Remove sandbox config and reference apps/grpo configs instead

Changes:
- Removed sandbox/grpo_language/qwen3_1_7b.yaml (use configs from apps/grpo/)
- Updated usage comment in main.py to reference apps/grpo/qwen3_1_7b.yaml
- Updated README.md to reference apps/grpo/ configs
- Fixed README.md to use <思考> tags instead of <think> tags

Author: casteryh

sandbox/grpo_language/README.md

@@ -34,9 +34,11 @@ pip install langid
 ## Usage
 
 ```bash
-python -m sandbox.grpo_language.main --config sandbox/grpo_language/qwen3_1_7b.yaml
+python -m sandbox.grpo_language.main --config apps/grpo/qwen3_1_7b.yaml
 ```
 
+You can use any of the config files from `apps/grpo/` (e.g., `qwen3_1_7b.yaml`, `qwen3_8b.yaml`, `qwen3_32b.yaml`).
+
 ## How It Works
 
 1. The model receives a math problem and is instructed to use `<思考>` tags for reasoning
@@ -70,7 +72,7 @@ To use a different language:
 
 Over the course of training, the model should learn to:
 1. Solve math problems correctly
-2. Use `<think></think>` tags for its reasoning
+2. Use `<思考></思考>` tags for its reasoning
 3. Write its thinking in Japanese (or the configured target language)
 
 ## Metrics

sandbox/grpo_language/main.py

@@ -4,7 +4,7 @@
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
 
-# Usage: python -m sandbox.grpo_language.main --config sandbox/grpo_language/qwen3_1_7b.yaml
+# Usage: python -m sandbox.grpo_language.main --config apps/grpo/qwen3_1_7b.yaml
 
 import asyncio
 import time