m Step 809/1000 | Loss: 1.9224\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:29 INFO\u001b[0m Step 809/1000 | Loss: 2.1926\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:29 INFO\u001b[0m Step 809/1000 | Loss: 1.8797\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:29 INFO\u001b[0m Step 809/1000 | Loss: 1.8852\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:29 INFO\u001b[0m Step 809/1000 | Loss: 1.7193\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:29 INFO\u001b[0m Step 809/1000 | Loss: 2.3271\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:29 INFO\u001b[0m Step 809/1000 | Loss: 2.2200\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:29 INFO\u001b[0m Step 809/1000 | Loss: 2.1885\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:29 INFO\u001b[0m Step 810/1000 | Loss: 2.0093\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:29 INFO\u001b[0m Step 810/1000 | Loss: 1.9539\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:29 INFO\u001b[0m Step 810/1000 | Loss: 1.6430\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:29 INFO\u001b[0m Step 810/1000 | Loss: 1.9058\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:29 INFO\u001b[0m Step 810/1000 | Loss: 2.9939\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:29 INFO\u001b[0m Step 810/1000 | Loss: 1.6236\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:29 INFO\u001b[0m Step 810/1000 | Loss: 2.3646\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:29 INFO\u001b[0m Step 810/1000 | Loss: 2.1437\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:30 INFO\u001b[0m Step 811/1000 | Loss: 1.9715\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:30 INFO\u001b[0m Step 811/1000 | Loss: 2.6949\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:30 INFO\u001b[0m Step 811/1000 | Loss: 2.0032\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:30 INFO\u001b[0m Step 811/1000 | Loss: 1.6993\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:30 INFO\u001b[0m Step 811/1000 | Loss: 1.9632\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:30 INFO\u001b[0m Step 811/1000 | Loss: 2.1362\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:30 INFO\u001b[0m Step 811/1000 | Loss: 1.8648\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:30 INFO\u001b[0m Step 811/1000 | Loss: 1.9268\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:30 INFO\u001b[0m Step 812/1000 | Loss: 2.7860\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:30 INFO\u001b[0m Step 812/1000 | Loss: 2.3425\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:30 INFO\u001b[0m Step 812/1000 | Loss: 1.8093\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:30 INFO\u001b[0m Step 812/1000 | Loss: 2.3017\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:30 INFO\u001b[0m Step 812/1000 | Loss: 1.9564\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:30 INFO\u001b[0m Step 812/1000 | Loss: 1.7983\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:30 INFO\u001b[0m Step 812/1000 | Loss: 2.3183\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:30 INFO\u001b[0m Step 812/1000 | Loss: 2.7355\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:30 INFO\u001b[0m Step 813/1000 | Loss: 1.7667\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:30 INFO\u001b[0m Step 813/1000 | Loss: 1.8487\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:30 INFO\u001b[0m Step 813/1000 | Loss: 2.2636\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:30 INFO\u001b[0m Step 813/1000 | Loss: 1.7958\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:30 INFO\u001b[0m Step 813/1000 | Loss: 2.1636\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:30 INFO\u001b[0m Step 813/1000 | Loss: 2.3872\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:30 INFO\u001b[0m Step 813/1000 | Loss: 1.8695\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:30 INFO\u001b[0m Step 813/1000 | Loss: 2.1662\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:31 INFO\u001b[0m Step 814/1000 | Loss: 2.3190\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:31 INFO\u001b[0m Step 814/1000 | Loss: 2.0626\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:31 INFO\u001b[0m Step 814/1000 | Loss: 2.1890\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:31 INFO\u001b[0m Step 814/1000 | Loss: 1.8418\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:31 INFO\u001b[0m Step 814/1000 | Loss: 2.5353\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:31 INFO\u001b[0m Step 814/1000 | Loss: 1.9736\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:31 INFO\u001b[0m Step 814/1000 | Loss: 1.8039\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:31 INFO\u001b[0m Step 814/1000 | Loss: 1.9619\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:31 INFO\u001b[0m Step 815/1000 | Loss: 1.9885\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:31 INFO\u001b[0m Step 815/1000 | Loss: 2.0140\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:31 INFO\u001b[0m Step 815/1000 | Loss: 2.3842\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:31 INFO\u001b[0m Step 815/1000 | Loss: 2.5204\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:31 INFO\u001b[0m Step 815/1000 | Loss: 1.9662\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:31 INFO\u001b[0m Step 815/1000 | Loss: 1.8214\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:31 INFO\u001b[0m Step 815/1000 | Loss: 2.5301\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:31 INFO\u001b[0m Step 815/1000 | Loss: 2.8758\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:32 INFO\u001b[0m Step 816/1000 | Loss: 2.4935\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:32 INFO\u001b[0m Step 816/1000 | Loss: 1.9225\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:32 INFO\u001b[0m Step 816/1000 | Loss: 1.8396\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:32 INFO\u001b[0m Step 816/1000 | Loss: 2.2257\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:32 INFO\u001b[0m Step 816/1000 | Loss: 2.0279\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:32 INFO\u001b[0m Step 816/1000 | Loss: 2.2356\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:32 INFO\u001b[0m Step 816/1000 | Loss: 2.0919\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:32 INFO\u001b[0m Step 816/1000 | Loss: 1.8472\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:32 INFO\u001b[0m Step 817/1000 | Loss: 1.9176\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:32 INFO\u001b[0m Step 817/1000 | Loss: 2.1179\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:32 INFO\u001b[0m Step 817/1000 | Loss: 2.2736\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:32 INFO\u001b[0m Step 817/1000 | Loss: 2.4397\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:32 INFO\u001b[0m Step 817/1000 | Loss: 2.5184\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:32 INFO\u001b[0m Step 817/1000 | Loss: 2.2351\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:32 INFO\u001b[0m Step 817/1000 | Loss: 2.2668\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:32 INFO\u001b[0m Step 817/1000 | Loss: 1.9101\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:32 INFO\u001b[0m Step 818/1000 | Loss: 1.7689\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:32 INFO\u001b[0m Step 818/1000 | Loss: 2.4805\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:32 INFO\u001b[0m Step 818/1000 | Loss: 1.8592\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:32 INFO\u001b[0m Step 818/1000 | Loss: 1.9894\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:32 INFO\u001b[0m Step 818/1000 | Loss: 1.7257\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:32 INFO\u001b[0m Step 818/1000 | Loss: 2.2602\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:32 INFO\u001b[0m Step 818/1000 | Loss: 1.6510\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:32 INFO\u001b[0m Step 818/1000 | Loss: 2.5053\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:33 INFO\u001b[0m Step 819/1000 | Loss: 1.8009\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:33 INFO\u001b[0m Step 819/1000 | Loss: 2.4117\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:33 INFO\u001b[0m Step 819/1000 | Loss: 2.0606\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:33 INFO\u001b[0m Step 819/1000 | Loss: 2.5189\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:33 INFO\u001b[0m Step 819/1000 | Loss: 2.1512\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:33 INFO\u001b[0m Step 819/1000 | Loss: 2.1816\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:33 INFO\u001b[0m Step 819/1000 | Loss: 1.9589\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:33 INFO\u001b[0m Step 819/1000 | Loss: 2.2437\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:33 INFO\u001b[0m Step 820/1000 | Loss: 2.2605\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:33 INFO\u001b[0m Step 820/1000 | Loss: 1.8730\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:33 INFO\u001b[0m Step 820/1000 | Loss: 2.2218\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:33 INFO\u001b[0m Step 820/1000 | Loss: 2.6863\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:33 INFO\u001b[0m Step 820/1000 | Loss: 2.2702\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:33 INFO\u001b[0m Step 820/1000 | Loss: 1.7116\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:33 INFO\u001b[0m Step 820/1000 | Loss: 2.1871\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:33 INFO\u001b[0m Step 820/1000 | Loss: 2.7274\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:34 INFO\u001b[0m Step 821/1000 | Loss: 2.1579\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:34 INFO\u001b[0m Step 821/1000 | Loss: 1.5901\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:34 INFO\u001b[0m Step 821/1000 | Loss: 1.8689\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:34 INFO\u001b[0m Step 821/1000 | Loss: 2.1522\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:34 INFO\u001b[0m Step 821/1000 | Loss: 2.1990\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:34 INFO\u001b[0m Step 821/1000 | Loss: 1.8479\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:34 INFO\u001b[0m Step 821/1000 | Loss: 2.1926\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:34 INFO\u001b[0m Step 821/1000 | Loss: 2.1123\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:34 INFO\u001b[0m Step 822/1000 | Loss: 2.1572\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:34 INFO\u001b[0m Step 822/1000 | Loss: 2.1391\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:34 INFO\u001b[0m Step 822/1000 | Loss: 2.2048\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:34 INFO\u001b[0m Step 822/1000 | Loss: 2.5404\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:34 INFO\u001b[0m Step 822/1000 | Loss: 2.1950\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:34 INFO\u001b[0m Step 822/1000 | Loss: 1.5465\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:34 INFO\u001b[0m Step 822/1000 | Loss: 2.1763\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:34 INFO\u001b[0m Step 822/1000 | Loss: 2.2427\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:34 INFO\u001b[0m Step 823/1000 | Loss: 2.3554\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:34 INFO\u001b[0m Step 823/1000 | Loss: 2.1864\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:34 INFO\u001b[0m Step 823/1000 | Loss: 1.9445\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:34 INFO\u001b[0m Step 823/1000 | Loss: 2.3551\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:34 INFO\u001b[0m Step 823/1000 | Loss: 1.8653\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:34 INFO\u001b[0m Step 823/1000 | Loss: 1.7057\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:34 INFO\u001b[0m Step 823/1000 | Loss: 2.6006\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:34 INFO\u001b[0m Step 823/1000 | Loss: 2.3140\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:35 INFO\u001b[0m Step 824/1000 | Loss: 1.9772\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:35 INFO\u001b[0m Step 824/1000 | Loss: 2.2247\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:35 INFO\u001b[0m Step 824/1000 | Loss: 1.8359\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:35 INFO\u001b[0m Step 824/1000 | Loss: 1.8948\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:35 INFO\u001b[0m Step 824/1000 | Loss: 2.0267\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:35 INFO\u001b[0m Step 824/1000 | Loss: 1.9442\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:35 INFO\u001b[0m Step 824/1000 | Loss: 1.9320\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:35 INFO\u001b[0m Step 824/1000 | Loss: 2.4719\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:35 INFO\u001b[0m Step 825/1000 | Loss: 2.0405\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:35 INFO\u001b[0m Step 825/1000 | Loss: 2.0128\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:35 INFO\u001b[0m Step 825/1000 | Loss: 1.8732\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:35 INFO\u001b[0m Step 825/1000 | Loss: 2.1116\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:35 INFO\u001b[0m Step 825/1000 | Loss: 2.0898\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:35 INFO\u001b[0m Step 825/1000 | Loss: 2.1604\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:35 INFO\u001b[0m Step 825/1000 | Loss: 1.9202\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:35 INFO\u001b[0m Step 825/1000 | Loss: 1.8860\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:36 INFO\u001b[0m Step 826/1000 | Loss: 2.1531\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:36 INFO\u001b[0m Step 826/1000 | Loss: 1.9021\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:36 INFO\u001b[0m Step 826/1000 | Loss: 2.3235\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:36 INFO\u001b[0m Step 826/1000 | Loss: 1.7935\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:36 INFO\u001b[0m Step 826/1000 | Loss: 2.0761\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:36 INFO\u001b[0m Step 826/1000 | Loss: 1.7028\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:36 INFO\u001b[0m Step 826/1000 | Loss: 1.9751\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:36 INFO\u001b[0m Step 826/1000 | Loss: 2.0016\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:36 INFO\u001b[0m Step 827/1000 | Loss: 2.2469\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:36 INFO\u001b[0m Step 827/1000 | Loss: 1.7645\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:36 INFO\u001b[0m Step 827/1000 | Loss: 2.6294\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:36 INFO\u001b[0m Step 827/1000 | Loss: 1.9562\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:36 INFO\u001b[0m Step 827/1000 | Loss: 2.0988\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:36 INFO\u001b[0m Step 827/1000 | Loss: 2.0474\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:36 INFO\u001b[0m Step 827/1000 | Loss: 2.1877\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:36 INFO\u001b[0m Step 827/1000 | Loss: 2.4664\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:36 INFO\u001b[0m Step 828/1000 | Loss: 1.9003\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:36 INFO\u001b[0m Step 828/1000 | Loss: 1.9429\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:36 INFO\u001b[0m Step 828/1000 | Loss: 2.2430\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:36 INFO\u001b[0m Step 828/1000 | Loss: 2.0900\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:36 INFO\u001b[0m Step 828/1000 | Loss: 1.8409\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:36 INFO\u001b[0m Step 828/1000 | Loss: 2.0495\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:36 INFO\u001b[0m Step 828/1000 | Loss: 2.1941\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:36 INFO\u001b[0m Step 828/1000 | Loss: 1.7148\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:37 INFO\u001b[0m Step 829/1000 | Loss: 2.6213\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:37 INFO\u001b[0m Step 829/1000 | Loss: 2.0632\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:37 INFO\u001b[0m Step 829/1000 | Loss: 2.0439\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:37 INFO\u001b[0m Step 829/1000 | Loss: 2.6061\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:37 INFO\u001b[0m Step 829/1000 | Loss: 1.8763\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:37 INFO\u001b[0m Step 829/1000 | Loss: 2.1156\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:37 INFO\u001b[0m Step 829/1000 | Loss: 2.3143\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:37 INFO\u001b[0m Step 829/1000 | Loss: 1.9758\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:37 INFO\u001b[0m Step 830/1000 | Loss: 2.2712\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:37 INFO\u001b[0m Step 830/1000 | Loss: 2.2189\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:37 INFO\u001b[0m Step 830/1000 | Loss: 2.3214\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:37 INFO\u001b[0m Step 830/1000 | Loss: 2.2385\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:37 INFO\u001b[0m Step 830/1000 | Loss: 2.2761\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:37 INFO\u001b[0m Step 830/1000 | Loss: 2.2955\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:37 INFO\u001b[0m Step 830/1000 | Loss: 1.7924\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:37 INFO\u001b[0m Step 830/1000 | Loss: 2.0906\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:38 INFO\u001b[0m Step 831/1000 | Loss: 2.3450\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:38 INFO\u001b[0m Step 831/1000 | Loss: 1.8560\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:38 INFO\u001b[0m Step 831/1000 | Loss: 2.7423\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:38 INFO\u001b[0m Step 831/1000 | Loss: 1.9503\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:38 INFO\u001b[0m Step 831/1000 | Loss: 2.0622\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:38 INFO\u001b[0m Step 831/1000 | Loss: 2.2786\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:38 INFO\u001b[0m Step 831/1000 | Loss: 2.1947\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:38 INFO\u001b[0m Step 831/1000 | Loss: 2.1561\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:38 INFO\u001b[0m Step 832/1000 | Loss: 2.5454\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:38 INFO\u001b[0m Step 832/1000 | Loss: 1.7552\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:38 INFO\u001b[0m Step 832/1000 | Loss: 2.5009\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:38 INFO\u001b[0m Step 832/1000 | Loss: 1.9129\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:38 INFO\u001b[0m Step 832/1000 | Loss: 1.6454\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:38 INFO\u001b[0m Step 832/1000 | Loss: 2.2234\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:38 INFO\u001b[0m Step 832/1000 | Loss: 2.0437\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:38 INFO\u001b[0m Step 832/1000 | Loss: 1.8985\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:38 INFO\u001b[0m Step 833/1000 | Loss: 1.9745\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:38 INFO\u001b[0m Step 833/1000 | Loss: 2.0499\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:38 INFO\u001b[0m Step 833/1000 | Loss: 2.0877\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:38 INFO\u001b[0m Step 833/1000 | Loss: 2.5160\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:38 INFO\u001b[0m Step 833/1000 | Loss: 2.4708\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:38 INFO\u001b[0m Step 833/1000 | Loss: 1.6855\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:38 INFO\u001b[0m Step 833/1000 | Loss: 2.3771\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:38 INFO\u001b[0m Step 833/1000 | Loss: 2.2281\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:39 INFO\u001b[0m Step 834/1000 | Loss: 2.5498\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:39 INFO\u001b[0m Step 834/1000 | Loss: 2.9111\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:39 INFO\u001b[0m Step 834/1000 | Loss: 2.3794\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:39 INFO\u001b[0m Step 834/1000 | Loss: 2.0801\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:39 INFO\u001b[0m Step 834/1000 | Loss: 1.9502\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:39 INFO\u001b[0m Step 834/1000 | Loss: 2.3180\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:39 INFO\u001b[0m Step 834/1000 | Loss: 2.0870\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:39 INFO\u001b[0m Step 834/1000 | Loss: 2.2473\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:39 INFO\u001b[0m Step 835/1000 | Loss: 2.0988\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:39 INFO\u001b[0m Step 835/1000 | Loss: 2.6410\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:39 INFO\u001b[0m Step 835/1000 | Loss: 1.9365\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:39 INFO\u001b[0m Step 835/1000 | Loss: 2.0169\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:39 INFO\u001b[0m Step 835/1000 | Loss: 1.6697\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:39 INFO\u001b[0m Step 835/1000 | Loss: 2.4253\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:39 INFO\u001b[0m Step 835/1000 | Loss: 2.4094\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:39 INFO\u001b[0m Step 835/1000 | Loss: 2.2282\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:40 INFO\u001b[0m Step 836/1000 | Loss: 1.9348\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:40 INFO\u001b[0m Step 836/1000 | Loss: 2.5488\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:40 INFO\u001b[0m Step 836/1000 | Loss: 1.7915\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:40 INFO\u001b[0m Step 836/1000 | Loss: 2.3709\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:40 INFO\u001b[0m Step 836/1000 | Loss: 2.0193\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:40 INFO\u001b[0m Step 836/1000 | Loss: 2.0059\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:40 INFO\u001b[0m Step 836/1000 | Loss: 2.8038\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:40 INFO\u001b[0m Step 836/1000 | Loss: 2.9962\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:40 INFO\u001b[0m Step 837/1000 | Loss: 2.0301\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:40 INFO\u001b[0m Step 837/1000 | Loss: 1.8706\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:40 INFO\u001b[0m Step 837/1000 | Loss: 2.0967\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:40 INFO\u001b[0m Step 837/1000 | Loss: 2.1314\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:40 INFO\u001b[0m Step 837/1000 | Loss: 2.3559\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:40 INFO\u001b[0m Step 837/1000 | Loss: 1.9383\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:40 INFO\u001b[0m Step 837/1000 | Loss: 2.3320\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:40 INFO\u001b[0m Step 837/1000 | Loss: 2.6588\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:40 INFO\u001b[0m Step 838/1000 | Loss: 2.3025\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:40 INFO\u001b[0m Step 838/1000 | Loss: 2.2441\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:40 INFO\u001b[0m Step 838/1000 | Loss: 2.2377\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:40 INFO\u001b[0m Step 838/1000 | Loss: 1.7775\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:40 INFO\u001b[0m Step 838/1000 | Loss: 2.2170\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:40 INFO\u001b[0m Step 838/1000 | Loss: 2.2104\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:40 INFO\u001b[0m Step 838/1000 | Loss: 2.1643\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:40 INFO\u001b[0m Step 838/1000 | Loss: 2.4145\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:41 INFO\u001b[0m Step 839/1000 | Loss: 2.1225\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:41 INFO\u001b[0m Step 839/1000 | Loss: 1.7974\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:41 INFO\u001b[0m Step 839/1000 | Loss: 2.4707\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:41 INFO\u001b[0m Step 839/1000 | Loss: 2.1366\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:41 INFO\u001b[0m Step 839/1000 | Loss: 1.9569\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:41 INFO\u001b[0m Step 839/1000 | Loss: 1.9776\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:41 INFO\u001b[0m Step 839/1000 | Loss: 2.1493\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:41 INFO\u001b[0m Step 839/1000 | Loss: 2.2239\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:41 INFO\u001b[0m Step 840/1000 | Loss: 2.0309\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:41 INFO\u001b[0m Step 840/1000 | Loss: 2.4565\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:41 INFO\u001b[0m Step 840/1000 | Loss: 1.9556\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:41 INFO\u001b[0m Step 840/1000 | Loss: 2.0397\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:41 INFO\u001b[0m Step 840/1000 | Loss: 2.2760\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:41 INFO\u001b[0m Step 840/1000 | Loss: 2.0538\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:41 INFO\u001b[0m Step 840/1000 | Loss: 2.0470\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:41 INFO\u001b[0m Step 840/1000 | Loss: 2.1124\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:42 INFO\u001b[0m Step 841/1000 | Loss: 2.9589\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:42 INFO\u001b[0m Step 841/1000 | Loss: 2.7204\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:42 INFO\u001b[0m Step 841/1000 | Loss: 2.1805\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:42 INFO\u001b[0m Step 841/1000 | Loss: 2.0211\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:42 INFO\u001b[0m Step 841/1000 | Loss: 1.6323\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:42 INFO\u001b[0m Step 841/1000 | Loss: 2.1378\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:42 INFO\u001b[0m Step 841/1000 | Loss: 2.1864\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:42 INFO\u001b[0m Step 841/1000 | Loss: 1.8205\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:42 INFO\u001b[0m Step 842/1000 | Loss: 2.5167\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:42 INFO\u001b[0m Step 842/1000 | Loss: 2.0753\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:42 INFO\u001b[0m Step 842/1000 | Loss: 2.7788\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:42 INFO\u001b[0m Step 842/1000 | Loss: 1.6372\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:42 INFO\u001b[0m Step 842/1000 | Loss: 2.2387\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:42 INFO\u001b[0m Step 842/1000 | Loss: 2.0586\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:42 INFO\u001b[0m Step 842/1000 | Loss: 1.9435\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:42 INFO\u001b[0m Step 842/1000 | Loss: 2.3114\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:42 INFO\u001b[0m Step 843/1000 | Loss: 2.0774\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:42 INFO\u001b[0m Step 843/1000 | Loss: 2.4358\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:42 INFO\u001b[0m Step 843/1000 | Loss: 2.6156\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:42 INFO\u001b[0m Step 843/1000 | Loss: 2.3869\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:42 INFO\u001b[0m Step 843/1000 | Loss: 2.1678\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:42 INFO\u001b[0m Step 843/1000 | Loss: 2.0563\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:42 INFO\u001b[0m Step 843/1000 | Loss: 1.4064\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:42 INFO\u001b[0m Step 843/1000 | Loss: 2.0717\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:43 INFO\u001b[0m Step 844/1000 | Loss: 1.6025\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:43 INFO\u001b[0m Step 844/1000 | Loss: 2.0117\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:43 INFO\u001b[0m Step 844/1000 | Loss: 1.6483\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:43 INFO\u001b[0m Step 844/1000 | Loss: 2.2610\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:43 INFO\u001b[0m Step 844/1000 | Loss: 1.7688\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:43 INFO\u001b[0m Step 844/1000 | Loss: 2.2615\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:43 INFO\u001b[0m Step 844/1000 | Loss: 2.8019\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:43 INFO\u001b[0m Step 844/1000 | Loss: 1.8335\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:43 INFO\u001b[0m Step 845/1000 | Loss: 2.0919\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:43 INFO\u001b[0m Step 845/1000 | Loss: 2.2567\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:43 INFO\u001b[0m Step 845/1000 | Loss: 1.7205\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:43 INFO\u001b[0m Step 845/1000 | Loss: 2.6856\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:43 INFO\u001b[0m Step 845/1000 | Loss: 2.4251\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:43 INFO\u001b[0m Step 845/1000 | Loss: 1.9058\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:43 INFO\u001b[0m Step 845/1000 | Loss: 2.1444\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:43 INFO\u001b[0m Step 845/1000 | Loss: 1.8734\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:44 INFO\u001b[0m Step 846/1000 | Loss: 2.3831\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:44 INFO\u001b[0m Step 846/1000 | Loss: 1.9884\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:44 INFO\u001b[0m Step 846/1000 | Loss: 2.0880\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:44 INFO\u001b[0m Step 846/1000 | Loss: 2.0495\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:44 INFO\u001b[0m Step 846/1000 | Loss: 2.4988\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:44 INFO\u001b[0m Step 846/1000 | Loss: 2.0318\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:44 INFO\u001b[0m Step 846/1000 | Loss: 2.0123\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:44 INFO\u001b[0m Step 846/1000 | Loss: 2.2139\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:44 INFO\u001b[0m Step 847/1000 | Loss: 1.8691\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:44 INFO\u001b[0m Step 847/1000 | Loss: 2.9497\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:44 INFO\u001b[0m Step 847/1000 | Loss: 2.3265\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:44 INFO\u001b[0m Step 847/1000 | Loss: 1.8652\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:44 INFO\u001b[0m Step 847/1000 | Loss: 1.9834\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:44 INFO\u001b[0m Step 847/1000 | Loss: 1.8994\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:44 INFO\u001b[0m Step 847/1000 | Loss: 1.9241\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:44 INFO\u001b[0m Step 847/1000 | Loss: 2.2946\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:44 INFO\u001b[0m Step 848/1000 | Loss: 2.0590\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:44 INFO\u001b[0m Step 848/1000 | Loss: 2.2189\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:44 INFO\u001b[0m Step 848/1000 | Loss: 2.2178\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:44 INFO\u001b[0m Step 848/1000 | Loss: 2.4338\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:44 INFO\u001b[0m Step 848/1000 | Loss: 2.4399\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:44 INFO\u001b[0m Step 848/1000 | Loss: 2.0204\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:44 INFO\u001b[0m Step 848/1000 | Loss: 2.3257\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:44 INFO\u001b[0m Step 848/1000 | Loss: 2.3385\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:45 INFO\u001b[0m Step 849/1000 | Loss: 1.9283\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:45 INFO\u001b[0m Step 849/1000 | Loss: 2.1906\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:45 INFO\u001b[0m Step 849/1000 | Loss: 1.9962\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:45 INFO\u001b[0m Step 849/1000 | Loss: 2.0100\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:45 INFO\u001b[0m Step 849/1000 | Loss: 2.6626\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:45 INFO\u001b[0m Step 849/1000 | Loss: 1.5653\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:45 INFO\u001b[0m Step 849/1000 | Loss: 1.6511\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:45 INFO\u001b[0m Step 849/1000 | Loss: 2.2884\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:45 INFO\u001b[0m Step 850/1000 | Loss: 1.9900\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:45 INFO\u001b[0m Step 850/1000 | Loss: 2.5861\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:45 INFO\u001b[0m Step 850/1000 | Loss: 1.9288\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:45 INFO\u001b[0m Step 850/1000 | Loss: 1.8886\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:45 INFO\u001b[0m Step 850/1000 | Loss: 1.9219\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:45 INFO\u001b[0m Step 850/1000 | Loss: 1.9885\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:45 INFO\u001b[0m Step 850/1000 | Loss: 2.0983\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:45 INFO\u001b[0m Step 850/1000 | Loss: 1.6964\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:46 INFO\u001b[0m Step 851/1000 | Loss: 2.3554\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:46 INFO\u001b[0m Step 851/1000 | Loss: 2.4385\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:46 INFO\u001b[0m Step 851/1000 | Loss: 2.0680\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:46 INFO\u001b[0m Step 851/1000 | Loss: 1.9727\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:46 INFO\u001b[0m Step 851/1000 | Loss: 3.2123\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:46 INFO\u001b[0m Step 851/1000 | Loss: 1.6575\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:46 INFO\u001b[0m Step 851/1000 | Loss: 2.2119\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:46 INFO\u001b[0m Step 851/1000 | Loss: 2.5276\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:46 INFO\u001b[0m Step 852/1000 | Loss: 2.1825\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:46 INFO\u001b[0m Step 852/1000 | Loss: 1.6226\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:46 INFO\u001b[0m Step 852/1000 | Loss: 2.0170\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:46 INFO\u001b[0m Step 852/1000 | Loss: 2.9115\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:46 INFO\u001b[0m Step 852/1000 | Loss: 1.9031\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:46 INFO\u001b[0m Step 852/1000 | Loss: 2.1375\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:46 INFO\u001b[0m Step 852/1000 | Loss: 2.0037\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:46 INFO\u001b[0m Step 852/1000 | Loss: 2.1347\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:47 INFO\u001b[0m Step 853/1000 | Loss: 1.5644\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:47 INFO\u001b[0m Step 853/1000 | Loss: 2.1823\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:47 INFO\u001b[0m Step 853/1000 | Loss: 2.0980\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:47 INFO\u001b[0m Step 853/1000 | Loss: 1.6109\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:47 INFO\u001b[0m Step 853/1000 | Loss: 2.5734\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:47 INFO\u001b[0m Step 853/1000 | Loss: 1.8297\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:47 INFO\u001b[0m Step 853/1000 | Loss: 1.5874\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:47 INFO\u001b[0m Step 853/1000 | Loss: 2.4169\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:47 INFO\u001b[0m Step 854/1000 | Loss: 1.8673\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:47 INFO\u001b[0m Step 854/1000 | Loss: 2.1995\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:47 INFO\u001b[0m Step 854/1000 | Loss: 1.9303\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:47 INFO\u001b[0m Step 854/1000 | Loss: 1.9412\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:47 INFO\u001b[0m Step 854/1000 | Loss: 1.7228\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:47 INFO\u001b[0m Step 854/1000 | Loss: 2.2699\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:47 INFO\u001b[0m Step 854/1000 | Loss: 2.3508\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:47 INFO\u001b[0m Step 854/1000 | Loss: 1.9626\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:47 INFO\u001b[0m Step 855/1000 | Loss: 1.8430\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:47 INFO\u001b[0m Step 855/1000 | Loss: 2.4107\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:47 INFO\u001b[0m Step 855/1000 | Loss: 1.7811\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:47 INFO\u001b[0m Step 855/1000 | Loss: 2.0574\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:47 INFO\u001b[0m Step 855/1000 | Loss: 1.8168\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:47 INFO\u001b[0m Step 855/1000 | Loss: 1.9968\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:47 INFO\u001b[0m Step 855/1000 | Loss: 1.8210\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:47 INFO\u001b[0m Step 855/1000 | Loss: 2.0011\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:48 INFO\u001b[0m Step 856/1000 | Loss: 2.5369\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:48 INFO\u001b[0m Step 856/1000 | Loss: 2.4118\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:48 INFO\u001b[0m Step 856/1000 | Loss: 2.3736\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:48 INFO\u001b[0m Step 856/1000 | Loss: 2.1606\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:48 INFO\u001b[0m Step 856/1000 | Loss: 2.0417\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:48 INFO\u001b[0m Step 856/1000 | Loss: 2.1040\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:48 INFO\u001b[0m Step 856/1000 | Loss: 1.9686\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:48 INFO\u001b[0m Step 856/1000 | Loss: 1.9465\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:48 INFO\u001b[0m Step 857/1000 | Loss: 1.7359\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:48 INFO\u001b[0m Step 857/1000 | Loss: 1.9654\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:48 INFO\u001b[0m Step 857/1000 | Loss: 1.9105\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:48 INFO\u001b[0m Step 857/1000 | Loss: 2.1635\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:48 INFO\u001b[0m Step 857/1000 | Loss: 2.0571\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:48 INFO\u001b[0m Step 857/1000 | Loss: 2.1608\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:48 INFO\u001b[0m Step 857/1000 | Loss: 1.9845\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:48 INFO\u001b[0m Step 857/1000 | Loss: 2.1708\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:49 INFO\u001b[0m Step 858/1000 | Loss: 2.2439\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:49 INFO\u001b[0m Step 858/1000 | Loss: 2.7395\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:49 INFO\u001b[0m Step 858/1000 | Loss: 2.1162\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:49 INFO\u001b[0m Step 858/1000 | Loss: 2.1443\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:49 INFO\u001b[0m Step 858/1000 | Loss: 2.3069\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:49 INFO\u001b[0m Step 858/1000 | Loss: 2.0458\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:49 INFO\u001b[0m Step 858/1000 | Loss: 1.7712\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:49 INFO\u001b[0m Step 858/1000 | Loss: 1.7315\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:49 INFO\u001b[0m Step 859/1000 | Loss: 2.0996\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:49 INFO\u001b[0m Step 859/1000 | Loss: 1.9178\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:49 INFO\u001b[0m Step 859/1000 | Loss: 1.7618\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:49 INFO\u001b[0m Step 859/1000 | Loss: 1.9344\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:49 INFO\u001b[0m Step 859/1000 | Loss: 1.9561\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:49 INFO\u001b[0m Step 859/1000 | Loss: 2.0731\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:49 INFO\u001b[0m Step 859/1000 | Loss: 1.7492\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:49 INFO\u001b[0m Step 859/1000 | Loss: 1.9803\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:49 INFO\u001b[0m Step 860/1000 | Loss: 2.2224\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:49 INFO\u001b[0m Step 860/1000 | Loss: 1.7105\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:49 INFO\u001b[0m Step 860/1000 | Loss: 2.1123\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:49 INFO\u001b[0m Step 860/1000 | Loss: 1.8494\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:49 INFO\u001b[0m Step 860/1000 | Loss: 1.8151\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:49 INFO\u001b[0m Step 860/1000 | Loss: 1.6942\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:49 INFO\u001b[0m Step 860/1000 | Loss: 1.9557\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:49 INFO\u001b[0m Step 860/1000 | Loss: 2.1293\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:50 INFO\u001b[0m Step 861/1000 | Loss: 1.9085\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:50 INFO\u001b[0m Step 861/1000 | Loss: 2.2030\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:50 INFO\u001b[0m Step 861/1000 | Loss: 1.8957\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:50 INFO\u001b[0m Step 861/1000 | Loss: 2.2671\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:50 INFO\u001b[0m Step 861/1000 | Loss: 2.4074\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:50 INFO\u001b[0m Step 861/1000 | Loss: 2.1500\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:50 INFO\u001b[0m Step 861/1000 | Loss: 1.7764\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:50 INFO\u001b[0m Step 861/1000 | Loss: 2.6943\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:50 INFO\u001b[0m Step 862/1000 | Loss: 2.0129\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:50 INFO\u001b[0m Step 862/1000 | Loss: 1.6170\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:50 INFO\u001b[0m Step 862/1000 | Loss: 2.2349\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:50 INFO\u001b[0m Step 862/1000 | Loss: 2.2307\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:50 INFO\u001b[0m Step 862/1000 | Loss: 2.3063\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:50 INFO\u001b[0m Step 862/1000 | Loss: 2.4596\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:50 INFO\u001b[0m Step 862/1000 | Loss: 2.1189\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:50 INFO\u001b[0m Step 862/1000 | Loss: 1.7785\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:51 INFO\u001b[0m Step 863/1000 | Loss: 1.9334\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:51 INFO\u001b[0m Step 863/1000 | Loss: 1.8308\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:51 INFO\u001b[0m Step 863/1000 | Loss: 1.9016\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:51 INFO\u001b[0m Step 863/1000 | Loss: 1.8373\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:51 INFO\u001b[0m Step 863/1000 | Loss: 2.3383\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:51 INFO\u001b[0m Step 863/1000 | Loss: 1.9734\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:51 INFO\u001b[0m Step 863/1000 | Loss: 1.8023\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:51 INFO\u001b[0m Step 863/1000 | Loss: 1.9778\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:51 INFO\u001b[0m Step 864/1000 | Loss: 1.8397\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:51 INFO\u001b[0m Step 864/1000 | Loss: 2.3299\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:51 INFO\u001b[0m Step 864/1000 | Loss: 1.6855\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:51 INFO\u001b[0m Step 864/1000 | Loss: 2.0019\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:51 INFO\u001b[0m Step 864/1000 | Loss: 1.9079\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:51 INFO\u001b[0m Step 864/1000 | Loss: 1.8897\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:51 INFO\u001b[0m Step 864/1000 | Loss: 1.6109\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:51 INFO\u001b[0m Step 864/1000 | Loss: 2.4018\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:51 INFO\u001b[0m Step 865/1000 | Loss: 1.8064\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:51 INFO\u001b[0m Step 865/1000 | Loss: 2.0114\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:51 INFO\u001b[0m Step 865/1000 | Loss: 2.3575\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:51 INFO\u001b[0m Step 865/1000 | Loss: 1.7410\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:51 INFO\u001b[0m Step 865/1000 | Loss: 2.3351\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:51 INFO\u001b[0m Step 865/1000 | Loss: 2.4643\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:51 INFO\u001b[0m Step 865/1000 | Loss: 1.7860\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:51 INFO\u001b[0m Step 865/1000 | Loss: 1.9102\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:52 INFO\u001b[0m Step 866/1000 | Loss: 2.3414\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:52 INFO\u001b[0m Step 866/1000 | Loss: 1.7709\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:52 INFO\u001b[0m Step 866/1000 | Loss: 1.9157\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:52 INFO\u001b[0m Step 866/1000 | Loss: 1.9037\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:52 INFO\u001b[0m Step 866/1000 | Loss: 1.7969\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:52 INFO\u001b[0m Step 866/1000 | Loss: 2.1628\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:52 INFO\u001b[0m Step 866/1000 | Loss: 2.0944\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:52 INFO\u001b[0m Step 866/1000 | Loss: 1.6077\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:52 INFO\u001b[0m Step 867/1000 | Loss: 1.7210\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:52 INFO\u001b[0m Step 867/1000 | Loss: 1.8344\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:52 INFO\u001b[0m Step 867/1000 | Loss: 2.0783\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:52 INFO\u001b[0m Step 867/1000 | Loss: 2.2023\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:52 INFO\u001b[0m Step 867/1000 | Loss: 1.8627\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:52 INFO\u001b[0m Step 867/1000 | Loss: 2.2554\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:52 INFO\u001b[0m Step 867/1000 | Loss: 1.9947\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:52 INFO\u001b[0m Step 867/1000 | Loss: 1.9110\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:53 INFO\u001b[0m Step 868/1000 | Loss: 2.1515\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:53 INFO\u001b[0m Step 868/1000 | Loss: 1.9778\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:53 INFO\u001b[0m Step 868/1000 | Loss: 2.2064\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:53 INFO\u001b[0m Step 868/1000 | Loss: 2.6272\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:53 INFO\u001b[0m Step 868/1000 | Loss: 2.3821\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:53 INFO\u001b[0m Step 868/1000 | Loss: 2.3863\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:53 INFO\u001b[0m Step 868/1000 | Loss: 1.6473\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:53 INFO\u001b[0m Step 868/1000 | Loss: 2.4540\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:53 INFO\u001b[0m Step 869/1000 | Loss: 1.8144\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:53 INFO\u001b[0m Step 869/1000 | Loss: 2.7138\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:53 INFO\u001b[0m Step 869/1000 | Loss: 2.4621\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:53 INFO\u001b[0m Step 869/1000 | Loss: 1.8678\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:53 INFO\u001b[0m Step 869/1000 | Loss: 1.9270\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:53 INFO\u001b[0m Step 869/1000 | Loss: 2.0176\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:53 INFO\u001b[0m Step 869/1000 | Loss: 1.5138\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:53 INFO\u001b[0m Step 869/1000 | Loss: 2.0204\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:53 INFO\u001b[0m Step 870/1000 | Loss: 2.3694\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:53 INFO\u001b[0m Step 870/1000 | Loss: 2.7046\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:53 INFO\u001b[0m Step 870/1000 | Loss: 2.1157\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:53 INFO\u001b[0m Step 870/1000 | Loss: 2.2037\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:53 INFO\u001b[0m Step 870/1000 | Loss: 1.9990\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:53 INFO\u001b[0m Step 870/1000 | Loss: 1.9500\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:53 INFO\u001b[0m Step 870/1000 | Loss: 1.8404\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:53 INFO\u001b[0m Step 870/1000 | Loss: 2.2123\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:54 INFO\u001b[0m Step 871/1000 | Loss: 2.1631\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:54 INFO\u001b[0m Step 871/1000 | Loss: 1.8218\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:54 INFO\u001b[0m Step 871/1000 | Loss: 2.3587\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:54 INFO\u001b[0m Step 871/1000 | Loss: 2.0936\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:54 INFO\u001b[0m Step 871/1000 | Loss: 2.1766\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:54 INFO\u001b[0m Step 871/1000 | Loss: 1.9070\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:54 INFO\u001b[0m Step 871/1000 | Loss: 1.8600\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:54 INFO\u001b[0m Step 871/1000 | Loss: 2.0890\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:54 INFO\u001b[0m Step 872/1000 | Loss: 2.0773\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:54 INFO\u001b[0m Step 872/1000 | Loss: 1.8314\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:54 INFO\u001b[0m Step 872/1000 | Loss: 1.6418\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:54 INFO\u001b[0m Step 872/1000 | Loss: 2.2786\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:54 INFO\u001b[0m Step 872/1000 | Loss: 1.6194\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:54 INFO\u001b[0m Step 872/1000 | Loss: 1.8946\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:54 INFO\u001b[0m Step 872/1000 | Loss: 1.9011\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:54 INFO\u001b[0m Step 872/1000 | Loss: 2.0533\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:55 INFO\u001b[0m Step 873/1000 | Loss: 1.6134\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:55 INFO\u001b[0m Step 873/1000 | Loss: 1.6809\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:55 INFO\u001b[0m Step 873/1000 | Loss: 1.6137\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:55 INFO\u001b[0m Step 873/1000 | Loss: 1.9850\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:55 INFO\u001b[0m Step 873/1000 | Loss: 1.8358\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:55 INFO\u001b[0m Step 873/1000 | Loss: 2.3000\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:55 INFO\u001b[0m Step 873/1000 | Loss: 1.9080\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:55 INFO\u001b[0m Step 873/1000 | Loss: 2.3653\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:55 INFO\u001b[0m Step 874/1000 | Loss: 1.8938\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:55 INFO\u001b[0m Step 874/1000 | Loss: 2.1819\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:55 INFO\u001b[0m Step 874/1000 | Loss: 2.1038\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:55 INFO\u001b[0m Step 874/1000 | Loss: 2.0470\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:55 INFO\u001b[0m Step 874/1000 | Loss: 1.7303\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:55 INFO\u001b[0m Step 874/1000 | Loss: 2.3778\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:55 INFO\u001b[0m Step 874/1000 | Loss: 1.5678\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:55 INFO\u001b[0m Step 874/1000 | Loss: 2.1449\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:55 INFO\u001b[0m Step 875/1000 | Loss: 2.1064\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:55 INFO\u001b[0m Step 875/1000 | Loss: 2.1397\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:55 INFO\u001b[0m Step 875/1000 | Loss: 1.9009\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:55 INFO\u001b[0m Step 875/1000 | Loss: 2.4031\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:55 INFO\u001b[0m Step 875/1000 | Loss: 1.4752\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:55 INFO\u001b[0m Step 875/1000 | Loss: 2.1961\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:55 INFO\u001b[0m Step 875/1000 | Loss: 1.5947\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:55 INFO\u001b[0m Step 875/1000 | Loss: 2.1173\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:56 INFO\u001b[0m Step 876/1000 | Loss: 1.6489\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:56 INFO\u001b[0m Step 876/1000 | Loss: 2.3104\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:56 INFO\u001b[0m Step 876/1000 | Loss: 1.6396\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:56 INFO\u001b[0m Step 876/1000 | Loss: 2.3064\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:56 INFO\u001b[0m Step 876/1000 | Loss: 1.5919\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:56 INFO\u001b[0m Step 876/1000 | Loss: 2.1451\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:56 INFO\u001b[0m Step 876/1000 | Loss: 2.0704\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:56 INFO\u001b[0m Step 876/1000 | Loss: 2.0428\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:56 INFO\u001b[0m Step 877/1000 | Loss: 2.0833\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:56 INFO\u001b[0m Step 877/1000 | Loss: 2.3275\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:56 INFO\u001b[0m Step 877/1000 | Loss: 1.9909\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:56 INFO\u001b[0m Step 877/1000 | Loss: 2.4099\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:56 INFO\u001b[0m Step 877/1000 | Loss: 1.7344\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:56 INFO\u001b[0m Step 877/1000 | Loss: 1.9795\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:56 INFO\u001b[0m Step 877/1000 | Loss: 2.0880\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:56 INFO\u001b[0m Step 877/1000 | Loss: 2.0422\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:57 INFO\u001b[0m Step 878/1000 | Loss: 2.5698\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:57 INFO\u001b[0m Step 878/1000 | Loss: 2.5275\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:57 INFO\u001b[0m Step 878/1000 | Loss: 1.8147\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:57 INFO\u001b[0m Step 878/1000 | Loss: 1.9559\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:57 INFO\u001b[0m Step 878/1000 | Loss: 1.7812\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:57 INFO\u001b[0m Step 878/1000 | Loss: 1.8049\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:57 INFO\u001b[0m Step 878/1000 | Loss: 2.1364\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:57 INFO\u001b[0m Step 878/1000 | Loss: 2.1650\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:57 INFO\u001b[0m Step 879/1000 | Loss: 2.0049\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:57 INFO\u001b[0m Step 879/1000 | Loss: 2.0134\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:57 INFO\u001b[0m Step 879/1000 | Loss: 1.6854\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:57 INFO\u001b[0m Step 879/1000 | Loss: 2.3887\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:57 INFO\u001b[0m Step 879/1000 | Loss: 1.8562\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:57 INFO\u001b[0m Step 879/1000 | Loss: 2.1145\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:57 INFO\u001b[0m Step 879/1000 | Loss: 2.0158\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:57 INFO\u001b[0m Step 879/1000 | Loss: 2.1320\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:57 INFO\u001b[0m Step 880/1000 | Loss: 1.8304\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:57 INFO\u001b[0m Step 880/1000 | Loss: 2.3295\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:57 INFO\u001b[0m Step 880/1000 | Loss: 2.3289\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:57 INFO\u001b[0m Step 880/1000 | Loss: 1.9133\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:57 INFO\u001b[0m Step 880/1000 | Loss: 1.7953\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:57 INFO\u001b[0m Step 880/1000 | Loss: 2.5267\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:57 INFO\u001b[0m Step 880/1000 | Loss: 2.5136\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:57 INFO\u001b[0m Step 880/1000 | Loss: 1.7159\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:58 INFO\u001b[0m Step 881/1000 | Loss: 1.7261\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:58 INFO\u001b[0m Step 881/1000 | Loss: 1.8076\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:58 INFO\u001b[0m Step 881/1000 | Loss: 1.9493\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:58 INFO\u001b[0m Step 881/1000 | Loss: 1.7852\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:58 INFO\u001b[0m Step 881/1000 | Loss: 2.0269\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:58 INFO\u001b[0m Step 881/1000 | Loss: 2.2802\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:58 INFO\u001b[0m Step 881/1000 | Loss: 2.0840\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:58 INFO\u001b[0m Step 881/1000 | Loss: 1.5762\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:58 INFO\u001b[0m Step 882/1000 | Loss: 2.1852\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:58 INFO\u001b[0m Step 882/1000 | Loss: 2.4615\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:58 INFO\u001b[0m Step 882/1000 | Loss: 2.2107\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:58 INFO\u001b[0m Step 882/1000 | Loss: 2.1949\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:58 INFO\u001b[0m Step 882/1000 | Loss: 2.1754\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:58 INFO\u001b[0m Step 882/1000 | Loss: 1.9720\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:58 INFO\u001b[0m Step 882/1000 | Loss: 2.0585\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:58 INFO\u001b[0m Step 882/1000 | Loss: 2.2608\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:59 INFO\u001b[0m Step 883/1000 | Loss: 1.8885\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:59 INFO\u001b[0m Step 883/1000 | Loss: 2.0424\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:59 INFO\u001b[0m Step 883/1000 | Loss: 2.1856\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:59 INFO\u001b[0m Step 883/1000 | Loss: 2.6516\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:59 INFO\u001b[0m Step 883/1000 | Loss: 2.0259\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:59 INFO\u001b[0m Step 883/1000 | Loss: 2.3105\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:59 INFO\u001b[0m Step 883/1000 | Loss: 1.4684\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:59 INFO\u001b[0m Step 883/1000 | Loss: 1.8674\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:59 INFO\u001b[0m Step 884/1000 | Loss: 1.8816\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:59 INFO\u001b[0m Step 884/1000 | Loss: 1.8211\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:59 INFO\u001b[0m Step 884/1000 | Loss: 2.5440\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:59 INFO\u001b[0m Step 884/1000 | Loss: 2.3327\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:59 INFO\u001b[0m Step 884/1000 | Loss: 1.9956\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:59 INFO\u001b[0m Step 884/1000 | Loss: 2.0265\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:59 INFO\u001b[0m Step 884/1000 | Loss: 1.9719\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:59 INFO\u001b[0m Step 884/1000 | Loss: 2.1132\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:47:59 INFO\u001b[0m Step 885/1000 | Loss: 2.1035\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:47:59 INFO\u001b[0m Step 885/1000 | Loss: 1.7953\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:47:59 INFO\u001b[0m Step 885/1000 | Loss: 2.1913\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:47:59 INFO\u001b[0m Step 885/1000 | Loss: 2.4282\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:47:59 INFO\u001b[0m Step 885/1000 | Loss: 1.7379\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:47:59 INFO\u001b[0m Step 885/1000 | Loss: 1.9531\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:47:59 INFO\u001b[0m Step 885/1000 | Loss: 2.2915\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:47:59 INFO\u001b[0m Step 885/1000 | Loss: 2.0095\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:00 INFO\u001b[0m Step 886/1000 | Loss: 2.3514\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:00 INFO\u001b[0m Step 886/1000 | Loss: 2.5975\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:00 INFO\u001b[0m Step 886/1000 | Loss: 1.6624\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:00 INFO\u001b[0m Step 886/1000 | Loss: 2.4327\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:00 INFO\u001b[0m Step 886/1000 | Loss: 2.1229\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:00 INFO\u001b[0m Step 886/1000 | Loss: 2.3537\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:00 INFO\u001b[0m Step 886/1000 | Loss: 1.7430\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:00 INFO\u001b[0m Step 886/1000 | Loss: 1.7768\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:00 INFO\u001b[0m Step 887/1000 | Loss: 2.0860\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:00 INFO\u001b[0m Step 887/1000 | Loss: 1.5761\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:00 INFO\u001b[0m Step 887/1000 | Loss: 2.0413\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:00 INFO\u001b[0m Step 887/1000 | Loss: 2.0750\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:00 INFO\u001b[0m Step 887/1000 | Loss: 1.8314\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:00 INFO\u001b[0m Step 887/1000 | Loss: 1.7868\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:00 INFO\u001b[0m Step 887/1000 | Loss: 1.9308\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:00 INFO\u001b[0m Step 887/1000 | Loss: 1.6998\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:01 INFO\u001b[0m Step 888/1000 | Loss: 1.6934\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:01 INFO\u001b[0m Step 888/1000 | Loss: 2.1097\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:01 INFO\u001b[0m Step 888/1000 | Loss: 2.1818\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:01 INFO\u001b[0m Step 888/1000 | Loss: 1.9534\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:01 INFO\u001b[0m Step 888/1000 | Loss: 1.5859\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:01 INFO\u001b[0m Step 888/1000 | Loss: 1.8437\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:01 INFO\u001b[0m Step 888/1000 | Loss: 2.3202\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:01 INFO\u001b[0m Step 888/1000 | Loss: 2.1869\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:01 INFO\u001b[0m Step 889/1000 | Loss: 1.5521\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:01 INFO\u001b[0m Step 889/1000 | Loss: 2.2326\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:01 INFO\u001b[0m Step 889/1000 | Loss: 2.1007\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:01 INFO\u001b[0m Step 889/1000 | Loss: 1.5011\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:01 INFO\u001b[0m Step 889/1000 | Loss: 2.5970\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:01 INFO\u001b[0m Step 889/1000 | Loss: 1.9294\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:01 INFO\u001b[0m Step 889/1000 | Loss: 1.6132\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:01 INFO\u001b[0m Step 889/1000 | Loss: 1.7269\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:01 INFO\u001b[0m Step 890/1000 | Loss: 2.2568\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:01 INFO\u001b[0m Step 890/1000 | Loss: 1.9260\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:01 INFO\u001b[0m Step 890/1000 | Loss: 1.9782\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:01 INFO\u001b[0m Step 890/1000 | Loss: 1.6960\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:01 INFO\u001b[0m Step 890/1000 | Loss: 2.0449\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:01 INFO\u001b[0m Step 890/1000 | Loss: 1.7984\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:01 INFO\u001b[0m Step 890/1000 | Loss: 1.9349\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:01 INFO\u001b[0m Step 890/1000 | Loss: 2.0995\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:02 INFO\u001b[0m Step 891/1000 | Loss: 1.8921\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:02 INFO\u001b[0m Step 891/1000 | Loss: 2.4131\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:02 INFO\u001b[0m Step 891/1000 | Loss: 1.9351\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:02 INFO\u001b[0m Step 891/1000 | Loss: 2.5478\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:02 INFO\u001b[0m Step 891/1000 | Loss: 2.5101\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:02 INFO\u001b[0m Step 891/1000 | Loss: 1.9593\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:02 INFO\u001b[0m Step 891/1000 | Loss: 1.8711\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:02 INFO\u001b[0m Step 891/1000 | Loss: 2.4131\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:02 INFO\u001b[0m Step 892/1000 | Loss: 2.3158\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:02 INFO\u001b[0m Step 892/1000 | Loss: 1.7878\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:02 INFO\u001b[0m Step 892/1000 | Loss: 1.8510\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:02 INFO\u001b[0m Step 892/1000 | Loss: 1.9426\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:02 INFO\u001b[0m Step 892/1000 | Loss: 2.2385\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:02 INFO\u001b[0m Step 892/1000 | Loss: 1.8426\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:02 INFO\u001b[0m Step 892/1000 | Loss: 2.4769\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:02 INFO\u001b[0m Step 892/1000 | Loss: 2.0432\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:03 INFO\u001b[0m Step 893/1000 | Loss: 2.2185\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:03 INFO\u001b[0m Step 893/1000 | Loss: 2.0136\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:03 INFO\u001b[0m Step 893/1000 | Loss: 2.1157\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:03 INFO\u001b[0m Step 893/1000 | Loss: 2.0571\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:03 INFO\u001b[0m Step 893/1000 | Loss: 1.6268\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:03 INFO\u001b[0m Step 893/1000 | Loss: 1.9793\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:03 INFO\u001b[0m Step 893/1000 | Loss: 1.9165\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:03 INFO\u001b[0m Step 893/1000 | Loss: 1.7242\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:03 INFO\u001b[0m Step 894/1000 | Loss: 1.8020\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:03 INFO\u001b[0m Step 894/1000 | Loss: 2.0648\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:03 INFO\u001b[0m Step 894/1000 | Loss: 1.5699\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:03 INFO\u001b[0m Step 894/1000 | Loss: 1.8543\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:03 INFO\u001b[0m Step 894/1000 | Loss: 2.2387\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:03 INFO\u001b[0m Step 894/1000 | Loss: 2.1957\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:03 INFO\u001b[0m Step 894/1000 | Loss: 1.7814\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:03 INFO\u001b[0m Step 894/1000 | Loss: 2.4730\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:03 INFO\u001b[0m Step 895/1000 | Loss: 1.7954\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:03 INFO\u001b[0m Step 895/1000 | Loss: 2.0851\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:03 INFO\u001b[0m Step 895/1000 | Loss: 1.5423\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:03 INFO\u001b[0m Step 895/1000 | Loss: 1.6498\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:03 INFO\u001b[0m Step 895/1000 | Loss: 1.8833\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:03 INFO\u001b[0m Step 895/1000 | Loss: 1.9276\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:03 INFO\u001b[0m Step 895/1000 | Loss: 2.3558\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:03 INFO\u001b[0m Step 895/1000 | Loss: 2.0216\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:04 INFO\u001b[0m Step 896/1000 | Loss: 1.8771\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:04 INFO\u001b[0m Step 896/1000 | Loss: 1.8869\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:04 INFO\u001b[0m Step 896/1000 | Loss: 1.6084\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:04 INFO\u001b[0m Step 896/1000 | Loss: 1.8623\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:04 INFO\u001b[0m Step 896/1000 | Loss: 1.9223\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:04 INFO\u001b[0m Step 896/1000 | Loss: 2.4199\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:04 INFO\u001b[0m Step 896/1000 | Loss: 1.8783\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:04 INFO\u001b[0m Step 896/1000 | Loss: 2.0054\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:04 INFO\u001b[0m Step 897/1000 | Loss: 1.9852\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:04 INFO\u001b[0m Step 897/1000 | Loss: 2.2445\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:04 INFO\u001b[0m Step 897/1000 | Loss: 1.9520\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:04 INFO\u001b[0m Step 897/1000 | Loss: 1.6622\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:04 INFO\u001b[0m Step 897/1000 | Loss: 2.2597\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:04 INFO\u001b[0m Step 897/1000 | Loss: 2.2554\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:04 INFO\u001b[0m Step 897/1000 | Loss: 2.3348\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:04 INFO\u001b[0m Step 897/1000 | Loss: 1.7874\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:05 INFO\u001b[0m Step 898/1000 | Loss: 2.1678\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:05 INFO\u001b[0m Step 898/1000 | Loss: 1.6391\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:05 INFO\u001b[0m Step 898/1000 | Loss: 1.9741\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:05 INFO\u001b[0m Step 898/1000 | Loss: 2.0923\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:05 INFO\u001b[0m Step 898/1000 | Loss: 1.7655\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:05 INFO\u001b[0m Step 898/1000 | Loss: 2.0660\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:05 INFO\u001b[0m Step 898/1000 | Loss: 1.8401\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:05 INFO\u001b[0m Step 898/1000 | Loss: 1.9174\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:05 INFO\u001b[0m Step 899/1000 | Loss: 2.7161\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:05 INFO\u001b[0m Step 899/1000 | Loss: 1.8451\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:05 INFO\u001b[0m Step 899/1000 | Loss: 2.2831\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:05 INFO\u001b[0m Step 899/1000 | Loss: 2.1871\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:05 INFO\u001b[0m Step 899/1000 | Loss: 2.1697\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:05 INFO\u001b[0m Step 899/1000 | Loss: 1.9474\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:05 INFO\u001b[0m Step 899/1000 | Loss: 2.2668\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:05 INFO\u001b[0m Step 899/1000 | Loss: 1.9648\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:05 INFO\u001b[0m Step 900/1000 | Loss: 1.6731\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:05 INFO\u001b[0m Step 900/1000 | Loss: 1.8799\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:05 INFO\u001b[0m Step 900/1000 | Loss: 1.9857\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:05 INFO\u001b[0m Step 900/1000 | Loss: 2.3886\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:05 INFO\u001b[0m Step 900/1000 | Loss: 1.9775\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:05 INFO\u001b[0m Step 900/1000 | Loss: 2.3395\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:05 INFO\u001b[0m Step 900/1000 | Loss: 2.1517\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:05 INFO\u001b[0m Step 900/1000 | Loss: 2.0897\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:06 INFO\u001b[0m Step 901/1000 | Loss: 1.6067\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:06 INFO\u001b[0m Step 901/1000 | Loss: 2.3632\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:06 INFO\u001b[0m Step 901/1000 | Loss: 1.4825\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:06 INFO\u001b[0m Step 901/1000 | Loss: 1.8933\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:06 INFO\u001b[0m Step 901/1000 | Loss: 2.0879\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:06 INFO\u001b[0m Step 901/1000 | Loss: 2.0549\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:06 INFO\u001b[0m Step 901/1000 | Loss: 1.8247\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:06 INFO\u001b[0m Step 901/1000 | Loss: 2.2713\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:06 INFO\u001b[0m Step 902/1000 | Loss: 2.0626\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:06 INFO\u001b[0m Step 902/1000 | Loss: 1.9242\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:06 INFO\u001b[0m Step 902/1000 | Loss: 2.2785\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:06 INFO\u001b[0m Step 902/1000 | Loss: 1.9631\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:06 INFO\u001b[0m Step 902/1000 | Loss: 2.3235\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:06 INFO\u001b[0m Step 902/1000 | Loss: 2.1208\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:06 INFO\u001b[0m Step 902/1000 | Loss: 1.8634\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:06 INFO\u001b[0m Step 902/1000 | Loss: 1.7338\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:07 INFO\u001b[0m Step 903/1000 | Loss: 1.6031\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:07 INFO\u001b[0m Step 903/1000 | Loss: 2.3028\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:07 INFO\u001b[0m Step 903/1000 | Loss: 2.4372\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:07 INFO\u001b[0m Step 903/1000 | Loss: 1.7177\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:07 INFO\u001b[0m Step 903/1000 | Loss: 1.9517\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:07 INFO\u001b[0m Step 903/1000 | Loss: 1.9493\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:07 INFO\u001b[0m Step 903/1000 | Loss: 1.9971\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:07 INFO\u001b[0m Step 903/1000 | Loss: 2.2298\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:07 INFO\u001b[0m Step 904/1000 | Loss: 3.4895\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:07 INFO\u001b[0m Step 904/1000 | Loss: 2.1815\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:07 INFO\u001b[0m Step 904/1000 | Loss: 2.3184\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:07 INFO\u001b[0m Step 904/1000 | Loss: 1.9734\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:07 INFO\u001b[0m Step 904/1000 | Loss: 1.8215\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:07 INFO\u001b[0m Step 904/1000 | Loss: 2.1295\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:07 INFO\u001b[0m Step 904/1000 | Loss: 2.1827\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:07 INFO\u001b[0m Step 904/1000 | Loss: 2.3883\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:07 INFO\u001b[0m Step 905/1000 | Loss: 1.7468\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:07 INFO\u001b[0m Step 905/1000 | Loss: 1.8005\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:07 INFO\u001b[0m Step 905/1000 | Loss: 1.7725\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:07 INFO\u001b[0m Step 905/1000 | Loss: 2.2866\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:07 INFO\u001b[0m Step 905/1000 | Loss: 1.8037\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:07 INFO\u001b[0m Step 905/1000 | Loss: 1.5475\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:07 INFO\u001b[0m Step 905/1000 | Loss: 2.3553\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:07 INFO\u001b[0m Step 905/1000 | Loss: 1.7501\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:08 INFO\u001b[0m Step 906/1000 | Loss: 2.3761\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:08 INFO\u001b[0m Step 906/1000 | Loss: 2.1228\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:08 INFO\u001b[0m Step 906/1000 | Loss: 2.5368\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:08 INFO\u001b[0m Step 906/1000 | Loss: 2.2185\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:08 INFO\u001b[0m Step 906/1000 | Loss: 1.9538\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:08 INFO\u001b[0m Step 906/1000 | Loss: 2.0844\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:08 INFO\u001b[0m Step 906/1000 | Loss: 1.8443\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:08 INFO\u001b[0m Step 906/1000 | Loss: 1.7345\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:08 INFO\u001b[0m Step 907/1000 | Loss: 1.7443\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:08 INFO\u001b[0m Step 907/1000 | Loss: 2.2802\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:08 INFO\u001b[0m Step 907/1000 | Loss: 2.3995\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:08 INFO\u001b[0m Step 907/1000 | Loss: 2.0108\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:08 INFO\u001b[0m Step 907/1000 | Loss: 2.0156\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:08 INFO\u001b[0m Step 907/1000 | Loss: 1.7246\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:08 INFO\u001b[0m Step 907/1000 | Loss: 1.8026\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:08 INFO\u001b[0m Step 907/1000 | Loss: 1.6395\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:09 INFO\u001b[0m Step 908/1000 | Loss: 1.9039\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:09 INFO\u001b[0m Step 908/1000 | Loss: 2.1013\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:09 INFO\u001b[0m Step 908/1000 | Loss: 1.7201\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:09 INFO\u001b[0m Step 908/1000 | Loss: 2.1438\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:09 INFO\u001b[0m Step 908/1000 | Loss: 2.2533\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:09 INFO\u001b[0m Step 908/1000 | Loss: 2.0244\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:09 INFO\u001b[0m Step 908/1000 | Loss: 1.8509\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:09 INFO\u001b[0m Step 908/1000 | Loss: 2.0072\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:09 INFO\u001b[0m Step 909/1000 | Loss: 1.6853\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:09 INFO\u001b[0m Step 909/1000 | Loss: 2.2074\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:09 INFO\u001b[0m Step 909/1000 | Loss: 2.0573\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:09 INFO\u001b[0m Step 909/1000 | Loss: 2.0530\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:09 INFO\u001b[0m Step 909/1000 | Loss: 1.9497\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:09 INFO\u001b[0m Step 909/1000 | Loss: 1.6157\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:09 INFO\u001b[0m Step 909/1000 | Loss: 2.0775\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:09 INFO\u001b[0m Step 909/1000 | Loss: 2.0163\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:09 INFO\u001b[0m Step 910/1000 | Loss: 2.1234\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:09 INFO\u001b[0m Step 910/1000 | Loss: 1.7258\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:09 INFO\u001b[0m Step 910/1000 | Loss: 2.3012\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:09 INFO\u001b[0m Step 910/1000 | Loss: 2.1012\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:09 INFO\u001b[0m Step 910/1000 | Loss: 1.9944\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:09 INFO\u001b[0m Step 910/1000 | Loss: 2.0405\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:09 INFO\u001b[0m Step 910/1000 | Loss: 1.7007\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:09 INFO\u001b[0m Step 910/1000 | Loss: 1.9902\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:10 INFO\u001b[0m Step 911/1000 | Loss: 2.2586\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:10 INFO\u001b[0m Step 911/1000 | Loss: 2.0294\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:10 INFO\u001b[0m Step 911/1000 | Loss: 2.2463\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:10 INFO\u001b[0m Step 911/1000 | Loss: 2.0948\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:10 INFO\u001b[0m Step 911/1000 | Loss: 2.0650\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:10 INFO\u001b[0m Step 911/1000 | Loss: 2.0705\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:10 INFO\u001b[0m Step 911/1000 | Loss: 2.1749\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:10 INFO\u001b[0m Step 911/1000 | Loss: 1.9572\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:10 INFO\u001b[0m Step 912/1000 | Loss: 2.3809\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:10 INFO\u001b[0m Step 912/1000 | Loss: 2.0163\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:10 INFO\u001b[0m Step 912/1000 | Loss: 1.9276\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:10 INFO\u001b[0m Step 912/1000 | Loss: 1.6687\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:10 INFO\u001b[0m Step 912/1000 | Loss: 2.4513\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:10 INFO\u001b[0m Step 912/1000 | Loss: 2.3696\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:10 INFO\u001b[0m Step 912/1000 | Loss: 1.7501\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:10 INFO\u001b[0m Step 912/1000 | Loss: 2.3624\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:11 INFO\u001b[0m Step 913/1000 | Loss: 1.7126\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:11 INFO\u001b[0m Step 913/1000 | Loss: 1.8229\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:11 INFO\u001b[0m Step 913/1000 | Loss: 1.5375\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:11 INFO\u001b[0m Step 913/1000 | Loss: 2.1288\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:11 INFO\u001b[0m Step 913/1000 | Loss: 2.4319\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:11 INFO\u001b[0m Step 913/1000 | Loss: 2.0067\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:11 INFO\u001b[0m Step 913/1000 | Loss: 1.9612\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:11 INFO\u001b[0m Step 913/1000 | Loss: 2.1296\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:11 INFO\u001b[0m Step 914/1000 | Loss: 2.1892\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:11 INFO\u001b[0m Step 914/1000 | Loss: 1.8434\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:11 INFO\u001b[0m Step 914/1000 | Loss: 1.9737\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:11 INFO\u001b[0m Step 914/1000 | Loss: 1.7824\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:11 INFO\u001b[0m Step 914/1000 | Loss: 1.7811\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:11 INFO\u001b[0m Step 914/1000 | Loss: 2.1323\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:11 INFO\u001b[0m Step 914/1000 | Loss: 2.1595\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:11 INFO\u001b[0m Step 914/1000 | Loss: 2.1717\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:12 INFO\u001b[0m Step 915/1000 | Loss: 1.5509\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:12 INFO\u001b[0m Step 915/1000 | Loss: 1.9466\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:12 INFO\u001b[0m Step 915/1000 | Loss: 2.1389\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:12 INFO\u001b[0m Step 915/1000 | Loss: 2.0687\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:12 INFO\u001b[0m Step 915/1000 | Loss: 1.8116\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:12 INFO\u001b[0m Step 915/1000 | Loss: 2.1377\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:12 INFO\u001b[0m Step 915/1000 | Loss: 1.8921\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:12 INFO\u001b[0m Step 915/1000 | Loss: 1.9805\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:12 INFO\u001b[0m Step 916/1000 | Loss: 1.8021\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:12 INFO\u001b[0m Step 916/1000 | Loss: 2.3030\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:12 INFO\u001b[0m Step 916/1000 | Loss: 1.7836\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:12 INFO\u001b[0m Step 916/1000 | Loss: 1.7074\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:12 INFO\u001b[0m Step 916/1000 | Loss: 1.8697\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:12 INFO\u001b[0m Step 916/1000 | Loss: 1.8851\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:12 INFO\u001b[0m Step 916/1000 | Loss: 1.8435\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:12 INFO\u001b[0m Step 916/1000 | Loss: 2.1490\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:12 INFO\u001b[0m Step 917/1000 | Loss: 1.9839\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:12 INFO\u001b[0m Step 917/1000 | Loss: 1.9343\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:12 INFO\u001b[0m Step 917/1000 | Loss: 2.2627\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:12 INFO\u001b[0m Step 917/1000 | Loss: 2.0192\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:12 INFO\u001b[0m Step 917/1000 | Loss: 1.5647\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:12 INFO\u001b[0m Step 917/1000 | Loss: 1.7342\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:12 INFO\u001b[0m Step 917/1000 | Loss: 2.7191\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:12 INFO\u001b[0m Step 917/1000 | Loss: 2.0128\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:13 INFO\u001b[0m Step 918/1000 | Loss: 2.1618\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:13 INFO\u001b[0m Step 918/1000 | Loss: 1.9225\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:13 INFO\u001b[0m Step 918/1000 | Loss: 2.3960\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:13 INFO\u001b[0m Step 918/1000 | Loss: 2.0444\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:13 INFO\u001b[0m Step 918/1000 | Loss: 1.5422\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:13 INFO\u001b[0m Step 918/1000 | Loss: 1.5666\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:13 INFO\u001b[0m Step 918/1000 | Loss: 1.8325\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:13 INFO\u001b[0m Step 918/1000 | Loss: 1.7383\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:13 INFO\u001b[0m Step 919/1000 | Loss: 1.6147\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:13 INFO\u001b[0m Step 919/1000 | Loss: 1.5797\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:13 INFO\u001b[0m Step 919/1000 | Loss: 1.8155\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:13 INFO\u001b[0m Step 919/1000 | Loss: 1.9198\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:13 INFO\u001b[0m Step 919/1000 | Loss: 2.1753\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:13 INFO\u001b[0m Step 919/1000 | Loss: 1.9331\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:13 INFO\u001b[0m Step 919/1000 | Loss: 2.2438\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:13 INFO\u001b[0m Step 919/1000 | Loss: 1.8097\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:14 INFO\u001b[0m Step 920/1000 | Loss: 1.8624\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:14 INFO\u001b[0m Step 920/1000 | Loss: 2.4885\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:14 INFO\u001b[0m Step 920/1000 | Loss: 1.8112\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:14 INFO\u001b[0m Step 920/1000 | Loss: 2.0114\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:14 INFO\u001b[0m Step 920/1000 | Loss: 1.6645\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:14 INFO\u001b[0m Step 920/1000 | Loss: 1.8253\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:14 INFO\u001b[0m Step 920/1000 | Loss: 1.9668\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:14 INFO\u001b[0m Step 920/1000 | Loss: 1.5349\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:14 INFO\u001b[0m Step 921/1000 | Loss: 1.9617\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:14 INFO\u001b[0m Step 921/1000 | Loss: 2.0353\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:14 INFO\u001b[0m Step 921/1000 | Loss: 1.7739\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:14 INFO\u001b[0m Step 921/1000 | Loss: 1.9894\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:14 INFO\u001b[0m Step 921/1000 | Loss: 1.9947\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:14 INFO\u001b[0m Step 921/1000 | Loss: 2.3487\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:14 INFO\u001b[0m Step 921/1000 | Loss: 2.1025\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:14 INFO\u001b[0m Step 921/1000 | Loss: 2.0783\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:14 INFO\u001b[0m Step 922/1000 | Loss: 2.2036\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:14 INFO\u001b[0m Step 922/1000 | Loss: 1.9208\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:14 INFO\u001b[0m Step 922/1000 | Loss: 1.9937\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:14 INFO\u001b[0m Step 922/1000 | Loss: 1.7311\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:14 INFO\u001b[0m Step 922/1000 | Loss: 1.7225\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:14 INFO\u001b[0m Step 922/1000 | Loss: 2.0802\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:14 INFO\u001b[0m Step 922/1000 | Loss: 1.9899\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:14 INFO\u001b[0m Step 922/1000 | Loss: 1.8084\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:15 INFO\u001b[0m Step 923/1000 | Loss: 1.4794\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:15 INFO\u001b[0m Step 923/1000 | Loss: 1.6810\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:15 INFO\u001b[0m Step 923/1000 | Loss: 2.5785\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:15 INFO\u001b[0m Step 923/1000 | Loss: 2.0545\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:15 INFO\u001b[0m Step 923/1000 | Loss: 2.0895\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:15 INFO\u001b[0m Step 923/1000 | Loss: 1.8432\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:15 INFO\u001b[0m Step 923/1000 | Loss: 1.7618\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:15 INFO\u001b[0m Step 923/1000 | Loss: 2.2820\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:15 INFO\u001b[0m Step 924/1000 | Loss: 1.9200\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:15 INFO\u001b[0m Step 924/1000 | Loss: 1.6595\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:15 INFO\u001b[0m Step 924/1000 | Loss: 2.2521\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:15 INFO\u001b[0m Step 924/1000 | Loss: 1.5738\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:15 INFO\u001b[0m Step 924/1000 | Loss: 1.7676\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:15 INFO\u001b[0m Step 924/1000 | Loss: 2.2333\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:15 INFO\u001b[0m Step 924/1000 | Loss: 1.8087\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:15 INFO\u001b[0m Step 924/1000 | Loss: 2.4602\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:16 INFO\u001b[0m Step 925/1000 | Loss: 2.7600\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:16 INFO\u001b[0m Step 925/1000 | Loss: 2.2586\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:16 INFO\u001b[0m Step 925/1000 | Loss: 1.6420\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:16 INFO\u001b[0m Step 925/1000 | Loss: 2.0131\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:16 INFO\u001b[0m Step 925/1000 | Loss: 2.1455\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:16 INFO\u001b[0m Step 925/1000 | Loss: 2.0562\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:16 INFO\u001b[0m Step 925/1000 | Loss: 1.8090\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:16 INFO\u001b[0m Step 925/1000 | Loss: 1.7587\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:16 INFO\u001b[0m Step 926/1000 | Loss: 1.6265\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:16 INFO\u001b[0m Step 926/1000 | Loss: 1.8540\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:16 INFO\u001b[0m Step 926/1000 | Loss: 1.9041\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:16 INFO\u001b[0m Step 926/1000 | Loss: 1.9245\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:16 INFO\u001b[0m Step 926/1000 | Loss: 2.0165\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:16 INFO\u001b[0m Step 926/1000 | Loss: 2.2915\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:16 INFO\u001b[0m Step 926/1000 | Loss: 1.6843\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:16 INFO\u001b[0m Step 926/1000 | Loss: 1.6541\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:16 INFO\u001b[0m Step 927/1000 | Loss: 1.8161\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:16 INFO\u001b[0m Step 927/1000 | Loss: 2.0107\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:16 INFO\u001b[0m Step 927/1000 | Loss: 1.8586\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:16 INFO\u001b[0m Step 927/1000 | Loss: 1.8153\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:16 INFO\u001b[0m Step 927/1000 | Loss: 1.9467\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:16 INFO\u001b[0m Step 927/1000 | Loss: 1.9001\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:16 INFO\u001b[0m Step 927/1000 | Loss: 2.1793\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:16 INFO\u001b[0m Step 927/1000 | Loss: 2.5256\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:17 INFO\u001b[0m Step 928/1000 | Loss: 2.0103\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:17 INFO\u001b[0m Step 928/1000 | Loss: 2.0138\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:17 INFO\u001b[0m Step 928/1000 | Loss: 1.9471\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:17 INFO\u001b[0m Step 928/1000 | Loss: 2.2111\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:17 INFO\u001b[0m Step 928/1000 | Loss: 1.8219\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:17 INFO\u001b[0m Step 928/1000 | Loss: 1.9342\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:17 INFO\u001b[0m Step 928/1000 | Loss: 2.0842\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:17 INFO\u001b[0m Step 928/1000 | Loss: 2.0755\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:17 INFO\u001b[0m Step 929/1000 | Loss: 1.9222\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:17 INFO\u001b[0m Step 929/1000 | Loss: 1.6358\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:17 INFO\u001b[0m Step 929/1000 | Loss: 2.1373\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:17 INFO\u001b[0m Step 929/1000 | Loss: 2.4273\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:17 INFO\u001b[0m Step 929/1000 | Loss: 1.9930\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:17 INFO\u001b[0m Step 929/1000 | Loss: 1.7913\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:17 INFO\u001b[0m Step 929/1000 | Loss: 1.8736\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:17 INFO\u001b[0m Step 929/1000 | Loss: 1.9577\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:18 INFO\u001b[0m Step 930/1000 | Loss: 2.2230\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:18 INFO\u001b[0m Step 930/1000 | Loss: 2.0318\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:18 INFO\u001b[0m Step 930/1000 | Loss: 1.6880\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:18 INFO\u001b[0m Step 930/1000 | Loss: 1.8311\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:18 INFO\u001b[0m Step 930/1000 | Loss: 2.0970\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:18 INFO\u001b[0m Step 930/1000 | Loss: 2.0227\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:18 INFO\u001b[0m Step 930/1000 | Loss: 2.3487\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:18 INFO\u001b[0m Step 930/1000 | Loss: 2.1948\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:18 INFO\u001b[0m Step 931/1000 | Loss: 2.1433\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:18 INFO\u001b[0m Step 931/1000 | Loss: 1.7823\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:18 INFO\u001b[0m Step 931/1000 | Loss: 2.0119\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:18 INFO\u001b[0m Step 931/1000 | Loss: 1.9846\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:18 INFO\u001b[0m Step 931/1000 | Loss: 1.9028\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:18 INFO\u001b[0m Step 931/1000 | Loss: 1.8644\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:18 INFO\u001b[0m Step 931/1000 | Loss: 2.1109\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:18 INFO\u001b[0m Step 931/1000 | Loss: 1.7287\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:18 INFO\u001b[0m Step 932/1000 | Loss: 2.1709\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:18 INFO\u001b[0m Step 932/1000 | Loss: 1.3648\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:18 INFO\u001b[0m Step 932/1000 | Loss: 2.1902\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:18 INFO\u001b[0m Step 932/1000 | Loss: 1.8477\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:18 INFO\u001b[0m Step 932/1000 | Loss: 1.8579\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:18 INFO\u001b[0m Step 932/1000 | Loss: 1.9479\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:18 INFO\u001b[0m Step 932/1000 | Loss: 1.9530\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:18 INFO\u001b[0m Step 932/1000 | Loss: 1.7297\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:19 INFO\u001b[0m Step 933/1000 | Loss: 2.3384\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:19 INFO\u001b[0m Step 933/1000 | Loss: 1.6409\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:19 INFO\u001b[0m Step 933/1000 | Loss: 2.2168\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:19 INFO\u001b[0m Step 933/1000 | Loss: 1.9325\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:19 INFO\u001b[0m Step 933/1000 | Loss: 2.3701\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:19 INFO\u001b[0m Step 933/1000 | Loss: 1.8869\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:19 INFO\u001b[0m Step 933/1000 | Loss: 1.7093\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:19 INFO\u001b[0m Step 933/1000 | Loss: 2.0878\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:19 INFO\u001b[0m Step 934/1000 | Loss: 1.7448\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:19 INFO\u001b[0m Step 934/1000 | Loss: 2.1238\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:19 INFO\u001b[0m Step 934/1000 | Loss: 2.1565\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:19 INFO\u001b[0m Step 934/1000 | Loss: 1.9384\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:19 INFO\u001b[0m Step 934/1000 | Loss: 1.9025\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:19 INFO\u001b[0m Step 934/1000 | Loss: 2.0338\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:19 INFO\u001b[0m Step 934/1000 | Loss: 2.0167\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:19 INFO\u001b[0m Step 934/1000 | Loss: 1.8565\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:20 INFO\u001b[0m Step 935/1000 | Loss: 2.0795\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:20 INFO\u001b[0m Step 935/1000 | Loss: 1.8280\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:20 INFO\u001b[0m Step 935/1000 | Loss: 1.7453\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:20 INFO\u001b[0m Step 935/1000 | Loss: 1.5794\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:20 INFO\u001b[0m Step 935/1000 | Loss: 1.7475\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:20 INFO\u001b[0m Step 935/1000 | Loss: 1.8343\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:20 INFO\u001b[0m Step 935/1000 | Loss: 2.2339\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:20 INFO\u001b[0m Step 935/1000 | Loss: 1.7570\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:20 INFO\u001b[0m Step 936/1000 | Loss: 2.5487\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:20 INFO\u001b[0m Step 936/1000 | Loss: 1.8344\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:20 INFO\u001b[0m Step 936/1000 | Loss: 2.0079\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:20 INFO\u001b[0m Step 936/1000 | Loss: 1.9330\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:20 INFO\u001b[0m Step 936/1000 | Loss: 1.8107\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:20 INFO\u001b[0m Step 936/1000 | Loss: 1.7839\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:20 INFO\u001b[0m Step 936/1000 | Loss: 1.8516\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:20 INFO\u001b[0m Step 936/1000 | Loss: 2.1594\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:20 INFO\u001b[0m Step 937/1000 | Loss: 1.7071\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:20 INFO\u001b[0m Step 937/1000 | Loss: 2.0198\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:20 INFO\u001b[0m Step 937/1000 | Loss: 1.6618\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:20 INFO\u001b[0m Step 937/1000 | Loss: 2.0050\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:20 INFO\u001b[0m Step 937/1000 | Loss: 2.1017\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:20 INFO\u001b[0m Step 937/1000 | Loss: 1.8287\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:20 INFO\u001b[0m Step 937/1000 | Loss: 1.8748\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:20 INFO\u001b[0m Step 937/1000 | Loss: 2.0704\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:21 INFO\u001b[0m Step 938/1000 | Loss: 1.9688\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:21 INFO\u001b[0m Step 938/1000 | Loss: 1.5926\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:21 INFO\u001b[0m Step 938/1000 | Loss: 2.0823\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:21 INFO\u001b[0m Step 938/1000 | Loss: 2.3636\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:21 INFO\u001b[0m Step 938/1000 | Loss: 1.7935\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:21 INFO\u001b[0m Step 938/1000 | Loss: 1.5711\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:21 INFO\u001b[0m Step 938/1000 | Loss: 2.1553\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:21 INFO\u001b[0m Step 938/1000 | Loss: 1.7288\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:21 INFO\u001b[0m Step 939/1000 | Loss: 2.1665\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:21 INFO\u001b[0m Step 939/1000 | Loss: 1.8787\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:21 INFO\u001b[0m Step 939/1000 | Loss: 1.7152\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:21 INFO\u001b[0m Step 939/1000 | Loss: 1.8949\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:21 INFO\u001b[0m Step 939/1000 | Loss: 1.7588\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:21 INFO\u001b[0m Step 939/1000 | Loss: 1.7945\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:21 INFO\u001b[0m Step 939/1000 | Loss: 2.0643\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:21 INFO\u001b[0m Step 939/1000 | Loss: 1.6476\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:22 INFO\u001b[0m Step 940/1000 | Loss: 1.8569\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:22 INFO\u001b[0m Step 940/1000 | Loss: 1.7743\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:22 INFO\u001b[0m Step 940/1000 | Loss: 1.6825\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:22 INFO\u001b[0m Step 940/1000 | Loss: 1.6166\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:22 INFO\u001b[0m Step 940/1000 | Loss: 1.8396\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:22 INFO\u001b[0m Step 940/1000 | Loss: 1.9389\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:22 INFO\u001b[0m Step 940/1000 | Loss: 1.9852\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:22 INFO\u001b[0m Step 940/1000 | Loss: 1.9509\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:22 INFO\u001b[0m Step 941/1000 | Loss: 1.7920\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:22 INFO\u001b[0m Step 941/1000 | Loss: 1.6444\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:22 INFO\u001b[0m Step 941/1000 | Loss: 1.7461\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:22 INFO\u001b[0m Step 941/1000 | Loss: 1.9172\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:22 INFO\u001b[0m Step 941/1000 | Loss: 1.5905\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:22 INFO\u001b[0m Step 941/1000 | Loss: 2.4442\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:22 INFO\u001b[0m Step 941/1000 | Loss: 1.6201\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:22 INFO\u001b[0m Step 941/1000 | Loss: 2.3548\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:22 INFO\u001b[0m Step 942/1000 | Loss: 2.2187\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:22 INFO\u001b[0m Step 942/1000 | Loss: 2.3023\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:22 INFO\u001b[0m Step 942/1000 | Loss: 1.7354\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:22 INFO\u001b[0m Step 942/1000 | Loss: 1.7854\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:22 INFO\u001b[0m Step 942/1000 | Loss: 1.9895\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:22 INFO\u001b[0m Step 942/1000 | Loss: 1.7176\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:22 INFO\u001b[0m Step 942/1000 | Loss: 2.1727\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:22 INFO\u001b[0m Step 942/1000 | Loss: 2.1145\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:23 INFO\u001b[0m Step 943/1000 | Loss: 2.2449\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:23 INFO\u001b[0m Step 943/1000 | Loss: 1.7749\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:23 INFO\u001b[0m Step 943/1000 | Loss: 1.7064\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:23 INFO\u001b[0m Step 943/1000 | Loss: 1.9120\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:23 INFO\u001b[0m Step 943/1000 | Loss: 1.8197\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:23 INFO\u001b[0m Step 943/1000 | Loss: 2.0937\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:23 INFO\u001b[0m Step 943/1000 | Loss: 1.7136\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:23 INFO\u001b[0m Step 943/1000 | Loss: 1.7548\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:23 INFO\u001b[0m Step 944/1000 | Loss: 1.6795\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:23 INFO\u001b[0m Step 944/1000 | Loss: 1.9612\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:23 INFO\u001b[0m Step 944/1000 | Loss: 1.8989\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:23 INFO\u001b[0m Step 944/1000 | Loss: 2.2581\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:23 INFO\u001b[0m Step 944/1000 | Loss: 1.9086\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:23 INFO\u001b[0m Step 944/1000 | Loss: 1.6977\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:23 INFO\u001b[0m Step 944/1000 | Loss: 1.6543\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:23 INFO\u001b[0m Step 944/1000 | Loss: 2.1067\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:24 INFO\u001b[0m Step 945/1000 | Loss: 2.1093\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:24 INFO\u001b[0m Step 945/1000 | Loss: 2.1252\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:24 INFO\u001b[0m Step 945/1000 | Loss: 1.8998\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:24 INFO\u001b[0m Step 945/1000 | Loss: 2.2029\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:24 INFO\u001b[0m Step 945/1000 | Loss: 1.6699\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:24 INFO\u001b[0m Step 945/1000 | Loss: 1.7557\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:24 INFO\u001b[0m Step 945/1000 | Loss: 1.9122\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:24 INFO\u001b[0m Step 945/1000 | Loss: 1.7926\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:24 INFO\u001b[0m Step 946/1000 | Loss: 1.9582\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:24 INFO\u001b[0m Step 946/1000 | Loss: 1.6205\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:24 INFO\u001b[0m Step 946/1000 | Loss: 2.1678\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:24 INFO\u001b[0m Step 946/1000 | Loss: 2.0569\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:24 INFO\u001b[0m Step 946/1000 | Loss: 1.7454\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:24 INFO\u001b[0m Step 946/1000 | Loss: 1.5967\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:24 INFO\u001b[0m Step 946/1000 | Loss: 1.5746\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:24 INFO\u001b[0m Step 946/1000 | Loss: 2.1719\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:24 INFO\u001b[0m Step 947/1000 | Loss: 1.4188\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:24 INFO\u001b[0m Step 947/1000 | Loss: 1.7562\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:24 INFO\u001b[0m Step 947/1000 | Loss: 1.7223\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:24 INFO\u001b[0m Step 947/1000 | Loss: 1.8565\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:24 INFO\u001b[0m Step 947/1000 | Loss: 1.9136\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:24 INFO\u001b[0m Step 947/1000 | Loss: 2.1105\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:24 INFO\u001b[0m Step 947/1000 | Loss: 2.1597\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:24 INFO\u001b[0m Step 947/1000 | Loss: 1.6493\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:25 INFO\u001b[0m Step 948/1000 | Loss: 2.0519\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:25 INFO\u001b[0m Step 948/1000 | Loss: 1.6475\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:25 INFO\u001b[0m Step 948/1000 | Loss: 2.0298\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:25 INFO\u001b[0m Step 948/1000 | Loss: 2.0711\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:25 INFO\u001b[0m Step 948/1000 | Loss: 1.9755\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:25 INFO\u001b[0m Step 948/1000 | Loss: 1.9339\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:25 INFO\u001b[0m Step 948/1000 | Loss: 1.6581\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:25 INFO\u001b[0m Step 948/1000 | Loss: 2.2569\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:25 INFO\u001b[0m Step 949/1000 | Loss: 1.7792\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:25 INFO\u001b[0m Step 949/1000 | Loss: 1.9351\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:25 INFO\u001b[0m Step 949/1000 | Loss: 2.2423\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:25 INFO\u001b[0m Step 949/1000 | Loss: 1.8056\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:25 INFO\u001b[0m Step 949/1000 | Loss: 1.7732\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:25 INFO\u001b[0m Step 949/1000 | Loss: 2.0227\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:25 INFO\u001b[0m Step 949/1000 | Loss: 2.1693\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:25 INFO\u001b[0m Step 949/1000 | Loss: 1.8263\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:26 INFO\u001b[0m Step 950/1000 | Loss: 1.6979\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:26 INFO\u001b[0m Step 950/1000 | Loss: 1.9797\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:26 INFO\u001b[0m Step 950/1000 | Loss: 2.2018\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:26 INFO\u001b[0m Step 950/1000 | Loss: 2.1637\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:26 INFO\u001b[0m Step 950/1000 | Loss: 1.9510\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:26 INFO\u001b[0m Step 950/1000 | Loss: 1.8377\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:26 INFO\u001b[0m Step 950/1000 | Loss: 1.7482\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:26 INFO\u001b[0m Step 950/1000 | Loss: 2.2997\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:26 INFO\u001b[0m Step 951/1000 | Loss: 1.6549\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:26 INFO\u001b[0m Step 951/1000 | Loss: 1.6353\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:26 INFO\u001b[0m Step 951/1000 | Loss: 1.9132\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:26 INFO\u001b[0m Step 951/1000 | Loss: 2.5151\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:26 INFO\u001b[0m Step 951/1000 | Loss: 1.5912\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:26 INFO\u001b[0m Step 951/1000 | Loss: 2.0401\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:26 INFO\u001b[0m Step 951/1000 | Loss: 2.1894\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:26 INFO\u001b[0m Step 951/1000 | Loss: 1.9227\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:26 INFO\u001b[0m Step 952/1000 | Loss: 1.5580\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:26 INFO\u001b[0m Step 952/1000 | Loss: 1.3092\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:26 INFO\u001b[0m Step 952/1000 | Loss: 1.8480\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:26 INFO\u001b[0m Step 952/1000 | Loss: 2.0184\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:26 INFO\u001b[0m Step 952/1000 | Loss: 1.8903\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:26 INFO\u001b[0m Step 952/1000 | Loss: 1.5534\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:26 INFO\u001b[0m Step 952/1000 | Loss: 1.8692\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:26 INFO\u001b[0m Step 952/1000 | Loss: 1.7993\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:27 INFO\u001b[0m Step 953/1000 | Loss: 1.9812\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:27 INFO\u001b[0m Step 953/1000 | Loss: 1.6848\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:27 INFO\u001b[0m Step 953/1000 | Loss: 1.9659\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:27 INFO\u001b[0m Step 953/1000 | Loss: 1.6743\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:27 INFO\u001b[0m Step 953/1000 | Loss: 1.8283\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:27 INFO\u001b[0m Step 953/1000 | Loss: 2.4468\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:27 INFO\u001b[0m Step 953/1000 | Loss: 2.1073\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:27 INFO\u001b[0m Step 953/1000 | Loss: 2.3210\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:27 INFO\u001b[0m Step 954/1000 | Loss: 1.9194\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:27 INFO\u001b[0m Step 954/1000 | Loss: 1.8765\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:27 INFO\u001b[0m Step 954/1000 | Loss: 1.8066\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:27 INFO\u001b[0m Step 954/1000 | Loss: 1.8471\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:27 INFO\u001b[0m Step 954/1000 | Loss: 1.5578\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:27 INFO\u001b[0m Step 954/1000 | Loss: 1.8858\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:27 INFO\u001b[0m Step 954/1000 | Loss: 2.3170\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:27 INFO\u001b[0m Step 954/1000 | Loss: 1.9260\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:28 INFO\u001b[0m Step 955/1000 | Loss: 2.0027\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:28 INFO\u001b[0m Step 955/1000 | Loss: 1.9002\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:28 INFO\u001b[0m Step 955/1000 | Loss: 2.1131\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:28 INFO\u001b[0m Step 955/1000 | Loss: 1.9206\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:28 INFO\u001b[0m Step 955/1000 | Loss: 1.7341\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:28 INFO\u001b[0m Step 955/1000 | Loss: 1.5986\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:28 INFO\u001b[0m Step 955/1000 | Loss: 2.0424\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:28 INFO\u001b[0m Step 955/1000 | Loss: 1.8627\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:28 INFO\u001b[0m Step 956/1000 | Loss: 1.7441\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:28 INFO\u001b[0m Step 956/1000 | Loss: 2.0128\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:28 INFO\u001b[0m Step 956/1000 | Loss: 1.9430\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:28 INFO\u001b[0m Step 956/1000 | Loss: 2.0346\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:28 INFO\u001b[0m Step 956/1000 | Loss: 1.8538\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:28 INFO\u001b[0m Step 956/1000 | Loss: 1.9168\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:28 INFO\u001b[0m Step 956/1000 | Loss: 1.7921\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:28 INFO\u001b[0m Step 956/1000 | Loss: 2.0061\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:29 INFO\u001b[0m Step 957/1000 | Loss: 1.6603\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:29 INFO\u001b[0m Step 957/1000 | Loss: 1.7171\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:29 INFO\u001b[0m Step 957/1000 | Loss: 2.0361\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:29 INFO\u001b[0m Step 957/1000 | Loss: 2.3107\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:29 INFO\u001b[0m Step 957/1000 | Loss: 1.8829\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:29 INFO\u001b[0m Step 957/1000 | Loss: 2.0363\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:29 INFO\u001b[0m Step 957/1000 | Loss: 1.7638\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:29 INFO\u001b[0m Step 957/1000 | Loss: 2.1078\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:29 INFO\u001b[0m Step 958/1000 | Loss: 1.8231\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:29 INFO\u001b[0m Step 958/1000 | Loss: 1.8868\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:29 INFO\u001b[0m Step 958/1000 | Loss: 2.2174\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:29 INFO\u001b[0m Step 958/1000 | Loss: 1.9204\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:29 INFO\u001b[0m Step 958/1000 | Loss: 1.8967\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:29 INFO\u001b[0m Step 958/1000 | Loss: 2.0617\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:29 INFO\u001b[0m Step 958/1000 | Loss: 1.7691\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:29 INFO\u001b[0m Step 958/1000 | Loss: 1.8754\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:29 INFO\u001b[0m Step 959/1000 | Loss: 2.1045\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:29 INFO\u001b[0m Step 959/1000 | Loss: 1.9322\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:29 INFO\u001b[0m Step 959/1000 | Loss: 1.6804\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:29 INFO\u001b[0m Step 959/1000 | Loss: 2.2594\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:29 INFO\u001b[0m Step 959/1000 | Loss: 1.7338\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:29 INFO\u001b[0m Step 959/1000 | Loss: 1.8954\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:29 INFO\u001b[0m Step 959/1000 | Loss: 1.7148\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:29 INFO\u001b[0m Step 959/1000 | Loss: 2.0570\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:30 INFO\u001b[0m Step 960/1000 | Loss: 1.9443\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:30 INFO\u001b[0m Step 960/1000 | Loss: 1.7542\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:30 INFO\u001b[0m Step 960/1000 | Loss: 1.9073\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:30 INFO\u001b[0m Step 960/1000 | Loss: 1.8804\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:30 INFO\u001b[0m Step 960/1000 | Loss: 2.6915\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:30 INFO\u001b[0m Step 960/1000 | Loss: 1.6930\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:30 INFO\u001b[0m Step 960/1000 | Loss: 2.0295\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:30 INFO\u001b[0m Step 960/1000 | Loss: 2.2076\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:30 INFO\u001b[0m Step 961/1000 | Loss: 2.4629\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:30 INFO\u001b[0m Step 961/1000 | Loss: 2.2881\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:30 INFO\u001b[0m Step 961/1000 | Loss: 1.9425\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:30 INFO\u001b[0m Step 961/1000 | Loss: 1.8956\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:30 INFO\u001b[0m Step 961/1000 | Loss: 2.5517\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:30 INFO\u001b[0m Step 961/1000 | Loss: 1.5158\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:30 INFO\u001b[0m Step 961/1000 | Loss: 1.9988\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:30 INFO\u001b[0m Step 961/1000 | Loss: 1.8353\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:31 INFO\u001b[0m Step 962/1000 | Loss: 1.6551\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:31 INFO\u001b[0m Step 962/1000 | Loss: 2.1505\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:31 INFO\u001b[0m Step 962/1000 | Loss: 1.9205\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:31 INFO\u001b[0m Step 962/1000 | Loss: 1.8756\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:31 INFO\u001b[0m Step 962/1000 | Loss: 2.4318\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:31 INFO\u001b[0m Step 962/1000 | Loss: 2.0341\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:31 INFO\u001b[0m Step 962/1000 | Loss: 1.8806\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:31 INFO\u001b[0m Step 962/1000 | Loss: 1.4689\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:31 INFO\u001b[0m Step 963/1000 | Loss: 1.6474\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:31 INFO\u001b[0m Step 963/1000 | Loss: 1.8699\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:31 INFO\u001b[0m Step 963/1000 | Loss: 1.7939\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:31 INFO\u001b[0m Step 963/1000 | Loss: 2.0464\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:31 INFO\u001b[0m Step 963/1000 | Loss: 1.7059\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:31 INFO\u001b[0m Step 963/1000 | Loss: 1.5295\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:31 INFO\u001b[0m Step 963/1000 | Loss: 1.8896\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:31 INFO\u001b[0m Step 963/1000 | Loss: 2.0815\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:31 INFO\u001b[0m Step 964/1000 | Loss: 2.1685\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:31 INFO\u001b[0m Step 964/1000 | Loss: 1.9975\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:31 INFO\u001b[0m Step 964/1000 | Loss: 1.8564\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:31 INFO\u001b[0m Step 964/1000 | Loss: 2.0463\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:31 INFO\u001b[0m Step 964/1000 | Loss: 1.8918\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:31 INFO\u001b[0m Step 964/1000 | Loss: 1.7265\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:31 INFO\u001b[0m Step 964/1000 | Loss: 2.1217\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:31 INFO\u001b[0m Step 964/1000 | Loss: 2.0317\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:32 INFO\u001b[0m Step 965/1000 | Loss: 1.7263\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:32 INFO\u001b[0m Step 965/1000 | Loss: 2.0979\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:32 INFO\u001b[0m Step 965/1000 | Loss: 1.9266\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:32 INFO\u001b[0m Step 965/1000 | Loss: 1.8110\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:32 INFO\u001b[0m Step 965/1000 | Loss: 2.0010\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:32 INFO\u001b[0m Step 965/1000 | Loss: 1.7128\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:32 INFO\u001b[0m Step 965/1000 | Loss: 1.8233\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:32 INFO\u001b[0m Step 965/1000 | Loss: 1.7429\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:32 INFO\u001b[0m Step 966/1000 | Loss: 1.8701\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:32 INFO\u001b[0m Step 966/1000 | Loss: 1.7189\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:32 INFO\u001b[0m Step 966/1000 | Loss: 2.1157\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:32 INFO\u001b[0m Step 966/1000 | Loss: 1.7452\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:32 INFO\u001b[0m Step 966/1000 | Loss: 2.5638\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:32 INFO\u001b[0m Step 966/1000 | Loss: 1.5801\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:32 INFO\u001b[0m Step 966/1000 | Loss: 1.9949\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:32 INFO\u001b[0m Step 966/1000 | Loss: 1.6338\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:33 INFO\u001b[0m Step 967/1000 | Loss: 1.9065\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:33 INFO\u001b[0m Step 967/1000 | Loss: 1.6275\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:33 INFO\u001b[0m Step 967/1000 | Loss: 1.7527\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:33 INFO\u001b[0m Step 967/1000 | Loss: 2.0682\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:33 INFO\u001b[0m Step 967/1000 | Loss: 1.8591\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:33 INFO\u001b[0m Step 967/1000 | Loss: 2.0267\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:33 INFO\u001b[0m Step 967/1000 | Loss: 1.9858\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:33 INFO\u001b[0m Step 967/1000 | Loss: 2.0306\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:33 INFO\u001b[0m Step 968/1000 | Loss: 1.8200\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:33 INFO\u001b[0m Step 968/1000 | Loss: 1.7398\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:33 INFO\u001b[0m Step 968/1000 | Loss: 1.6976\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:33 INFO\u001b[0m Step 968/1000 | Loss: 1.8872\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:33 INFO\u001b[0m Step 968/1000 | Loss: 1.8894\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:33 INFO\u001b[0m Step 968/1000 | Loss: 1.9483\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:33 INFO\u001b[0m Step 968/1000 | Loss: 2.1715\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:33 INFO\u001b[0m Step 968/1000 | Loss: 2.0058\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:33 INFO\u001b[0m Step 969/1000 | Loss: 2.1532\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:33 INFO\u001b[0m Step 969/1000 | Loss: 1.8023\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:33 INFO\u001b[0m Step 969/1000 | Loss: 1.6965\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:33 INFO\u001b[0m Step 969/1000 | Loss: 2.3688\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:33 INFO\u001b[0m Step 969/1000 | Loss: 1.7041\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:33 INFO\u001b[0m Step 969/1000 | Loss: 2.3280\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:33 INFO\u001b[0m Step 969/1000 | Loss: 1.6274\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:33 INFO\u001b[0m Step 969/1000 | Loss: 2.0031\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:34 INFO\u001b[0m Step 970/1000 | Loss: 2.0979\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:34 INFO\u001b[0m Step 970/1000 | Loss: 2.1075\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:34 INFO\u001b[0m Step 970/1000 | Loss: 2.2438\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:34 INFO\u001b[0m Step 970/1000 | Loss: 1.8739\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:34 INFO\u001b[0m Step 970/1000 | Loss: 1.8983\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:34 INFO\u001b[0m Step 970/1000 | Loss: 1.7122\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:34 INFO\u001b[0m Step 970/1000 | Loss: 1.9358\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:34 INFO\u001b[0m Step 970/1000 | Loss: 1.7476\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:34 INFO\u001b[0m Step 971/1000 | Loss: 1.8308\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:34 INFO\u001b[0m Step 971/1000 | Loss: 1.7869\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:34 INFO\u001b[0m Step 971/1000 | Loss: 1.6426\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:34 INFO\u001b[0m Step 971/1000 | Loss: 1.9893\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:34 INFO\u001b[0m Step 971/1000 | Loss: 1.6456\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:34 INFO\u001b[0m Step 971/1000 | Loss: 2.0243\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:34 INFO\u001b[0m Step 971/1000 | Loss: 1.8478\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:34 INFO\u001b[0m Step 971/1000 | Loss: 1.9519\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:35 INFO\u001b[0m Step 972/1000 | Loss: 2.0576\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:35 INFO\u001b[0m Step 972/1000 | Loss: 2.2250\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:35 INFO\u001b[0m Step 972/1000 | Loss: 1.5784\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:35 INFO\u001b[0m Step 972/1000 | Loss: 1.8747\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:35 INFO\u001b[0m Step 972/1000 | Loss: 2.5742\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:35 INFO\u001b[0m Step 972/1000 | Loss: 1.9529\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:35 INFO\u001b[0m Step 972/1000 | Loss: 1.7372\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:35 INFO\u001b[0m Step 972/1000 | Loss: 2.0168\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:35 INFO\u001b[0m Step 973/1000 | Loss: 1.5259\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:35 INFO\u001b[0m Step 973/1000 | Loss: 2.1466\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:35 INFO\u001b[0m Step 973/1000 | Loss: 2.3050\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:35 INFO\u001b[0m Step 973/1000 | Loss: 2.0891\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:35 INFO\u001b[0m Step 973/1000 | Loss: 1.5843\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:35 INFO\u001b[0m Step 973/1000 | Loss: 1.8199\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:35 INFO\u001b[0m Step 973/1000 | Loss: 1.8795\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:35 INFO\u001b[0m Step 973/1000 | Loss: 2.1851\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:35 INFO\u001b[0m Step 974/1000 | Loss: 1.8438\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:35 INFO\u001b[0m Step 974/1000 | Loss: 1.7513\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:35 INFO\u001b[0m Step 974/1000 | Loss: 1.7558\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:35 INFO\u001b[0m Step 974/1000 | Loss: 1.4948\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:35 INFO\u001b[0m Step 974/1000 | Loss: 2.0607\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:35 INFO\u001b[0m Step 974/1000 | Loss: 2.0480\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:35 INFO\u001b[0m Step 974/1000 | Loss: 1.4360\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:35 INFO\u001b[0m Step 974/1000 | Loss: 2.0571\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:36 INFO\u001b[0m Step 975/1000 | Loss: 1.8065\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:36 INFO\u001b[0m Step 975/1000 | Loss: 1.9628\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:36 INFO\u001b[0m Step 975/1000 | Loss: 2.1041\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:36 INFO\u001b[0m Step 975/1000 | Loss: 1.8708\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:36 INFO\u001b[0m Step 975/1000 | Loss: 1.9411\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:36 INFO\u001b[0m Step 975/1000 | Loss: 2.0384\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:36 INFO\u001b[0m Step 975/1000 | Loss: 1.9936\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:36 INFO\u001b[0m Step 975/1000 | Loss: 5.7108\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:36 INFO\u001b[0m Step 976/1000 | Loss: 1.8276\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:36 INFO\u001b[0m Step 976/1000 | Loss: 1.4967\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:36 INFO\u001b[0m Step 976/1000 | Loss: 1.5495\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:36 INFO\u001b[0m Step 976/1000 | Loss: 2.0675\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:36 INFO\u001b[0m Step 976/1000 | Loss: 2.3340\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:36 INFO\u001b[0m Step 976/1000 | Loss: 1.9345\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:36 INFO\u001b[0m Step 976/1000 | Loss: 2.3547\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:36 INFO\u001b[0m Step 976/1000 | Loss: 1.6206\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:37 INFO\u001b[0m Step 977/1000 | Loss: 1.7512\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:37 INFO\u001b[0m Step 977/1000 | Loss: 1.6826\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:37 INFO\u001b[0m Step 977/1000 | Loss: 1.5931\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:37 INFO\u001b[0m Step 977/1000 | Loss: 1.6953\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:37 INFO\u001b[0m Step 977/1000 | Loss: 1.9860\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:37 INFO\u001b[0m Step 977/1000 | Loss: 1.8673\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:37 INFO\u001b[0m Step 977/1000 | Loss: 1.2790\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:37 INFO\u001b[0m Step 977/1000 | Loss: 2.1652\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:37 INFO\u001b[0m Step 978/1000 | Loss: 1.9275\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:37 INFO\u001b[0m Step 978/1000 | Loss: 1.9786\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:37 INFO\u001b[0m Step 978/1000 | Loss: 2.6459\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:37 INFO\u001b[0m Step 978/1000 | Loss: 1.9703\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:37 INFO\u001b[0m Step 978/1000 | Loss: 1.8126\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:37 INFO\u001b[0m Step 978/1000 | Loss: 1.8234\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:37 INFO\u001b[0m Step 978/1000 | Loss: 2.2171\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:37 INFO\u001b[0m Step 978/1000 | Loss: 1.4780\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:37 INFO\u001b[0m Step 979/1000 | Loss: 1.6751\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:37 INFO\u001b[0m Step 979/1000 | Loss: 1.8375\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:37 INFO\u001b[0m Step 979/1000 | Loss: 1.2623\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:37 INFO\u001b[0m Step 979/1000 | Loss: 2.1066\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:37 INFO\u001b[0m Step 979/1000 | Loss: 2.0133\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:37 INFO\u001b[0m Step 979/1000 | Loss: 1.8294\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:37 INFO\u001b[0m Step 979/1000 | Loss: 1.8239\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:37 INFO\u001b[0m Step 979/1000 | Loss: 2.0886\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:38 INFO\u001b[0m Step 980/1000 | Loss: 1.8990\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:38 INFO\u001b[0m Step 980/1000 | Loss: 1.7648\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:38 INFO\u001b[0m Step 980/1000 | Loss: 1.8731\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:38 INFO\u001b[0m Step 980/1000 | Loss: 2.3509\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:38 INFO\u001b[0m Step 980/1000 | Loss: 2.0063\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:38 INFO\u001b[0m Step 980/1000 | Loss: 1.9690\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:38 INFO\u001b[0m Step 980/1000 | Loss: 2.4765\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:38 INFO\u001b[0m Step 980/1000 | Loss: 2.1759\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:38 INFO\u001b[0m Step 981/1000 | Loss: 1.7807\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:38 INFO\u001b[0m Step 981/1000 | Loss: 1.9273\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:38 INFO\u001b[0m Step 981/1000 | Loss: 2.0010\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:38 INFO\u001b[0m Step 981/1000 | Loss: 2.2763\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:38 INFO\u001b[0m Step 981/1000 | Loss: 1.8387\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:38 INFO\u001b[0m Step 981/1000 | Loss: 1.8883\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:38 INFO\u001b[0m Step 981/1000 | Loss: 1.7702\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:38 INFO\u001b[0m Step 981/1000 | Loss: 2.0474\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:39 INFO\u001b[0m Step 982/1000 | Loss: 1.8477\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:39 INFO\u001b[0m Step 982/1000 | Loss: 1.7732\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:39 INFO\u001b[0m Step 982/1000 | Loss: 2.0325\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:39 INFO\u001b[0m Step 982/1000 | Loss: 1.9312\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:39 INFO\u001b[0m Step 982/1000 | Loss: 1.6586\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:39 INFO\u001b[0m Step 982/1000 | Loss: 2.0343\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:39 INFO\u001b[0m Step 982/1000 | Loss: 1.8103\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:39 INFO\u001b[0m Step 982/1000 | Loss: 2.0873\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:39 INFO\u001b[0m Step 983/1000 | Loss: 2.0300\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:39 INFO\u001b[0m Step 983/1000 | Loss: 2.0910\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:39 INFO\u001b[0m Step 983/1000 | Loss: 1.6978\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:39 INFO\u001b[0m Step 983/1000 | Loss: 1.8870\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:39 INFO\u001b[0m Step 983/1000 | Loss: 1.8648\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:39 INFO\u001b[0m Step 983/1000 | Loss: 1.9045\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:39 INFO\u001b[0m Step 983/1000 | Loss: 2.1216\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:39 INFO\u001b[0m Step 983/1000 | Loss: 2.0574\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:39 INFO\u001b[0m Step 984/1000 | Loss: 1.6804\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:39 INFO\u001b[0m Step 984/1000 | Loss: 2.0890\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:39 INFO\u001b[0m Step 984/1000 | Loss: 1.6695\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:39 INFO\u001b[0m Step 984/1000 | Loss: 1.5090\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:39 INFO\u001b[0m Step 984/1000 | Loss: 1.9856\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:39 INFO\u001b[0m Step 984/1000 | Loss: 1.9117\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:39 INFO\u001b[0m Step 984/1000 | Loss: 2.3885\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:39 INFO\u001b[0m Step 984/1000 | Loss: 1.8684\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:40 INFO\u001b[0m Step 985/1000 | Loss: 1.9345\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:40 INFO\u001b[0m Step 985/1000 | Loss: 1.5783\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:40 INFO\u001b[0m Step 985/1000 | Loss: 2.1998\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:40 INFO\u001b[0m Step 985/1000 | Loss: 1.8861\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:40 INFO\u001b[0m Step 985/1000 | Loss: 1.8062\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:40 INFO\u001b[0m Step 985/1000 | Loss: 1.7746\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:40 INFO\u001b[0m Step 985/1000 | Loss: 1.6022\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:40 INFO\u001b[0m Step 985/1000 | Loss: 2.1647\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:40 INFO\u001b[0m Step 986/1000 | Loss: 1.4325\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:40 INFO\u001b[0m Step 986/1000 | Loss: 2.1134\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:40 INFO\u001b[0m Step 986/1000 | Loss: 2.2119\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:40 INFO\u001b[0m Step 986/1000 | Loss: 2.0763\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:40 INFO\u001b[0m Step 986/1000 | Loss: 1.5295\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:40 INFO\u001b[0m Step 986/1000 | Loss: 2.2250\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:40 INFO\u001b[0m Step 986/1000 | Loss: 1.8459\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:40 INFO\u001b[0m Step 986/1000 | Loss: 2.0485\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:41 INFO\u001b[0m Step 987/1000 | Loss: 1.7294\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:41 INFO\u001b[0m Step 987/1000 | Loss: 1.6714\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:41 INFO\u001b[0m Step 987/1000 | Loss: 2.0524\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:41 INFO\u001b[0m Step 987/1000 | Loss: 1.5674\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:41 INFO\u001b[0m Step 987/1000 | Loss: 1.7815\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:41 INFO\u001b[0m Step 987/1000 | Loss: 2.0488\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:41 INFO\u001b[0m Step 987/1000 | Loss: 1.7385\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:41 INFO\u001b[0m Step 987/1000 | Loss: 2.1358\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:41 INFO\u001b[0m Step 988/1000 | Loss: 2.0686\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:41 INFO\u001b[0m Step 988/1000 | Loss: 1.5166\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:41 INFO\u001b[0m Step 988/1000 | Loss: 1.9432\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:41 INFO\u001b[0m Step 988/1000 | Loss: 1.7738\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:41 INFO\u001b[0m Step 988/1000 | Loss: 1.9405\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:41 INFO\u001b[0m Step 988/1000 | Loss: 2.1126\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:41 INFO\u001b[0m Step 988/1000 | Loss: 1.7792\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:41 INFO\u001b[0m Step 988/1000 | Loss: 1.9933\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:41 INFO\u001b[0m Step 989/1000 | Loss: 1.7753\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:41 INFO\u001b[0m Step 989/1000 | Loss: 2.0777\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:41 INFO\u001b[0m Step 989/1000 | Loss: 2.2182\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:41 INFO\u001b[0m Step 989/1000 | Loss: 1.4972\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:41 INFO\u001b[0m Step 989/1000 | Loss: 1.6224\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:41 INFO\u001b[0m Step 989/1000 | Loss: 1.6519\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:41 INFO\u001b[0m Step 989/1000 | Loss: 2.0006\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:41 INFO\u001b[0m Step 989/1000 | Loss: 1.5340\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:42 INFO\u001b[0m Step 990/1000 | Loss: 1.6253\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:42 INFO\u001b[0m Step 990/1000 | Loss: 1.9025\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:42 INFO\u001b[0m Step 990/1000 | Loss: 1.7487\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:42 INFO\u001b[0m Step 990/1000 | Loss: 1.8130\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:42 INFO\u001b[0m Step 990/1000 | Loss: 2.2267\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:42 INFO\u001b[0m Step 990/1000 | Loss: 1.8959\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:42 INFO\u001b[0m Step 990/1000 | Loss: 2.0996\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:42 INFO\u001b[0m Step 990/1000 | Loss: 1.9906\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:42 INFO\u001b[0m Step 991/1000 | Loss: 1.7626\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:42 INFO\u001b[0m Step 991/1000 | Loss: 1.8395\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:42 INFO\u001b[0m Step 991/1000 | Loss: 2.0232\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:42 INFO\u001b[0m Step 991/1000 | Loss: 1.5590\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:42 INFO\u001b[0m Step 991/1000 | Loss: 2.0863\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:42 INFO\u001b[0m Step 991/1000 | Loss: 1.8455\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:42 INFO\u001b[0m Step 991/1000 | Loss: 2.0033\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:42 INFO\u001b[0m Step 991/1000 | Loss: 1.8521\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:43 INFO\u001b[0m Step 992/1000 | Loss: 1.6370\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:43 INFO\u001b[0m Step 992/1000 | Loss: 1.9110\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:43 INFO\u001b[0m Step 992/1000 | Loss: 2.0896\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:43 INFO\u001b[0m Step 992/1000 | Loss: 2.0188\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:43 INFO\u001b[0m Step 992/1000 | Loss: 1.8299\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:43 INFO\u001b[0m Step 992/1000 | Loss: 1.6253\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:43 INFO\u001b[0m Step 992/1000 | Loss: 1.6157\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:43 INFO\u001b[0m Step 992/1000 | Loss: 1.8125\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:43 INFO\u001b[0m Step 993/1000 | Loss: 1.9589\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:43 INFO\u001b[0m Step 993/1000 | Loss: 1.7561\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:43 INFO\u001b[0m Step 993/1000 | Loss: 1.9467\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:43 INFO\u001b[0m Step 993/1000 | Loss: 1.9550\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:43 INFO\u001b[0m Step 993/1000 | Loss: 1.7927\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:43 INFO\u001b[0m Step 993/1000 | Loss: 2.1645\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:43 INFO\u001b[0m Step 993/1000 | Loss: 1.9800\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:43 INFO\u001b[0m Step 993/1000 | Loss: 1.7060\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:43 INFO\u001b[0m Step 994/1000 | Loss: 1.9006\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:43 INFO\u001b[0m Step 994/1000 | Loss: 1.9095\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:43 INFO\u001b[0m Step 994/1000 | Loss: 1.5183\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:43 INFO\u001b[0m Step 994/1000 | Loss: 2.0252\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:43 INFO\u001b[0m Step 994/1000 | Loss: 1.3115\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:43 INFO\u001b[0m Step 994/1000 | Loss: 2.0764\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:43 INFO\u001b[0m Step 994/1000 | Loss: 1.7201\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:43 INFO\u001b[0m Step 994/1000 | Loss: 1.9316\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:44 INFO\u001b[0m Step 995/1000 | Loss: 1.8546\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:44 INFO\u001b[0m Step 995/1000 | Loss: 2.4217\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:44 INFO\u001b[0m Step 995/1000 | Loss: 1.7860\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:44 INFO\u001b[0m Step 995/1000 | Loss: 2.0023\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:44 INFO\u001b[0m Step 995/1000 | Loss: 1.7533\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:44 INFO\u001b[0m Step 995/1000 | Loss: 1.8981\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:44 INFO\u001b[0m Step 995/1000 | Loss: 1.9979\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:44 INFO\u001b[0m Step 995/1000 | Loss: 1.9491\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:44 INFO\u001b[0m Step 996/1000 | Loss: 1.6978\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:44 INFO\u001b[0m Step 996/1000 | Loss: 1.8754\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:44 INFO\u001b[0m Step 996/1000 | Loss: 1.7993\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:44 INFO\u001b[0m Step 996/1000 | Loss: 1.5138\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:44 INFO\u001b[0m Step 996/1000 | Loss: 1.8449\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:44 INFO\u001b[0m Step 996/1000 | Loss: 2.1237\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:44 INFO\u001b[0m Step 996/1000 | Loss: 2.0114\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:44 INFO\u001b[0m Step 996/1000 | Loss: 1.6966\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:45 INFO\u001b[0m Step 997/1000 | Loss: 1.8625\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:45 INFO\u001b[0m Step 997/1000 | Loss: 1.6658\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:45 INFO\u001b[0m Step 997/1000 | Loss: 1.8555\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:45 INFO\u001b[0m Step 997/1000 | Loss: 1.5345\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:45 INFO\u001b[0m Step 997/1000 | Loss: 2.0807\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:45 INFO\u001b[0m Step 997/1000 | Loss: 2.0459\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:45 INFO\u001b[0m Step 997/1000 | Loss: 1.9589\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:45 INFO\u001b[0m Step 997/1000 | Loss: 1.6433\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:45 INFO\u001b[0m Step 998/1000 | Loss: 1.5638\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:45 INFO\u001b[0m Step 998/1000 | Loss: 1.9738\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:45 INFO\u001b[0m Step 998/1000 | Loss: 2.3698\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:45 INFO\u001b[0m Step 998/1000 | Loss: 1.8588\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:45 INFO\u001b[0m Step 998/1000 | Loss: 2.0712\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:45 INFO\u001b[0m Step 998/1000 | Loss: 2.0403\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:45 INFO\u001b[0m Step 998/1000 | Loss: 2.0635\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:45 INFO\u001b[0m Step 998/1000 | Loss: 1.9171\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:45 INFO\u001b[0m Step 999/1000 | Loss: 1.8366\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:45 INFO\u001b[0m Step 999/1000 | Loss: 2.4319\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:45 INFO\u001b[0m Step 999/1000 | Loss: 1.6347\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:45 INFO\u001b[0m Step 999/1000 | Loss: 2.0900\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:45 INFO\u001b[0m Step 999/1000 | Loss: 1.9721\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:45 INFO\u001b[0m Step 999/1000 | Loss: 1.7384\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:45 INFO\u001b[0m Step 999/1000 | Loss: 1.4629\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:45 INFO\u001b[0m Step 999/1000 | Loss: 1.9464\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:45 INFO\u001b[0m Saving the checkpoint (or staging if async is enabled).\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:48:45 INFO\u001b[0m Saving a model only checkpoint in torch.float32 at last step, step 1000.\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:45 INFO\u001b[0m Saving the checkpoint (or staging if async is enabled).\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:45 INFO\u001b[0m Saving the checkpoint (or staging if async is enabled).\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:48:45 INFO\u001b[0m Saving a model only checkpoint in torch.float32 at last step, step 1000.\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:48:45 INFO\u001b[0m Saving a model only checkpoint in torch.float32 at last step, step 1000.\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:45 INFO\u001b[0m Saving the checkpoint (or staging if async is enabled).\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:45 INFO\u001b[0m Saving the checkpoint (or staging if async is enabled).\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:45 INFO\u001b[0m Saving the checkpoint (or staging if async is enabled).\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:48:45 INFO\u001b[0m Saving a model only checkpoint in torch.float32 at last step, step 1000.\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:48:45 INFO\u001b[0m Saving a model only checkpoint in torch.float32 at last step, step 1000.\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:48:45 INFO\u001b[0m Saving a model only checkpoint in torch.float32 at last step, step 1000.\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:45 INFO\u001b[0m Saving the checkpoint (or staging if async is enabled).\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:48:45 INFO\u001b[0m Saving a model only checkpoint in torch.float32 at last step, step 1000.\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:45 INFO\u001b[0m Saving the checkpoint (or staging if async is enabled).\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:48:45 INFO\u001b[0m Saving a model only checkpoint in torch.float32 at last step, step 1000.\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[0] /home/hosseinkh/.conda/envs/forge/lib/python3.10/site-packages/torch/distributed/distributed_c10d.py:4870: UserWarning: barrier(): using the device under current context. You can specify `device_id` in `init_process_group` to mute this warning.\n", + "[0] warnings.warn( # warn only once\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:49:35 INFO\u001b[0m [GC] GC collection invoked by checkpointer. took 2.57 seconds\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 11:49:35 INFO\u001b[0m Training complete!\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:49:35 INFO\u001b[0m [GC] GC collection invoked by checkpointer. took 2.60 seconds\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 11:49:35 INFO\u001b[0m Training complete!\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:49:35 INFO\u001b[0m [GC] GC collection invoked by checkpointer. took 2.62 seconds\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 11:49:35 INFO\u001b[0m Training complete!\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:49:35 INFO\u001b[0m [GC] GC collection invoked by checkpointer. took 2.63 seconds\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:49:35 INFO\u001b[0m [GC] GC collection invoked by checkpointer. took 2.63 seconds\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 11:49:35 INFO\u001b[0m Training complete!\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 11:49:35 INFO\u001b[0m Training complete!\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:49:35 INFO\u001b[0m [GC] GC collection invoked by checkpointer. took 2.68 seconds\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 11:49:35 INFO\u001b[0m Training complete!\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:49:35 INFO\u001b[0m [GC] GC collection invoked by checkpointer. took 2.69 seconds\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 11:49:35 INFO\u001b[0m Training complete!\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:49:35 INFO\u001b[0m [GC] GC collection invoked by checkpointer. took 2.71 seconds\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 11:49:35 INFO\u001b[0m Training complete!\n", + "✓ Training complete\n" + ] + } + ], + "source": [ + "# Run training\n", + "await spawner.run()\n", + "print(\"✓ Training complete\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Cleanup" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": { + "output": { + "id": 742146812207438, + "loadingStatus": "loaded" + } + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 12:20:30 INFO\u001b[0m Cleaning up trainer actor...\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 12:20:30 INFO\u001b[0m Cleaning up trainer actor...\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 12:20:30 INFO\u001b[0m Cleaning up trainer actor...\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 12:20:30 INFO\u001b[0m Cleaning up trainer actor...\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 12:20:30 INFO\u001b[0m Cleaning up trainer actor...\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 12:20:30 INFO\u001b[0m Cleaning up trainer actor...\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 12:20:30 INFO\u001b[0m Cleaning up trainer actor...\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 12:20:30 INFO\u001b[0m Destroying the purge thread.\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 12:20:30 INFO\u001b[0m Destroying the purge thread.\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 12:20:30 INFO\u001b[0m Destroying the purge thread.\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 12:20:30 INFO\u001b[0m Destroying the purge thread.\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 12:20:30 INFO\u001b[0m Destroying the purge thread.\n", + "[5] \u001b[34m[TrainerActor-5/8] 2025-10-15 12:20:30 INFO\u001b[0m Cleanup complete.\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 12:20:30 INFO\u001b[0m Destroying the purge thread.\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 12:20:30 INFO\u001b[0m Destroying the purge thread.\n", + "[6] \u001b[34m[TrainerActor-6/8] 2025-10-15 12:20:30 INFO\u001b[0m Cleanup complete.\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 12:20:30 INFO\u001b[0m Cleaning up trainer actor...\n", + "[4] \u001b[34m[TrainerActor-4/8] 2025-10-15 12:20:30 INFO\u001b[0m Cleanup complete.\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 12:20:30 INFO\u001b[0m Destroying the purge thread.\n", + "[2] \u001b[34m[TrainerActor-2/8] 2025-10-15 12:20:30 INFO\u001b[0m Cleanup complete.\n", + "[7] \u001b[34m[TrainerActor-7/8] 2025-10-15 12:20:30 INFO\u001b[0m Cleanup complete.\n", + "[1] \u001b[34m[TrainerActor-1/8] 2025-10-15 12:20:30 INFO\u001b[0m Cleanup complete.\n", + "[3] \u001b[34m[TrainerActor-3/8] 2025-10-15 12:20:30 INFO\u001b[0m Cleanup complete.\n", + "[0] \u001b[34m[TrainerActor-0/8] 2025-10-15 12:20:30 INFO\u001b[0m Cleanup complete.\n", + "✓ Cleanup complete\n" + ] + } + ], + "source": [ + "# Cleanup resources\n", + "await spawner.cleanup()\n", + "print(\"✓ Cleanup complete\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "---\n", + "\n", + "# Quick Configuration Templates\n", + "\n", + "Here are ready-to-use templates for common scenarios!" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Template 1: Quick Test (Single GPU, Small Steps)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "quick_test_config = OmegaConf.create({\n", + " \"comm\": {\"trace_buf_size\": 0},\n", + " \"model\": {\n", + " \"name\": \"llama3\",\n", + " \"flavor\": \"8B\",\n", + " \"hf_assets_path\": \"/tmp/Meta-Llama-3.1-8B-Instruct\"\n", + " },\n", + " \"processes\": {\"procs\": 1, \"with_gpus\": True},\n", + " \"optimizer\": {\"name\": \"AdamW\", \"lr\": 1e-5, \"eps\": 1e-8},\n", + " \"lr_scheduler\": {\"warmup_steps\": 10},\n", + " \"training\": {\n", + " \"local_batch_size\": 1,\n", + " \"seq_len\": 1024,\n", + " \"max_norm\": 1.0,\n", + " \"steps\": 100, # Just 100 steps for quick testing\n", + " \"compile\": False,\n", + " \"dataset\": \"c4\"\n", + " },\n", + " \"parallelism\": {\n", + " \"data_parallel_replicate_degree\": 1,\n", + " \"data_parallel_shard_degree\": 1,\n", + " \"tensor_parallel_degree\": 1,\n", + " \"pipeline_parallel_degree\": 1,\n", + " \"context_parallel_degree\": 1,\n", + " \"expert_parallel_degree\": 1,\n", + " \"disable_loss_parallel\": False\n", + " },\n", + " \"checkpoint\": {\n", + " \"enable\": True,\n", + " \"folder\": \"/tmp/quick_test_checkpoints\",\n", + " \"initial_load_path\": \"/tmp/Meta-Llama-3.1-8B-Instruct/\",\n", + " \"initial_load_in_hf\": True,\n", + " \"last_save_in_hf\": True,\n", + " \"interval\": 50,\n", + " \"async_mode\": \"disabled\"\n", + " },\n", + " \"activation_checkpoint\": {\n", + " \"mode\": \"selective\",\n", + " \"selective_ac_option\": \"op\"\n", + " }\n", + "})\n", + "\n", + "print(\"Quick Test Configuration:\")\n", + "print(OmegaConf.to_yaml(quick_test_config))\n", + "\n", + "# To use: await run_actor(TrainerActor, quick_test_config)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Template 2: Multi-GPU Training (8 GPUs with FSDP)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "multi_gpu_config = OmegaConf.create({\n", + " \"comm\": {\"trace_buf_size\": 0},\n", + " \"model\": {\n", + " \"name\": \"llama3\",\n", + " \"flavor\": \"8B\",\n", + " \"hf_assets_path\": \"/tmp/Meta-Llama-3.1-8B-Instruct\"\n", + " },\n", + " \"processes\": {\"procs\": 8, \"with_gpus\": True},\n", + " \"optimizer\": {\"name\": \"AdamW\", \"lr\": 2e-5, \"eps\": 1e-8},\n", + " \"lr_scheduler\": {\"warmup_steps\": 200},\n", + " \"training\": {\n", + " \"local_batch_size\": 2,\n", + " \"seq_len\": 2048,\n", + " \"max_norm\": 1.0,\n", + " \"steps\": 5000,\n", + " \"compile\": False,\n", + " \"dataset\": \"c4\"\n", + " },\n", + " \"parallelism\": {\n", + " \"data_parallel_replicate_degree\": 1,\n", + " \"data_parallel_shard_degree\": 8, # FSDP across 8 GPUs\n", + " \"tensor_parallel_degree\": 1,\n", + " \"pipeline_parallel_degree\": 1,\n", + " \"context_parallel_degree\": 1,\n", + " \"expert_parallel_degree\": 1,\n", + " \"disable_loss_parallel\": False\n", + " },\n", + " \"checkpoint\": {\n", + " \"enable\": True,\n", + " \"folder\": \"/tmp/multi_gpu_checkpoints\",\n", + " \"initial_load_path\": \"/tmp/Meta-Llama-3.1-8B-Instruct/\",\n", + " \"initial_load_in_hf\": True,\n", + " \"last_save_in_hf\": True,\n", + " \"interval\": 500,\n", + " \"async_mode\": \"disabled\"\n", + " },\n", + " \"activation_checkpoint\": {\n", + " \"mode\": \"selective\",\n", + " \"selective_ac_option\": \"op\"\n", + " }\n", + "})\n", + "\n", + "print(\"Multi-GPU Configuration:\")\n", + "print(OmegaConf.to_yaml(multi_gpu_config))\n", + "\n", + "# To use: await run_actor(TrainerActor, multi_gpu_config)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "---\n", + "\n", + "# Tips & Tricks\n", + "\n", + "## Memory Optimization\n", + "- ⬇️ Reduce `seq_len` if running out of memory\n", + "- ⬇️ Reduce `local_batch_size` if running out of memory\n", + "- ✅ Enable `activation_checkpoint` for memory savings\n", + "\n", + "## Training Speed\n", + "- ⬆️ Increase `local_batch_size` for faster training (if memory allows)\n", + "- 🚀 Use multiple GPUs with FSDP (`data_parallel_shard_degree > 1`)\n", + "- ⚡ Enable `compile: true` for PyTorch compilation (experimental)\n", + "\n", + "## Debugging\n", + "- 🧪 Start with small `steps` (e.g., 10-100) to test quickly\n", + "- 🔍 Use single GPU first (`procs: 1`)\n", + "- 📊 Monitor loss values in logs\n", + "\n", + "## Checkpoint Management\n", + "- 💾 Set `interval` based on how often you want to save\n", + "- 📁 Ensure `folder` path exists and has enough space\n", + "- 🔄 Use `initial_load_path` to resume from checkpoints" + ] + } + ], + "metadata": { + "fileHeader": "", + "fileUid": "924c63b2-fa48-4468-a04b-437f8bd23456", + "isAdHoc": false, + "kernelspec": { + "display_name": "forge (conda)", + "language": "python", + "name": "conda_forge" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.10.18" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git a/apps/sft/spawn_actor.py b/apps/sft/spawn_actor.py new file mode 100644 index 000000000..af235dfa4 --- /dev/null +++ b/apps/sft/spawn_actor.py @@ -0,0 +1,139 @@ +# Copyright (c) Meta Platforms, Inc. and affiliates. +# All rights reserved. +# +# This source code is licensed under the BSD-style license found in the +# LICENSE file in the root directory of this source tree. + +""" +SpawnActor - Orchestrates the spawning and lifecycle management of actors. + +This module provides a high-level interface for creating, setting up, running, +and cleaning up different types of actors (e.g., Trainer, Evaluator, etc.) +""" + +import logging +from typing import Any, Type + +from apps.sft.actor import BaseForgeActor +from omegaconf import DictConfig + +logger = logging.getLogger(__name__) +logger.setLevel(logging.INFO) + + +class SpawnActor: + """ + Orchestrator for spawning and managing actor lifecycles. + + This class handles the creation, setup, execution, and cleanup of actors + in a standardized way. + """ + + def __init__(self, actor_class: Type[BaseForgeActor], config: DictConfig): + """ + Initialize the spawn actor orchestrator. + + Args: + actor_class: The actor class to instantiate (must inherit from BaseForgeActor) + config: Configuration dictionary for the actor + """ + self.actor_class = actor_class + self.config = config + self.actor = None + + if not issubclass(actor_class, BaseForgeActor): + raise TypeError( + f"actor_class must be a subclass of BaseForgeActor, got {actor_class}" + ) + + async def spawn(self) -> Any: + """ + Spawn the actor instance with the given configuration. + + Returns: + The spawned actor instance + """ + logger.info(f"Spawning {self.actor_class.__name__}...") + + process_cfg = self.config.pop("processes", {}) + + self.actor = await self.actor_class.options(**process_cfg).as_actor(self.config) + + logger.info(f"{self.actor_class.__name__} spawned successfully.") + return self.actor + + async def setup(self): + """ + Setup the spawned actor (load data, checkpoints, etc.). + """ + if self.actor is None: + raise RuntimeError( + "Actor must be spawned before setup. Call spawn() first." + ) + + logger.info(f"Setting up {self.actor_class.__name__}...") + await self.actor.setup.call() + logger.info(f"{self.actor_class.__name__} setup complete.") + + async def run(self): + """ + Run the main execution logic of the actor. + """ + if self.actor is None: + raise RuntimeError( + "Actor must be spawned before running. Call spawn() first." + ) + + logger.info(f"Running {self.actor_class.__name__}...") + await self.actor.run.call() + logger.info(f"{self.actor_class.__name__} execution complete.") + + async def cleanup(self): + """ + Cleanup the actor resources and stop the mesh. + """ + if self.actor is None: + raise RuntimeError( + "Actor must be spawned before cleanup. Call spawn() first." + ) + + logger.info(f"Cleaning up {self.actor_class.__name__}...") + await self.actor.cleanup.call() + + if hasattr(self.actor, "mesh"): + await self.actor.mesh.stop() + + logger.info(f"{self.actor_class.__name__} cleanup complete.") + + async def run_full_lifecycle(self): + """ + Execute the complete actor lifecycle: spawn -> setup -> run -> cleanup. + + This is a convenience method that runs all phases in sequence. + """ + logger.info(f"Starting full lifecycle for {self.actor_class.__name__}...") + + try: + await self.spawn() + await self.setup() + await self.run() + finally: + if self.actor is not None: + await self.cleanup() + + logger.info(f"Full lifecycle complete for {self.actor_class.__name__}.") + + +async def run_actor( + actor_class: Type[BaseForgeActor], + config: DictConfig, +) -> None: + """ + Convenience function to run an actor with full lifecycle management. + + Args: + actor_class: The actor class to instantiate + config: Configuration dictionary for the actor + """ + spawner = SpawnActor(actor_class, config) + await spawner.run_full_lifecycle() diff --git a/apps/sft/trainer_actor.py b/apps/sft/trainer_actor.py new file mode 100644 index 000000000..bd0e4630a --- /dev/null +++ b/apps/sft/trainer_actor.py @@ -0,0 +1,189 @@ +# Copyright (c) Meta Platforms, Inc. and affiliates. +# All rights reserved. +# +# This source code is licensed under the BSD-style license found in the +# LICENSE file in the root directory of this source tree. + +""" +Trainer actor implementation for SFT training. + +This is a concrete implementation of BaseForgeActor for supervised fine-tuning. +""" + +import logging + +import torch +import torchtitan.experiments.forge.train_spec as forge_train_spec +from apps.sft.actor import BaseForgeActor +from apps.sft.utils import ( + create_context_parallel_context, + log_training_step, + move_batch_to_device, + setup_sft_dataloader, + setup_tokenizer, +) +from monarch.actor import endpoint +from omegaconf import DictConfig + +logger = logging.getLogger(__name__) +logger.setLevel(logging.INFO) + + +class TrainerActor(BaseForgeActor): + """ + Concrete trainer actor for supervised fine-tuning. + + Handles training loop, forward/backward passes, and checkpoint management. + """ + + train_spec: forge_train_spec.ForgeTrainSpec + train_dataloader: any + num_training_steps: int + + def __init__(self, config: DictConfig): + """ + Initialize the trainer actor. + + Args: + config: Configuration dictionary containing training settings + """ + super().__init__(config) + self.num_training_steps = self.job_config.training.steps + + @endpoint + async def setup(self): + """ + Setup the trainer (load data, checkpoint, etc.). + """ + logger.info("Setting up trainer actor...") + + self.tokenizer = setup_tokenizer( + hf_assets_path=self.job_config.model.hf_assets_path + ) + + self.train_dataloader = setup_sft_dataloader( + tokenizer=self.tokenizer, + dataset_path="yahma/alpaca-cleaned", + dataset_split="train", + target_tokens_per_pack=self.job_config.training.seq_len, + batch_size=self.job_config.training.local_batch_size, + device=self.device, + ) + + if self.checkpointer: + logger.info("Loading checkpoint...") + self.checkpointer.load(step=self.current_step) + + logger.info("Trainer setup complete.") + + def forward_backward( + self, input_dict: dict[str, torch.Tensor], labels: torch.Tensor + ) -> torch.Tensor: + """ + Perform forward and backward pass. + + Args: + input_dict: Dictionary containing input tokens + labels: Ground truth labels + + Returns: + Computed loss value + """ + model_parts = self.model_parts + parallel_dims = self.parallel_dims + inputs = input_dict["tokens"] + + optional_context_parallel_ctx = create_context_parallel_context( + parallel_dims=parallel_dims, + inputs=inputs, + labels=labels, + model_parts=model_parts, + rotate_method=self.job_config.parallelism.context_parallel_rotate_method, + ) + + if parallel_dims.pp_enabled: + with self.train_context(optional_context_parallel_ctx): + targets, losses = ( + (labels, []) if self.pp_has_last_stage else (None, None) + ) + if self.pp_has_first_stage: + self.pp_schedule.step( + inputs, target=targets, losses=losses, input_batch=inputs + ) + else: + self.pp_schedule.step( + target=targets, losses=losses, input_batch=inputs + ) + + loss = ( + torch.mean(torch.stack(losses)).to(self.device) + if self.pp_has_last_stage + else torch.tensor([-1.0], device=self.device) + ) + else: + with self.train_context(optional_context_parallel_ctx): + assert len(model_parts) == 1 + with self.maybe_enable_amp: + pred = model_parts[0](inputs) + loss = self.loss_fn(pred, labels) + del pred + loss.backward() + + return loss + + def train_step(self, batch: dict[str, torch.Tensor]) -> None: + """ + Execute a single training step. + + Args: + batch: Dictionary containing batch data (tokens, labels, etc.) + """ + labels = batch.pop("labels") + loss = self.forward_backward(batch, labels) + + log_training_step(self.current_step, self.num_training_steps, loss, logger) + + self.optimizers.step() + self.lr_schedulers.step() + + @endpoint + async def run(self) -> None: + """ + Main training loop. + """ + logger.info("Starting training loop...") + + dataloader = iter(self.train_dataloader) + self.optimizers.zero_grad() + + while self.current_step < self.num_training_steps: + batch = next(dataloader) + batch = move_batch_to_device(batch, self.device) + + self.train_step(batch) + self.current_step += 1 + + if self.checkpointer: + self.checkpointer.save( + curr_step=self.current_step, + last_step=self.current_step == self.num_training_steps, + ) + + logger.info("Training complete!") + + @endpoint + async def cleanup(self) -> None: + """ + Cleanup resources (close checkpointer, logger, etc.). + """ + logger.info("Cleaning up trainer actor...") + + if self.checkpointer: + self.checkpointer.close() + if self.metric_logger: + self.metric_logger.close() + + logger.info("Cleanup complete.") + + def __repr__(self) -> str: + return "TrainerActor" diff --git a/apps/sft/utils.py b/apps/sft/utils.py new file mode 100644 index 000000000..6d0219805 --- /dev/null +++ b/apps/sft/utils.py @@ -0,0 +1,187 @@ +# Copyright (c) Meta Platforms, Inc. and affiliates. +# All rights reserved. +# +# This source code is licensed under the BSD-style license found in the +# LICENSE file in the root directory of this source tree. + +""" +Utility functions for SFT training actors. + +These utilities handle data loading, model setup, and common operations. +""" + +import logging +import os +from functools import partial +from typing import Any, Optional + +import torch +from forge.data.collate import collate_packed +from forge.data.datasets.packed import PackedDataset, TextPacker +from forge.data.datasets.sft_dataset import AlpacaToMessages, sft_iterable_dataset +from forge.data.tokenizer import HuggingFaceModelTokenizer +from torchdata.stateful_dataloader import StatefulDataLoader +from torchtitan.distributed import ParallelDims, utils as dist_utils + +logger = logging.getLogger(__name__) +logger.setLevel(logging.INFO) + + +def setup_tokenizer( + hf_assets_path: str, + tokenizer_filename: str = "tokenizer.json", + tokenizer_config_filename: str = "tokenizer_config.json", + generation_config_filename: str = "generation_config.json", +) -> HuggingFaceModelTokenizer: + """ + Setup HuggingFace tokenizer from model assets. + + Args: + hf_assets_path: Path to the directory containing tokenizer files + tokenizer_filename: Name of the tokenizer JSON file + tokenizer_config_filename: Name of the tokenizer config JSON file + generation_config_filename: Name of the generation config JSON file + + Returns: + Initialized HuggingFaceModelTokenizer + """ + tokenizer_json_path = os.path.join(hf_assets_path, tokenizer_filename) + tokenizer_config_path = os.path.join(hf_assets_path, tokenizer_config_filename) + generation_config_path = os.path.join(hf_assets_path, generation_config_filename) + + logger.info(f"Loading tokenizer from: {tokenizer_json_path}") + + tokenizer = HuggingFaceModelTokenizer( + tokenizer_json_path=tokenizer_json_path, + tokenizer_config_json_path=tokenizer_config_path, + generation_config_path=generation_config_path, + ) + + return tokenizer + + +def setup_sft_dataloader( + tokenizer: HuggingFaceModelTokenizer, + dataset_path: str, + dataset_split: str, + target_tokens_per_pack: int, + batch_size: int, + device: torch.device, + padding_idx: int = 0, + message_transform: Optional[Any] = None, +) -> StatefulDataLoader: + """ + Setup dataloader for SFT training. + + Args: + tokenizer: Tokenizer to use for processing text + dataset_path: Path or name of the dataset (e.g., "yahma/alpaca-cleaned") + dataset_split: Dataset split to use (e.g., "train", "validation") + target_tokens_per_pack: Target sequence length for packing + batch_size: Batch size for training + device: Device to move tensors to + padding_idx: Padding token index + message_transform: Transform to convert dataset format to messages + + Returns: + Configured StatefulDataLoader + """ + if message_transform is None: + message_transform = AlpacaToMessages() + + logger.info(f"Loading SFT dataset from: {dataset_path}, split: {dataset_split}") + + dataset = sft_iterable_dataset( + model_transform=tokenizer, + message_transform=message_transform, + path=dataset_path, + split=dataset_split, + ) + + packer = TextPacker(padding_idx=padding_idx) + dataset = PackedDataset( + dataset=dataset, + packer=packer, + target_tokens_per_pack=target_tokens_per_pack, + ) + + dataloader = StatefulDataLoader( + dataset=dataset, + batch_size=batch_size, + collate_fn=partial( + collate_packed, mask_fn=packer.create_block_mask, device=device + ), + ) + + logger.info( + f"Created dataloader with batch_size={batch_size}, target_tokens={target_tokens_per_pack}" + ) + + return dataloader + + +def create_context_parallel_context( + parallel_dims: ParallelDims, + inputs: torch.Tensor, + labels: torch.Tensor, + model_parts: list, + rotate_method: str, +): + """ + Create context parallel context for distributed training. + + Args: + parallel_dims: Parallel dimensions configuration + inputs: Input tensor + labels: Label tensor + model_parts: List of model parts + rotate_method: Context parallel rotation method + + Returns: + Context parallel context or None if CP is not enabled + """ + if not parallel_dims.cp_enabled: + return None + + return dist_utils.create_context_parallel_ctx( + cp_mesh=parallel_dims.world_mesh["cp"], + cp_buffers=[inputs, labels] + [m.freqs_cis for m in model_parts], + cp_seq_dims=[1, 1] + [0 for _ in model_parts], + cp_no_restore_buffers={inputs, labels}, + cp_rotate_method=rotate_method, + ) + + +def move_batch_to_device(batch: dict[str, Any], device: torch.device) -> dict[str, Any]: + """ + Move batch tensors to the specified device. + + Args: + batch: Dictionary containing batch data + device: Target device + + Returns: + Batch with tensors moved to device + """ + for key, value in batch.items(): + if isinstance(value, torch.Tensor): + batch[key] = value.to(device) + return batch + + +def log_training_step( + step: int, + total_steps: int, + loss: torch.Tensor, + logger: logging.Logger, +): + """ + Log training step information. + + Args: + step: Current training step + total_steps: Total number of training steps + loss: Current loss value + logger: Logger instance + """ + logger.info(f"Step {step}/{total_steps} | Loss: {loss.item():.4f}")