diff --git a/assets/answer_flow.jpg b/assets/answer_flow.jpg index c0072f185..a24437dd0 100644 Binary files a/assets/answer_flow.jpg and b/assets/answer_flow.jpg differ diff --git a/assets/distillation.jpg b/assets/distillation.jpg index 25661347d..6637d48c4 100644 Binary files a/assets/distillation.jpg and b/assets/distillation.jpg differ diff --git a/assets/training_pipeline_details.jpg b/assets/training_pipeline_details.jpg index 5ffe448a9..fc4d687e6 100644 Binary files a/assets/training_pipeline_details.jpg and b/assets/training_pipeline_details.jpg differ diff --git a/examples/NERDiffgram/step_2_AI_populate_data.ipynb b/examples/NERDiffgram/step_2_AI_populate_data.ipynb new file mode 100644 index 000000000..ea1b45675 --- /dev/null +++ b/examples/NERDiffgram/step_2_AI_populate_data.ipynb @@ -0,0 +1,591 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": null, + "id": "c519a5b8-6dc3-4277-8c91-d725604a0cdc", + "metadata": {}, + "outputs": [], + "source": [ + "!pip install boto3\n", + "!pip install torch transformers diffgram neo4j anthropic pandas tqdm\n", + "!pip install llama_index" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "id": "5d5ac541-5a2f-4a45-a266-9f4954f28714", + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/usr/local/lib/python3.11/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 torch\n", + "from transformers import BertTokenizerFast, BertForTokenClassification\n", + "from torch.utils.data import Dataset, DataLoader\n", + "import pandas as pd\n", + "from diffgram import Project\n", + "from typing import List, Dict, Optional\n", + "import anthropic\n", + "import json\n", + "from neo4j import GraphDatabase\n", + "from tqdm import tqdm\n", + "import logging\n", + "import os\n", + "import sys\n", + "import boto3\n", + "import requests\n", + "import pprint" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "id": "40f6eab4-0661-4ede-adc3-58fb0d579ed7", + "metadata": {}, + "outputs": [], + "source": [ + "# Use os.getcwd() since __file__ is not available in interactive environments\n", + "current_dir = os.getcwd()\n", + "\n", + "# If your structure is such that the package is in the parent directory, compute the parent directory:\n", + "parent_dir = os.path.abspath(os.path.join(current_dir, '..'))\n", + "\n", + "# Add the parent directory to sys.path if it's not already there\n", + "if parent_dir not in sys.path:\n", + " sys.path.insert(0, parent_dir)" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "54c7996d-cdd6-4d20-ab07-ef537ecf9180", + "metadata": {}, + "outputs": [], + "source": [ + "from AgenticWorkflow.bedrock_session import get_boto_session" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "9720aa06-77df-4234-ad5b-b6aae2cc154c", + "metadata": {}, + "outputs": [], + "source": [ + "session = get_boto_session()" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "id": "e9efc16a-7e28-42e8-bd00-d3906c1657b2", + "metadata": {}, + "outputs": [], + "source": [ + "bedrock_runtime = session.client(\"bedrock-runtime\", region_name=\"us-east-1\")" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "id": "73a5036b-4530-40b2-aa91-bff59cc5cee8", + "metadata": {}, + "outputs": [], + "source": [ + "def get_claudia_kwargs(prompt):\n", + " kwargs = {\n", + " \"modelId\": \"anthropic.claude-3-5-sonnet-20240620-v1:0\",\n", + " \"contentType\": \"application/json\",\n", + " \"accept\": \"application/json\",\n", + " \"body\": json.dumps({\n", + " \"anthropic_version\": \"bedrock-2023-05-31\",\n", + " \"max_tokens\": 10000,\n", + " \"messages\": [\n", + " {\n", + " \"role\": \"user\",\n", + " \"content\": [\n", + " {\n", + " \"type\": \"text\",\n", + " \"text\": prompt\n", + " }\n", + " ]\n", + " }\n", + " ]\n", + " })\n", + " }\n", + " return kwargs" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "id": "3a0701ed-16a4-4cc3-b71a-31ae142157d9", + "metadata": {}, + "outputs": [], + "source": [ + "prompt = \"Does this work?\"" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "id": "40eba4e6-83c2-4b2e-8f57-81d9642042f4", + "metadata": {}, + "outputs": [], + "source": [ + "kwargs = get_claudia_kwargs(prompt)" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "id": "53479f1a-6e3d-465c-bb59-c1411e83c026", + "metadata": {}, + "outputs": [], + "source": [ + "def get_response(prompt):\n", + " kwargs = get_claudia_kwargs(prompt)\n", + " response = bedrock_runtime.invoke_model(**kwargs)\n", + " response_body = json.loads(response.get(\"body\").read())\n", + " return response_body['content'][0]['text']" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "id": "6c26526a-051a-4884-88ec-b973af4515d6", + "metadata": {}, + "outputs": [], + "source": [ + "response = get_response(prompt)" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "id": "ab54537f-dade-4ba1-b827-abf04f491019", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "'I apologize, but I don\\'t have any context about what you\\'re referring to when you ask \"Does this work?\" Without more information, I can\\'t determine if something works or not. If you have a specific question, problem, or task in mind, please provide more details so I can better assist you. What exactly are you trying to do or asking about?'" + ] + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "response" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "id": "e146627f-f1fc-4d65-badb-93287e074c28", + "metadata": {}, + "outputs": [], + "source": [ + "# Configuration\n", + "DIFFGRAM_CONFIG = {\n", + " \"host\": \"http://dispatcher:8085\",\n", + " \"project_string_id\": \"translucenttracker\",\n", + " \"client_id\": \"LIVE__u3v8q0m7tx1p851dp0ap\",\n", + " \"client_secret\": \"1qgd8as7xfcbuem6mw9j1z0xvjfmmvlagbugqr8z1g1ntypugr2ul24cce5k\"\n", + "}" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "id": "bf0a96a3-5083-461b-94e3-72c295c6bde5", + "metadata": {}, + "outputs": [], + "source": [ + "project = Project(host=DIFFGRAM_CONFIG[\"host\"],\n", + " project_string_id = \"translucenttracker\",\n", + " client_id = \"LIVE__u3v8q0m7tx1p851dp0ap\",\n", + " client_secret = \"1qgd8as7xfcbuem6mw9j1z0xvjfmmvlagbugqr8z1g1ntypugr2ul24cce5k\"\n", + " )\n", + "project_local = project" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "id": "5e96e5b7-43d6-46f8-9178-d0ad395eab91", + "metadata": {}, + "outputs": [], + "source": [ + "# Define constants\n", + "BATCH_SIZE = 32\n", + "MAX_LENGTH = 256\n", + "NUM_TRAIN_SAMPLES = 5440 # Number of samples to use for training\n", + "NUM_TRAINING_DATA = 5440\n", + "train_dataset_suffix = \"NER_train_batch_\"\n", + "test_dataset_suffix = \"NER_test_batch_\"\n", + "JOB_NAME = \"Law_NER_task1\"\n", + "JOB_TRAIN_SUFFIX = \"NER_train_JOB_\"\n", + "JOB_TEST_SUFFIX = \"NER_test_JOB_\"\n", + "MAX_NUM_OF_TASK = 250\n", + "NER_schema_name = 'ENTITY_TRAINING_SCHEMA'" + ] + }, + { + "cell_type": "markdown", + "id": "52a7eb45-358c-46b8-845d-8b24f52d323c", + "metadata": {}, + "source": [ + "## Import all the files \n", + "### make sure you have the diffgram_processing_v2 folder which has all the data arranged for NER task" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "id": "92689df2-b043-406a-b07a-6abe61e86a63", + "metadata": {}, + "outputs": [], + "source": [ + "from llama_index.core import SimpleDirectoryReader, StorageContext" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "id": "4bb5f37c-1ab5-4142-8607-8185cdf97d8a", + "metadata": {}, + "outputs": [], + "source": [ + "file_metadata = lambda x: {\"filename\": x}\n", + "diffgram_documents = SimpleDirectoryReader(\"diffgram_processing\",file_metadata=file_metadata).load_data()" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "id": "725190dc-bd0d-405b-82d2-503b00442a28", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "81611\n" + ] + } + ], + "source": [ + "print(len(diffgram_documents))" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "id": "bf0fdd85-ed40-4d26-a753-dbfcb2eb290d", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Chunk ID: Provincial Sales Tax Act-chunk-Tax if tangible personal property no longer for temporary use-0000\n", + "Act ID: Provincial Sales Tax Act\n", + "Regulation ID: None\n", + "Section Name: Tax if tangible personal property no longer for temporary use\n", + "Section ID: 51.1\n", + "Sequence ID: 0\n", + "Text:\n", + "1 this section applies to a person in relation to tangible personal property if a section 51 applied to the person in relation to the tangible personal property, and b within 3 years after the date on which the tangible personal property is first used in british columbia and during a calculation year in respect of which tax was payable under section 51, the person uses that property, or allows that property to be used, in british columbia for a purpose other than for temporary use. 2 a person to whom this section applies must pay to the government tax in an amount equal to the amount of tax under section 49 that would have otherwise been payable if that section had applied to the person in relation to the tangible personal property less the amount of tax paid by the person under section 51 in respect of the tangible personal property.\n" + ] + } + ], + "source": [ + "print(diffgram_documents[500].text)" + ] + }, + { + "cell_type": "markdown", + "id": "890247fc-effd-40d9-90c6-0fea4c191039", + "metadata": {}, + "source": [ + "## Diffgram utilities" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "id": "2eb6cb0f-4884-468a-b073-73fc66d59726", + "metadata": {}, + "outputs": [], + "source": [ + "def check_if_directory_exist(dir_name):\n", + " project = project_local.directory.get_directory_list(limit=50000)\n", + " for project_dir in project:\n", + " if (project_dir.__dict__['nickname'] == dir_name):\n", + " return project_dir\n", + " return None" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "id": "ad38eae0-8cac-4d0b-9b2b-f295d05121e9", + "metadata": {}, + "outputs": [], + "source": [ + "## You may need to run this twice to see if the directory is created\n", + "def create_diffgram_directory(dataset_name):\n", + " #directory = project_local.directory.get(name = dataset_name)\n", + " directory = check_if_directory_exist(dataset_name)\n", + " if (directory is None):\n", + " project_local.directory.new(name=dataset_name)\n", + " directory = check_if_directory_exist(dataset_name)\n", + " print(directory.__dict__) \n", + " return directory" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "id": "cd73b019-c012-4035-8275-65cbde52afba", + "metadata": {}, + "outputs": [], + "source": [ + "## check if file exist in the dir\n", + "def check_if_file_exist_in_dir(filename):\n", + " file = project_local.file.file_list_exists(filename)" + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "id": "734f5146-e911-4af4-bb3e-ce83b348f261", + "metadata": {}, + "outputs": [], + "source": [ + "def create_dataset_job(data_suffix, job_suffix, index, member_list_ids):\n", + " dataset_batch_name = data_suffix + str(index)\n", + " directory = create_diffgram_directory(dataset_batch_name)\n", + "\n", + " if directory is None:\n", + " print(f\"{dataset_batch_name} Directory does not exist\")\n", + " return\n", + "\n", + " job_name = job_suffix + str(index)\n", + "\n", + " job = project_local.job.new(\n", + " name = job_name,\n", + " instance_type = \"box\",\n", + " share = \"Project\",\n", + " sync_directories = [directory],\n", + " label_schema_id = schema_id,\n", + " tag_list = [\"Laws\", \"Acts\", \"Regulations\"],\n", + " members_list_ids = member_list_ids,\n", + " auto_launch = True\n", + " )\n", + " print(f\"The {job_name} task is created\")\n", + " return directory" + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "id": "5991441f-4cc6-4b29-a6f0-17127bfa347b", + "metadata": {}, + "outputs": [], + "source": [ + "def upload_files_to_dataset(index,batch_size, offset, directory):\n", + " for document in range((index+offset) * batch_size, ((index + offset) * batch_size) + batch_size):\n", + " filename = diffgram_documents[document].metadata['filename']\n", + " # check if the file exist in the diffgram directory\n", + " try:\n", + " file = project_local.file.from_local(filename,directory_id=directory.__dict__['id'])\n", + " except:\n", + " print(f\"File with {filename} exist in this directory. Continuing ....\")\n", + " continue;" + ] + }, + { + "cell_type": "markdown", + "id": "48fb3578-211d-43e6-8a7e-fe72c5696baa", + "metadata": {}, + "source": [ + "## get schmea id" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "id": "a7b66919-7417-4f73-bb63-09049594019a", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Existing Schemas in Diffgram:\n", + "[\n", + " {\n", + " \"archived\": false,\n", + " \"id\": 8,\n", + " \"is_default\": true,\n", + " \"member_created_id\": 1,\n", + " \"member_updated_id\": null,\n", + " \"name\": \"Default Schema\",\n", + " \"project_id\": 4,\n", + " \"time_created\": \"2025-02-04 22:16:17\",\n", + " \"time_updated\": null\n", + " },\n", + " {\n", + " \"archived\": false,\n", + " \"id\": 9,\n", + " \"is_default\": false,\n", + " \"member_created_id\": 10,\n", + " \"member_updated_id\": null,\n", + " \"name\": \"NER_TRAINING_SCHEMA\",\n", + " \"project_id\": 4,\n", + " \"time_created\": \"2025-02-05 17:08:24\",\n", + " \"time_updated\": null\n", + " },\n", + " {\n", + " \"archived\": false,\n", + " \"id\": 11,\n", + " \"is_default\": false,\n", + " \"member_created_id\": 10,\n", + " \"member_updated_id\": null,\n", + " \"name\": \"ENTITY_TRAINING_SCHEMA\",\n", + " \"project_id\": 4,\n", + " \"time_created\": \"2025-02-05 17:20:02\",\n", + " \"time_updated\": null\n", + " }\n", + "]\n", + "Schema 'ENTITY_TRAINING_SCHEMA' already exists with id: 11\n" + ] + } + ], + "source": [ + "schema_id = None\n", + "\n", + "# List the existing schemas in your Diffgram project.\n", + "schemas = project.schema.list()\n", + "print(\"Existing Schemas in Diffgram:\")\n", + "print(json.dumps(schemas, indent=2))\n", + "\n", + "# Check if a schema with the name NER_schema_name already exists.\n", + "for schema in schemas:\n", + " if schema.get('name') == NER_schema_name:\n", + " schema_id = schema.get('id')\n", + " break\n", + "\n", + "# If the schema does not exist, create a new one.\n", + "if schema_id is None:\n", + " print(f\"Schema '{NER_schema_name}' not found. Creating a new one...\")\n", + " json_response = project.new_schema(name=NER_schema_name)\n", + " schema_id = json_response.get(\"id\")\n", + " print(f\"Created new schema with id: {schema_id}\")\n", + "else:\n", + " print(f\"Schema '{NER_schema_name}' already exists with id: {schema_id}\")" + ] + }, + { + "cell_type": "markdown", + "id": "ee0c1ec0-3d8d-4c3a-b0ea-4bf7ed131e53", + "metadata": {}, + "source": [ + "## Uplaod the files" + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "id": "b82b43cd-5919-4139-a9b1-cd9eb1a78fe7", + "metadata": {}, + "outputs": [], + "source": [ + "import math \n", + "def create_datasets(diffgram_documents, num_training_data, batch_size, train_suffix, test_suffix, job_train_suffix, job_test_suffix):\n", + " #check if the lenght of all the data is equal to or more than num_training_data\n", + " if (len(diffgram_documents) < num_training_data):\n", + " print(f\"Not sufficient data for training {len(diffgram_documents)}\")\n", + " return\n", + " \n", + " train_batch_size = math.floor(num_training_data/batch_size)\n", + " test_batch_size = math.floor((num_training_data * (5 /100))/ batch_size)\n", + " #train_dataset_name = \"NER_train_batch_\"\n", + " \n", + " print(f\"The batch size of the training data is : {train_batch_size}\")\n", + " print(f\"The batch size of the test data is: {test_batch_size}\")\n", + " \n", + " member_list = project.get_member_list()\n", + " member_list_ids = [x['member_id'] for x in member_list]\n", + " \n", + " #schemas = project_local.schema.list()\n", + " train_batch_size = max(MAX_NUM_OF_TASK, train_batch_size)\n", + " test_batch_size = max(MAX_NUM_OF_TASK, test_batch_size)\n", + " \n", + " for index in range(66, train_batch_size):\n", + " directory = create_dataset_job(train_suffix, job_train_suffix, index, member_list_ids)\n", + " \n", + " print(f\"Creating / Uploading data to directory {directory.__dict__['nickname']}\")\n", + " upload_files_to_dataset(index,batch_size, 0, directory)\n", + " \n", + "# for index in range(0, test_batch_size):\n", + "# directory = create_dataset_job(test_suffix, job_test_suffix, index, member_list_ids)\n", + "# \n", + "# print(f\"Creating / Uploading data to directory {directory.__dict__['nickname']}\")\n", + "# upload_files_to_dataset(index,batch_size, train_batch_size+1, directory)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "bdbb5019-682a-45e2-937a-0eddad15ede6", + "metadata": {}, + "outputs": [], + "source": [ + "create_datasets(diffgram_documents[2112:], NUM_TRAINING_DATA, BATCH_SIZE, train_dataset_suffix, test_dataset_suffix, JOB_TRAIN_SUFFIX, JOB_TEST_SUFFIX)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "c0601d03-0651-4edf-837b-d1756037f5ea", + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.11.11" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/examples/NERDiffgram/step_2_AI_annotation.ipynb b/examples/NERDiffgram/step_3_AI_annotation.ipynb similarity index 100% rename from examples/NERDiffgram/step_2_AI_annotation.ipynb rename to examples/NERDiffgram/step_3_AI_annotation.ipynb diff --git a/examples/NERDiffgram/step_3_AI_annotate_incomplete.ipynb b/examples/NERDiffgram/step_4_AI_annotate_incomplete.ipynb similarity index 99% rename from examples/NERDiffgram/step_3_AI_annotate_incomplete.ipynb rename to examples/NERDiffgram/step_4_AI_annotate_incomplete.ipynb index d35bea198..27f791a3d 100644 --- a/examples/NERDiffgram/step_3_AI_annotate_incomplete.ipynb +++ b/examples/NERDiffgram/step_4_AI_annotate_incomplete.ipynb @@ -37,19 +37,10 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 1, "id": "d548875c-6194-47f4-b56e-8eff4a06ea7e", "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/usr/local/lib/python3.11/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" - ] - } - ], + "outputs": [], "source": [ "import torch\n", "from transformers import BertTokenizerFast, BertForTokenClassification\n", diff --git a/examples/NERDiffgram/step_4_AI_populate_data.ipynb b/examples/NERDiffgram/step_4_AI_populate_data.ipynb deleted file mode 100644 index 7422656d8..000000000 --- a/examples/NERDiffgram/step_4_AI_populate_data.ipynb +++ /dev/null @@ -1,1151 +0,0 @@ -{ - "cells": [ - { - "cell_type": "code", - "execution_count": null, - "id": "c519a5b8-6dc3-4277-8c91-d725604a0cdc", - "metadata": {}, - "outputs": [], - "source": [ - "!pip install boto3\n", - "!pip install torch transformers diffgram neo4j anthropic pandas tqdm\n", - "!pip install llama_index" - ] - }, - { - "cell_type": "code", - "execution_count": 1, - "id": "5d5ac541-5a2f-4a45-a266-9f4954f28714", - "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/usr/local/lib/python3.11/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 torch\n", - "from transformers import BertTokenizerFast, BertForTokenClassification\n", - "from torch.utils.data import Dataset, DataLoader\n", - "import pandas as pd\n", - "from diffgram import Project\n", - "from typing import List, Dict, Optional\n", - "import anthropic\n", - "import json\n", - "from neo4j import GraphDatabase\n", - "from tqdm import tqdm\n", - "import logging\n", - "import os\n", - "import sys\n", - "import boto3\n", - "import requests\n", - "import pprint" - ] - }, - { - "cell_type": "code", - "execution_count": 2, - "id": "40f6eab4-0661-4ede-adc3-58fb0d579ed7", - "metadata": {}, - "outputs": [], - "source": [ - "# Use os.getcwd() since __file__ is not available in interactive environments\n", - "current_dir = os.getcwd()\n", - "\n", - "# If your structure is such that the package is in the parent directory, compute the parent directory:\n", - "parent_dir = os.path.abspath(os.path.join(current_dir, '..'))\n", - "\n", - "# Add the parent directory to sys.path if it's not already there\n", - "if parent_dir not in sys.path:\n", - " sys.path.insert(0, parent_dir)" - ] - }, - { - "cell_type": "code", - "execution_count": 3, - "id": "54c7996d-cdd6-4d20-ab07-ef537ecf9180", - "metadata": {}, - "outputs": [], - "source": [ - "from AgenticWorkflow.bedrock_session import get_boto_session" - ] - }, - { - "cell_type": "code", - "execution_count": 4, - "id": "9720aa06-77df-4234-ad5b-b6aae2cc154c", - "metadata": {}, - "outputs": [], - "source": [ - "session = get_boto_session()" - ] - }, - { - "cell_type": "code", - "execution_count": 5, - "id": "e9efc16a-7e28-42e8-bd00-d3906c1657b2", - "metadata": {}, - "outputs": [], - "source": [ - "bedrock_runtime = session.client(\"bedrock-runtime\", region_name=\"us-east-1\")" - ] - }, - { - "cell_type": "code", - "execution_count": 6, - "id": "73a5036b-4530-40b2-aa91-bff59cc5cee8", - "metadata": {}, - "outputs": [], - "source": [ - "def get_claudia_kwargs(prompt):\n", - " kwargs = {\n", - " \"modelId\": \"anthropic.claude-3-5-sonnet-20240620-v1:0\",\n", - " \"contentType\": \"application/json\",\n", - " \"accept\": \"application/json\",\n", - " \"body\": json.dumps({\n", - " \"anthropic_version\": \"bedrock-2023-05-31\",\n", - " \"max_tokens\": 10000,\n", - " \"messages\": [\n", - " {\n", - " \"role\": \"user\",\n", - " \"content\": [\n", - " {\n", - " \"type\": \"text\",\n", - " \"text\": prompt\n", - " }\n", - " ]\n", - " }\n", - " ]\n", - " })\n", - " }\n", - " return kwargs" - ] - }, - { - "cell_type": "code", - "execution_count": 7, - "id": "3a0701ed-16a4-4cc3-b71a-31ae142157d9", - "metadata": {}, - "outputs": [], - "source": [ - "prompt = \"Does this work?\"" - ] - }, - { - "cell_type": "code", - "execution_count": 8, - "id": "40eba4e6-83c2-4b2e-8f57-81d9642042f4", - "metadata": {}, - "outputs": [], - "source": [ - "kwargs = get_claudia_kwargs(prompt)" - ] - }, - { - "cell_type": "code", - "execution_count": 9, - "id": "53479f1a-6e3d-465c-bb59-c1411e83c026", - "metadata": {}, - "outputs": [], - "source": [ - "def get_response(prompt):\n", - " kwargs = get_claudia_kwargs(prompt)\n", - " response = bedrock_runtime.invoke_model(**kwargs)\n", - " response_body = json.loads(response.get(\"body\").read())\n", - " return response_body['content'][0]['text']" - ] - }, - { - "cell_type": "code", - "execution_count": 10, - "id": "6c26526a-051a-4884-88ec-b973af4515d6", - "metadata": {}, - "outputs": [], - "source": [ - "response = get_response(prompt)" - ] - }, - { - "cell_type": "code", - "execution_count": 11, - "id": "ab54537f-dade-4ba1-b827-abf04f491019", - "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "'I apologize, but I don\\'t have any context about what you\\'re referring to when you ask \"Does this work?\" Without more information, I can\\'t determine if something works or not. If you have a specific question, problem, or task in mind, please provide more details so I can better assist you. What exactly are you trying to do or asking about?'" - ] - }, - "execution_count": 11, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "response" - ] - }, - { - "cell_type": "code", - "execution_count": 12, - "id": "e146627f-f1fc-4d65-badb-93287e074c28", - "metadata": {}, - "outputs": [], - "source": [ - "# Configuration\n", - "DIFFGRAM_CONFIG = {\n", - " \"host\": \"http://dispatcher:8085\",\n", - " \"project_string_id\": \"translucenttracker\",\n", - " \"client_id\": \"LIVE__u3v8q0m7tx1p851dp0ap\",\n", - " \"client_secret\": \"1qgd8as7xfcbuem6mw9j1z0xvjfmmvlagbugqr8z1g1ntypugr2ul24cce5k\"\n", - "}" - ] - }, - { - "cell_type": "code", - "execution_count": 13, - "id": "bf0a96a3-5083-461b-94e3-72c295c6bde5", - "metadata": {}, - "outputs": [], - "source": [ - "project = Project(host=DIFFGRAM_CONFIG[\"host\"],\n", - " project_string_id = \"translucenttracker\",\n", - " client_id = \"LIVE__u3v8q0m7tx1p851dp0ap\",\n", - " client_secret = \"1qgd8as7xfcbuem6mw9j1z0xvjfmmvlagbugqr8z1g1ntypugr2ul24cce5k\"\n", - " )\n", - "project_local = project" - ] - }, - { - "cell_type": "code", - "execution_count": 15, - "id": "5e96e5b7-43d6-46f8-9178-d0ad395eab91", - "metadata": {}, - "outputs": [], - "source": [ - "# Define constants\n", - "BATCH_SIZE = 32\n", - "MAX_LENGTH = 256\n", - "NUM_TRAIN_SAMPLES = 5440 # Number of samples to use for training\n", - "NUM_TRAINING_DATA = 5440\n", - "train_dataset_suffix = \"NER_train_batch_\"\n", - "test_dataset_suffix = \"NER_test_batch_\"\n", - "JOB_NAME = \"Law_NER_task1\"\n", - "JOB_TRAIN_SUFFIX = \"NER_train_JOB_\"\n", - "JOB_TEST_SUFFIX = \"NER_test_JOB_\"\n", - "MAX_NUM_OF_TASK = 250\n", - "NER_schema_name = 'ENTITY_TRAINING_SCHEMA'" - ] - }, - { - "cell_type": "markdown", - "id": "52a7eb45-358c-46b8-845d-8b24f52d323c", - "metadata": {}, - "source": [ - "## Import all the files \n", - "### make sure you have the diffgram_processing_v2 folder which has all the data arranged for NER task" - ] - }, - { - "cell_type": "code", - "execution_count": 16, - "id": "92689df2-b043-406a-b07a-6abe61e86a63", - "metadata": {}, - "outputs": [], - "source": [ - "from llama_index.core import SimpleDirectoryReader, StorageContext" - ] - }, - { - "cell_type": "code", - "execution_count": 17, - "id": "4bb5f37c-1ab5-4142-8607-8185cdf97d8a", - "metadata": {}, - "outputs": [], - "source": [ - "file_metadata = lambda x: {\"filename\": x}\n", - "diffgram_documents = SimpleDirectoryReader(\"diffgram_processing\",file_metadata=file_metadata).load_data()" - ] - }, - { - "cell_type": "code", - "execution_count": 18, - "id": "725190dc-bd0d-405b-82d2-503b00442a28", - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "81611\n" - ] - } - ], - "source": [ - "print(len(diffgram_documents))" - ] - }, - { - "cell_type": "code", - "execution_count": 19, - "id": "bf0fdd85-ed40-4d26-a753-dbfcb2eb290d", - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Chunk ID: Provincial Sales Tax Act-chunk-Tax if tangible personal property no longer for temporary use-0000\n", - "Act ID: Provincial Sales Tax Act\n", - "Regulation ID: None\n", - "Section Name: Tax if tangible personal property no longer for temporary use\n", - "Section ID: 51.1\n", - "Sequence ID: 0\n", - "Text:\n", - "1 this section applies to a person in relation to tangible personal property if a section 51 applied to the person in relation to the tangible personal property, and b within 3 years after the date on which the tangible personal property is first used in british columbia and during a calculation year in respect of which tax was payable under section 51, the person uses that property, or allows that property to be used, in british columbia for a purpose other than for temporary use. 2 a person to whom this section applies must pay to the government tax in an amount equal to the amount of tax under section 49 that would have otherwise been payable if that section had applied to the person in relation to the tangible personal property less the amount of tax paid by the person under section 51 in respect of the tangible personal property.\n" - ] - } - ], - "source": [ - "print(diffgram_documents[500].text)" - ] - }, - { - "cell_type": "markdown", - "id": "890247fc-effd-40d9-90c6-0fea4c191039", - "metadata": {}, - "source": [ - "## Diffgram utilities" - ] - }, - { - "cell_type": "code", - "execution_count": 20, - "id": "2eb6cb0f-4884-468a-b073-73fc66d59726", - "metadata": {}, - "outputs": [], - "source": [ - "def check_if_directory_exist(dir_name):\n", - " project = project_local.directory.get_directory_list(limit=50000)\n", - " for project_dir in project:\n", - " if (project_dir.__dict__['nickname'] == dir_name):\n", - " return project_dir\n", - " return None" - ] - }, - { - "cell_type": "code", - "execution_count": 21, - "id": "ad38eae0-8cac-4d0b-9b2b-f295d05121e9", - "metadata": {}, - "outputs": [], - "source": [ - "## You may need to run this twice to see if the directory is created\n", - "def create_diffgram_directory(dataset_name):\n", - " #directory = project_local.directory.get(name = dataset_name)\n", - " directory = check_if_directory_exist(dataset_name)\n", - " if (directory is None):\n", - " project_local.directory.new(name=dataset_name)\n", - " directory = check_if_directory_exist(dataset_name)\n", - " print(directory.__dict__) \n", - " return directory" - ] - }, - { - "cell_type": "code", - "execution_count": 22, - "id": "cd73b019-c012-4035-8275-65cbde52afba", - "metadata": {}, - "outputs": [], - "source": [ - "## check if file exist in the dir\n", - "def check_if_file_exist_in_dir(filename):\n", - " file = project_local.file.file_list_exists(filename)" - ] - }, - { - "cell_type": "code", - "execution_count": 23, - "id": "734f5146-e911-4af4-bb3e-ce83b348f261", - "metadata": {}, - "outputs": [], - "source": [ - "def create_dataset_job(data_suffix, job_suffix, index, member_list_ids):\n", - " dataset_batch_name = data_suffix + str(index)\n", - " directory = create_diffgram_directory(dataset_batch_name)\n", - "\n", - " if directory is None:\n", - " print(f\"{dataset_batch_name} Directory does not exist\")\n", - " return\n", - "\n", - " job_name = job_suffix + str(index)\n", - "\n", - " job = project_local.job.new(\n", - " name = job_name,\n", - " instance_type = \"box\",\n", - " share = \"Project\",\n", - " sync_directories = [directory],\n", - " label_schema_id = schema_id,\n", - " tag_list = [\"Laws\", \"Acts\", \"Regulations\"],\n", - " members_list_ids = member_list_ids,\n", - " auto_launch = True\n", - " )\n", - " print(f\"The {job_name} task is created\")\n", - " return directory" - ] - }, - { - "cell_type": "code", - "execution_count": 24, - "id": "5991441f-4cc6-4b29-a6f0-17127bfa347b", - "metadata": {}, - "outputs": [], - "source": [ - "def upload_files_to_dataset(index,batch_size, offset, directory):\n", - " for document in range((index+offset) * batch_size, ((index + offset) * batch_size) + batch_size):\n", - " filename = diffgram_documents[document].metadata['filename']\n", - " # check if the file exist in the diffgram directory\n", - " try:\n", - " file = project_local.file.from_local(filename,directory_id=directory.__dict__['id'])\n", - " except:\n", - " print(f\"File with {filename} exist in this directory. Continuing ....\")\n", - " continue;" - ] - }, - { - "cell_type": "markdown", - "id": "48fb3578-211d-43e6-8a7e-fe72c5696baa", - "metadata": {}, - "source": [ - "## get schmea id" - ] - }, - { - "cell_type": "code", - "execution_count": 25, - "id": "a7b66919-7417-4f73-bb63-09049594019a", - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Existing Schemas in Diffgram:\n", - "[\n", - " {\n", - " \"archived\": false,\n", - " \"id\": 8,\n", - " \"is_default\": true,\n", - " \"member_created_id\": 1,\n", - " \"member_updated_id\": null,\n", - " \"name\": \"Default Schema\",\n", - " \"project_id\": 4,\n", - " \"time_created\": \"2025-02-04 22:16:17\",\n", - " \"time_updated\": null\n", - " },\n", - " {\n", - " \"archived\": false,\n", - " \"id\": 9,\n", - " \"is_default\": false,\n", - " \"member_created_id\": 10,\n", - " \"member_updated_id\": null,\n", - " \"name\": \"NER_TRAINING_SCHEMA\",\n", - " \"project_id\": 4,\n", - " \"time_created\": \"2025-02-05 17:08:24\",\n", - " \"time_updated\": null\n", - " },\n", - " {\n", - " \"archived\": false,\n", - " \"id\": 11,\n", - " \"is_default\": false,\n", - " \"member_created_id\": 10,\n", - " \"member_updated_id\": null,\n", - " \"name\": \"ENTITY_TRAINING_SCHEMA\",\n", - " \"project_id\": 4,\n", - " \"time_created\": \"2025-02-05 17:20:02\",\n", - " \"time_updated\": null\n", - " }\n", - "]\n", - "Schema 'ENTITY_TRAINING_SCHEMA' already exists with id: 11\n" - ] - } - ], - "source": [ - "schema_id = None\n", - "\n", - "# List the existing schemas in your Diffgram project.\n", - "schemas = project.schema.list()\n", - "print(\"Existing Schemas in Diffgram:\")\n", - "print(json.dumps(schemas, indent=2))\n", - "\n", - "# Check if a schema with the name NER_schema_name already exists.\n", - "for schema in schemas:\n", - " if schema.get('name') == NER_schema_name:\n", - " schema_id = schema.get('id')\n", - " break\n", - "\n", - "# If the schema does not exist, create a new one.\n", - "if schema_id is None:\n", - " print(f\"Schema '{NER_schema_name}' not found. Creating a new one...\")\n", - " json_response = project.new_schema(name=NER_schema_name)\n", - " schema_id = json_response.get(\"id\")\n", - " print(f\"Created new schema with id: {schema_id}\")\n", - "else:\n", - " print(f\"Schema '{NER_schema_name}' already exists with id: {schema_id}\")" - ] - }, - { - "cell_type": "markdown", - "id": "ee0c1ec0-3d8d-4c3a-b0ea-4bf7ed131e53", - "metadata": {}, - "source": [ - "## Uplaod the files" - ] - }, - { - "cell_type": "code", - "execution_count": 27, - "id": "b82b43cd-5919-4139-a9b1-cd9eb1a78fe7", - "metadata": {}, - "outputs": [], - "source": [ - "import math \n", - "def create_datasets(diffgram_documents, num_training_data, batch_size, train_suffix, test_suffix, job_train_suffix, job_test_suffix):\n", - " #check if the lenght of all the data is equal to or more than num_training_data\n", - " if (len(diffgram_documents) < num_training_data):\n", - " print(f\"Not sufficient data for training {len(diffgram_documents)}\")\n", - " return\n", - " \n", - " train_batch_size = math.floor(num_training_data/batch_size)\n", - " test_batch_size = math.floor((num_training_data * (5 /100))/ batch_size)\n", - " #train_dataset_name = \"NER_train_batch_\"\n", - " \n", - " print(f\"The batch size of the training data is : {train_batch_size}\")\n", - " print(f\"The batch size of the test data is: {test_batch_size}\")\n", - " \n", - " member_list = project.get_member_list()\n", - " member_list_ids = [x['member_id'] for x in member_list]\n", - " \n", - " #schemas = project_local.schema.list()\n", - " train_batch_size = max(MAX_NUM_OF_TASK, train_batch_size)\n", - " test_batch_size = max(MAX_NUM_OF_TASK, test_batch_size)\n", - " \n", - " for index in range(66, train_batch_size):\n", - " directory = create_dataset_job(train_suffix, job_train_suffix, index, member_list_ids)\n", - " \n", - " print(f\"Creating / Uploading data to directory {directory.__dict__['nickname']}\")\n", - " upload_files_to_dataset(index,batch_size, 0, directory)\n", - " \n", - "# for index in range(0, test_batch_size):\n", - "# directory = create_dataset_job(test_suffix, job_test_suffix, index, member_list_ids)\n", - "# \n", - "# print(f\"Creating / Uploading data to directory {directory.__dict__['nickname']}\")\n", - "# upload_files_to_dataset(index,batch_size, train_batch_size+1, directory)" - ] - }, - { - "cell_type": "code", - "execution_count": 28, - "id": "bdbb5019-682a-45e2-937a-0eddad15ede6", - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "The batch size of the training data is : 170\n", - "The batch size of the test data is: 8\n", - "The NER_train_JOB_66 task is created\n", - "Creating / Uploading data to directory NER_train_batch_66\n", - "{'client': , 'id': 332, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 332, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_67', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:27:13.880710', 'directory_id': 332, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_67 task is created\n", - "Creating / Uploading data to directory NER_train_batch_67\n", - "{'client': , 'id': 334, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 334, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_68', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:27:31.327612', 'directory_id': 334, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_68 task is created\n", - "Creating / Uploading data to directory NER_train_batch_68\n", - "{'client': , 'id': 336, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 336, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_69', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:27:47.371096', 'directory_id': 336, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_69 task is created\n", - "Creating / Uploading data to directory NER_train_batch_69\n", - "{'client': , 'id': 338, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 338, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_70', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:28:03.001664', 'directory_id': 338, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_70 task is created\n", - "Creating / Uploading data to directory NER_train_batch_70\n", - "{'client': , 'id': 340, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 340, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_71', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:28:18.837509', 'directory_id': 340, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_71 task is created\n", - "Creating / Uploading data to directory NER_train_batch_71\n", - "{'client': , 'id': 342, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 342, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_72', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:28:34.529592', 'directory_id': 342, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_72 task is created\n", - "Creating / Uploading data to directory NER_train_batch_72\n", - "{'client': , 'id': 344, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 344, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_73', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:28:50.725575', 'directory_id': 344, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_73 task is created\n", - "Creating / Uploading data to directory NER_train_batch_73\n", - "{'client': , 'id': 346, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 346, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_74', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:29:06.686954', 'directory_id': 346, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_74 task is created\n", - "Creating / Uploading data to directory NER_train_batch_74\n", - "{'client': , 'id': 348, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 348, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_75', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:29:23.577772', 'directory_id': 348, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_75 task is created\n", - "Creating / Uploading data to directory NER_train_batch_75\n", - "{'client': , 'id': 350, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 350, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_76', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:29:39.879249', 'directory_id': 350, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_76 task is created\n", - "Creating / Uploading data to directory NER_train_batch_76\n", - "{'client': , 'id': 352, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 352, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_77', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:29:58.237238', 'directory_id': 352, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_77 task is created\n", - "Creating / Uploading data to directory NER_train_batch_77\n", - "{'client': , 'id': 354, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 354, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_78', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:30:15.983067', 'directory_id': 354, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_78 task is created\n", - "Creating / Uploading data to directory NER_train_batch_78\n", - "{'client': , 'id': 356, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 356, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_79', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:30:34.150755', 'directory_id': 356, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_79 task is created\n", - "Creating / Uploading data to directory NER_train_batch_79\n", - "{'client': , 'id': 358, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 358, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_80', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:30:51.512098', 'directory_id': 358, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_80 task is created\n", - "Creating / Uploading data to directory NER_train_batch_80\n", - "{'client': , 'id': 360, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 360, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_81', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:31:09.959313', 'directory_id': 360, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_81 task is created\n", - "Creating / Uploading data to directory NER_train_batch_81\n", - "{'client': , 'id': 362, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 362, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_82', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:31:27.961441', 'directory_id': 362, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_82 task is created\n", - "Creating / Uploading data to directory NER_train_batch_82\n", - "{'client': , 'id': 364, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 364, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_83', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:31:44.307284', 'directory_id': 364, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_83 task is created\n", - "Creating / Uploading data to directory NER_train_batch_83\n", - "{'client': , 'id': 366, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 366, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_84', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:31:59.846358', 'directory_id': 366, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_84 task is created\n", - "Creating / Uploading data to directory NER_train_batch_84\n", - "{'client': , 'id': 368, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 368, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_85', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:32:15.013380', 'directory_id': 368, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_85 task is created\n", - "Creating / Uploading data to directory NER_train_batch_85\n", - "{'client': , 'id': 370, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 370, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_86', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:32:30.702676', 'directory_id': 370, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_86 task is created\n", - "Creating / Uploading data to directory NER_train_batch_86\n", - "{'client': , 'id': 372, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 372, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_87', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:32:46.174752', 'directory_id': 372, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_87 task is created\n", - "Creating / Uploading data to directory NER_train_batch_87\n", - "{'client': , 'id': 374, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 374, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_88', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:33:01.639252', 'directory_id': 374, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_88 task is created\n", - "Creating / Uploading data to directory NER_train_batch_88\n", - "{'client': , 'id': 376, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 376, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_89', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:33:17.369725', 'directory_id': 376, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_89 task is created\n", - "Creating / Uploading data to directory NER_train_batch_89\n", - "{'client': , 'id': 378, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 378, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_90', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:33:33.492912', 'directory_id': 378, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_90 task is created\n", - "Creating / Uploading data to directory NER_train_batch_90\n", - "{'client': , 'id': 380, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 380, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_91', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:33:49.675187', 'directory_id': 380, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_91 task is created\n", - "Creating / Uploading data to directory NER_train_batch_91\n", - "{'client': , 'id': 382, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 382, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_92', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:34:05.708357', 'directory_id': 382, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_92 task is created\n", - "Creating / Uploading data to directory NER_train_batch_92\n", - "{'client': , 'id': 384, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 384, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_93', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:34:21.575114', 'directory_id': 384, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_93 task is created\n", - "Creating / Uploading data to directory NER_train_batch_93\n", - "{'client': , 'id': 386, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 386, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_94', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:34:37.635371', 'directory_id': 386, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_94 task is created\n", - "Creating / Uploading data to directory NER_train_batch_94\n", - "{'client': , 'id': 388, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 388, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_95', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:34:53.246378', 'directory_id': 388, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_95 task is created\n", - "Creating / Uploading data to directory NER_train_batch_95\n", - "{'client': , 'id': 390, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 390, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_96', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:35:09.609952', 'directory_id': 390, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_96 task is created\n", - "Creating / Uploading data to directory NER_train_batch_96\n", - "{'client': , 'id': 392, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 392, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_97', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:35:25.636125', 'directory_id': 392, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_97 task is created\n", - "Creating / Uploading data to directory NER_train_batch_97\n", - "{'client': , 'id': 394, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 394, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_98', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:35:42.126879', 'directory_id': 394, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_98 task is created\n", - "Creating / Uploading data to directory NER_train_batch_98\n", - "{'client': , 'id': 396, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 396, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_99', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:35:58.108409', 'directory_id': 396, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_99 task is created\n", - "Creating / Uploading data to directory NER_train_batch_99\n", - "{'client': , 'id': 398, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 398, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_100', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:36:14.578760', 'directory_id': 398, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_100 task is created\n", - "Creating / Uploading data to directory NER_train_batch_100\n", - "{'client': , 'id': 400, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 400, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_101', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:36:30.551570', 'directory_id': 400, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_101 task is created\n", - "Creating / Uploading data to directory NER_train_batch_101\n", - "{'client': , 'id': 402, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 402, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_102', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:36:47.079982', 'directory_id': 402, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_102 task is created\n", - "Creating / Uploading data to directory NER_train_batch_102\n", - "{'client': , 'id': 404, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 404, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_103', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:37:03.328785', 'directory_id': 404, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_103 task is created\n", - "Creating / Uploading data to directory NER_train_batch_103\n", - "{'client': , 'id': 406, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 406, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_104', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:37:20.054769', 'directory_id': 406, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_104 task is created\n", - "Creating / Uploading data to directory NER_train_batch_104\n", - "{'client': , 'id': 408, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 408, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_105', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:37:36.246422', 'directory_id': 408, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_105 task is created\n", - "Creating / Uploading data to directory NER_train_batch_105\n", - "{'client': , 'id': 410, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 410, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_106', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:37:52.855247', 'directory_id': 410, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_106 task is created\n", - "Creating / Uploading data to directory NER_train_batch_106\n", - "{'client': , 'id': 412, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 412, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_107', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:38:09.332204', 'directory_id': 412, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_107 task is created\n", - "Creating / Uploading data to directory NER_train_batch_107\n", - "{'client': , 'id': 414, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 414, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_108', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:38:25.948199', 'directory_id': 414, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_108 task is created\n", - "Creating / Uploading data to directory NER_train_batch_108\n", - "{'client': , 'id': 416, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 416, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_109', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:38:42.767002', 'directory_id': 416, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_109 task is created\n", - "Creating / Uploading data to directory NER_train_batch_109\n", - "{'client': , 'id': 418, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 418, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_110', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:38:59.641709', 'directory_id': 418, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_110 task is created\n", - "Creating / Uploading data to directory NER_train_batch_110\n", - "{'client': , 'id': 420, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 420, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_111', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:39:16.241102', 'directory_id': 420, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_111 task is created\n", - "Creating / Uploading data to directory NER_train_batch_111\n", - "{'client': , 'id': 422, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 422, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_112', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:39:33.036815', 'directory_id': 422, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_112 task is created\n", - "Creating / Uploading data to directory NER_train_batch_112\n", - "{'client': , 'id': 424, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 424, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_113', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:39:49.801682', 'directory_id': 424, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_113 task is created\n", - "Creating / Uploading data to directory NER_train_batch_113\n", - "{'client': , 'id': 426, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 426, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_114', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:40:06.658549', 'directory_id': 426, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_114 task is created\n", - "Creating / Uploading data to directory NER_train_batch_114\n", - "{'client': , 'id': 428, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 428, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_115', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:40:23.624694', 'directory_id': 428, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_115 task is created\n", - "Creating / Uploading data to directory NER_train_batch_115\n", - "{'client': , 'id': 430, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 430, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_116', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:40:40.942859', 'directory_id': 430, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_116 task is created\n", - "Creating / Uploading data to directory NER_train_batch_116\n", - "{'client': , 'id': 432, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 432, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_117', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:40:57.950194', 'directory_id': 432, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_117 task is created\n", - "Creating / Uploading data to directory NER_train_batch_117\n", - "{'client': , 'id': 434, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 434, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_118', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:41:15.074779', 'directory_id': 434, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_118 task is created\n", - "Creating / Uploading data to directory NER_train_batch_118\n", - "{'client': , 'id': 436, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 436, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_119', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:41:32.135143', 'directory_id': 436, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_119 task is created\n", - "Creating / Uploading data to directory NER_train_batch_119\n", - "{'client': , 'id': 438, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 438, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_120', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:41:49.656602', 'directory_id': 438, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_120 task is created\n", - "Creating / Uploading data to directory NER_train_batch_120\n", - "{'client': , 'id': 440, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 440, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_121', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:42:06.766857', 'directory_id': 440, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_121 task is created\n", - "Creating / Uploading data to directory NER_train_batch_121\n", - "{'client': , 'id': 442, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 442, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_122', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:42:24.141966', 'directory_id': 442, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_122 task is created\n", - "Creating / Uploading data to directory NER_train_batch_122\n", - "{'client': , 'id': 444, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 444, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_123', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:42:41.386362', 'directory_id': 444, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_123 task is created\n", - "Creating / Uploading data to directory NER_train_batch_123\n", - "{'client': , 'id': 446, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 446, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_124', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:42:59.015229', 'directory_id': 446, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_124 task is created\n", - "Creating / Uploading data to directory NER_train_batch_124\n", - "{'client': , 'id': 448, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 448, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_125', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:43:16.836735', 'directory_id': 448, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_125 task is created\n", - "Creating / Uploading data to directory NER_train_batch_125\n", - "{'client': , 'id': 450, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 450, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_126', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:43:34.184904', 'directory_id': 450, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_126 task is created\n", - "Creating / Uploading data to directory NER_train_batch_126\n", - "{'client': , 'id': 452, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 452, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_127', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:43:52.231768', 'directory_id': 452, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_127 task is created\n", - "Creating / Uploading data to directory NER_train_batch_127\n", - "{'client': , 'id': 454, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 454, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_128', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:44:10.067219', 'directory_id': 454, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_128 task is created\n", - "Creating / Uploading data to directory NER_train_batch_128\n", - "{'client': , 'id': 456, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 456, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_129', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:44:27.834376', 'directory_id': 456, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_129 task is created\n", - "Creating / Uploading data to directory NER_train_batch_129\n", - "{'client': , 'id': 458, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 458, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_130', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:44:45.677979', 'directory_id': 458, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_130 task is created\n", - "Creating / Uploading data to directory NER_train_batch_130\n", - "{'client': , 'id': 460, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 460, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_131', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:45:03.622109', 'directory_id': 460, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_131 task is created\n", - "Creating / Uploading data to directory NER_train_batch_131\n", - "{'client': , 'id': 462, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 462, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_132', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:45:21.552941', 'directory_id': 462, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_132 task is created\n", - "Creating / Uploading data to directory NER_train_batch_132\n", - "{'client': , 'id': 464, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 464, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_133', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:45:39.438064', 'directory_id': 464, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_133 task is created\n", - "Creating / Uploading data to directory NER_train_batch_133\n", - "{'client': , 'id': 466, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 466, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_134', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:45:57.475929', 'directory_id': 466, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_134 task is created\n", - "Creating / Uploading data to directory NER_train_batch_134\n", - "{'client': , 'id': 468, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 468, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_135', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:46:15.801261', 'directory_id': 468, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_135 task is created\n", - "Creating / Uploading data to directory NER_train_batch_135\n", - "{'client': , 'id': 470, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 470, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_136', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:46:34.070177', 'directory_id': 470, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_136 task is created\n", - "Creating / Uploading data to directory NER_train_batch_136\n", - "{'client': , 'id': 472, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 472, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_137', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:46:51.983592', 'directory_id': 472, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_137 task is created\n", - "Creating / Uploading data to directory NER_train_batch_137\n", - "{'client': , 'id': 474, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 474, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_138', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:47:10.391757', 'directory_id': 474, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_138 task is created\n", - "Creating / Uploading data to directory NER_train_batch_138\n", - "{'client': , 'id': 476, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 476, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_139', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:47:28.601715', 'directory_id': 476, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_139 task is created\n", - "Creating / Uploading data to directory NER_train_batch_139\n", - "{'client': , 'id': 478, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 478, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_140', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:47:47.188887', 'directory_id': 478, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_140 task is created\n", - "Creating / Uploading data to directory NER_train_batch_140\n", - "{'client': , 'id': 480, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 480, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_141', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:48:05.346610', 'directory_id': 480, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_141 task is created\n", - "Creating / Uploading data to directory NER_train_batch_141\n", - "{'client': , 'id': 482, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 482, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_142', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:48:23.741319', 'directory_id': 482, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_142 task is created\n", - "Creating / Uploading data to directory NER_train_batch_142\n", - "{'client': , 'id': 484, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 484, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_143', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:48:42.408997', 'directory_id': 484, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_143 task is created\n", - "Creating / Uploading data to directory NER_train_batch_143\n", - "{'client': , 'id': 486, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 486, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_144', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:49:01.211840', 'directory_id': 486, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_144 task is created\n", - "Creating / Uploading data to directory NER_train_batch_144\n", - "{'client': , 'id': 488, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 488, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_145', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:49:19.967333', 'directory_id': 488, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_145 task is created\n", - "Creating / Uploading data to directory NER_train_batch_145\n", - "{'client': , 'id': 490, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 490, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_146', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:49:38.173941', 'directory_id': 490, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_146 task is created\n", - "Creating / Uploading data to directory NER_train_batch_146\n", - "{'client': , 'id': 492, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 492, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_147', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:49:57.084808', 'directory_id': 492, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_147 task is created\n", - "Creating / Uploading data to directory NER_train_batch_147\n", - "{'client': , 'id': 494, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 494, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_148', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:50:15.773604', 'directory_id': 494, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_148 task is created\n", - "Creating / Uploading data to directory NER_train_batch_148\n", - "{'client': , 'id': 496, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 496, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_149', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:50:34.748229', 'directory_id': 496, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_149 task is created\n", - "Creating / Uploading data to directory NER_train_batch_149\n", - "{'client': , 'id': 498, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 498, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_150', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:50:53.643624', 'directory_id': 498, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_150 task is created\n", - "Creating / Uploading data to directory NER_train_batch_150\n", - "{'client': , 'id': 500, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 500, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_151', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:51:12.397748', 'directory_id': 500, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_151 task is created\n", - "Creating / Uploading data to directory NER_train_batch_151\n", - "{'client': , 'id': 502, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 502, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_152', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:51:31.421024', 'directory_id': 502, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_152 task is created\n", - "Creating / Uploading data to directory NER_train_batch_152\n", - "{'client': , 'id': 504, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 504, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_153', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:51:50.330932', 'directory_id': 504, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_153 task is created\n", - "Creating / Uploading data to directory NER_train_batch_153\n", - "{'client': , 'id': 506, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 506, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_154', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:52:09.374952', 'directory_id': 506, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_154 task is created\n", - "Creating / Uploading data to directory NER_train_batch_154\n", - "{'client': , 'id': 508, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 508, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_155', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:52:28.225261', 'directory_id': 508, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_155 task is created\n", - "Creating / Uploading data to directory NER_train_batch_155\n", - "{'client': , 'id': 510, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 510, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_156', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:52:47.580990', 'directory_id': 510, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_156 task is created\n", - "Creating / Uploading data to directory NER_train_batch_156\n", - "{'client': , 'id': 512, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 512, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_157', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:53:06.906751', 'directory_id': 512, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_157 task is created\n", - "Creating / Uploading data to directory NER_train_batch_157\n", - "{'client': , 'id': 514, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 514, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_158', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:53:26.300079', 'directory_id': 514, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_158 task is created\n", - "Creating / Uploading data to directory NER_train_batch_158\n", - "{'client': , 'id': 516, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 516, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_159', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:53:45.701404', 'directory_id': 516, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_159 task is created\n", - "Creating / Uploading data to directory NER_train_batch_159\n", - "{'client': , 'id': 518, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 518, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_160', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:54:04.328062', 'directory_id': 518, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_160 task is created\n", - "Creating / Uploading data to directory NER_train_batch_160\n", - "{'client': , 'id': 520, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 520, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_161', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:54:23.463090', 'directory_id': 520, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_161 task is created\n", - "Creating / Uploading data to directory NER_train_batch_161\n", - "{'client': , 'id': 522, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 522, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_162', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:54:42.156766', 'directory_id': 522, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_162 task is created\n", - "Creating / Uploading data to directory NER_train_batch_162\n", - "{'client': , 'id': 524, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 524, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_163', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:55:01.254752', 'directory_id': 524, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_163 task is created\n", - "Creating / Uploading data to directory NER_train_batch_163\n", - "{'client': , 'id': 526, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 526, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_164', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:55:20.039202', 'directory_id': 526, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_164 task is created\n", - "Creating / Uploading data to directory NER_train_batch_164\n", - "{'client': , 'id': 528, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 528, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_165', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:55:38.935044', 'directory_id': 528, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_165 task is created\n", - "Creating / Uploading data to directory NER_train_batch_165\n", - "{'client': , 'id': 530, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 530, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_166', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:55:58.428288', 'directory_id': 530, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_166 task is created\n", - "Creating / Uploading data to directory NER_train_batch_166\n", - "{'client': , 'id': 532, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 532, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_167', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:56:17.812983', 'directory_id': 532, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_167 task is created\n", - "Creating / Uploading data to directory NER_train_batch_167\n", - "{'client': , 'id': 534, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 534, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_168', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:56:37.759891', 'directory_id': 534, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_168 task is created\n", - "Creating / Uploading data to directory NER_train_batch_168\n", - "{'client': , 'id': 536, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 536, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_169', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:56:57.302230', 'directory_id': 536, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_169 task is created\n", - "Creating / Uploading data to directory NER_train_batch_169\n", - "{'client': , 'id': 538, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 538, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_170', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:57:16.848891', 'directory_id': 538, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_170 task is created\n", - "Creating / Uploading data to directory NER_train_batch_170\n", - "{'client': , 'id': 540, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 540, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_171', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:57:36.842984', 'directory_id': 540, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_171 task is created\n", - "Creating / Uploading data to directory NER_train_batch_171\n", - "{'client': , 'id': 542, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 542, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_172', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:57:56.414037', 'directory_id': 542, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_172 task is created\n", - "Creating / Uploading data to directory NER_train_batch_172\n", - "{'client': , 'id': 544, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 544, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_173', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:58:16.258713', 'directory_id': 544, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_173 task is created\n", - "Creating / Uploading data to directory NER_train_batch_173\n", - "{'client': , 'id': 546, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 546, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_174', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:58:36.541644', 'directory_id': 546, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_174 task is created\n", - "Creating / Uploading data to directory NER_train_batch_174\n", - "{'client': , 'id': 548, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 548, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_175', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:58:56.382694', 'directory_id': 548, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_175 task is created\n", - "Creating / Uploading data to directory NER_train_batch_175\n", - "{'client': , 'id': 550, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 550, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_176', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:59:16.670958', 'directory_id': 550, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_176 task is created\n", - "Creating / Uploading data to directory NER_train_batch_176\n", - "{'client': , 'id': 552, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 552, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_177', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:59:36.620031', 'directory_id': 552, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_177 task is created\n", - "Creating / Uploading data to directory NER_train_batch_177\n", - "{'client': , 'id': 554, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 554, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_178', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T14:59:56.885008', 'directory_id': 554, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_178 task is created\n", - "Creating / Uploading data to directory NER_train_batch_178\n", - "{'client': , 'id': 556, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 556, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_179', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:00:17.110146', 'directory_id': 556, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_179 task is created\n", - "Creating / Uploading data to directory NER_train_batch_179\n", - "{'client': , 'id': 558, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 558, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_180', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:00:37.308777', 'directory_id': 558, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_180 task is created\n", - "Creating / Uploading data to directory NER_train_batch_180\n", - "{'client': , 'id': 560, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 560, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_181', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:00:57.674930', 'directory_id': 560, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_181 task is created\n", - "Creating / Uploading data to directory NER_train_batch_181\n", - "{'client': , 'id': 562, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 562, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_182', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:01:18.885620', 'directory_id': 562, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_182 task is created\n", - "Creating / Uploading data to directory NER_train_batch_182\n", - "{'client': , 'id': 564, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 564, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_183', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:01:39.779106', 'directory_id': 564, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_183 task is created\n", - "Creating / Uploading data to directory NER_train_batch_183\n", - "{'client': , 'id': 566, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 566, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_184', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:02:00.813204', 'directory_id': 566, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_184 task is created\n", - "Creating / Uploading data to directory NER_train_batch_184\n", - "{'client': , 'id': 568, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 568, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_185', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:02:21.838898', 'directory_id': 568, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_185 task is created\n", - "Creating / Uploading data to directory NER_train_batch_185\n", - "{'client': , 'id': 570, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 570, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_186', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:02:44.372530', 'directory_id': 570, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_186 task is created\n", - "Creating / Uploading data to directory NER_train_batch_186\n", - "{'client': , 'id': 572, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 572, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_187', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:03:06.752060', 'directory_id': 572, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_187 task is created\n", - "Creating / Uploading data to directory NER_train_batch_187\n", - "{'client': , 'id': 574, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 574, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_188', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:03:28.169252', 'directory_id': 574, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_188 task is created\n", - "Creating / Uploading data to directory NER_train_batch_188\n", - "{'client': , 'id': 576, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 576, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_189', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:03:49.760270', 'directory_id': 576, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_189 task is created\n", - "Creating / Uploading data to directory NER_train_batch_189\n", - "{'client': , 'id': 578, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 578, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_190', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:04:11.361428', 'directory_id': 578, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_190 task is created\n", - "Creating / Uploading data to directory NER_train_batch_190\n", - "{'client': , 'id': 580, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 580, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_191', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:04:32.754486', 'directory_id': 580, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_191 task is created\n", - "Creating / Uploading data to directory NER_train_batch_191\n", - "{'client': , 'id': 582, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 582, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_192', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:04:54.915594', 'directory_id': 582, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_192 task is created\n", - "Creating / Uploading data to directory NER_train_batch_192\n", - "{'client': , 'id': 584, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 584, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_193', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:05:16.610102', 'directory_id': 584, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_193 task is created\n", - "Creating / Uploading data to directory NER_train_batch_193\n", - "{'client': , 'id': 586, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 586, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_194', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:05:38.276685', 'directory_id': 586, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_194 task is created\n", - "Creating / Uploading data to directory NER_train_batch_194\n", - "{'client': , 'id': 588, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 588, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_195', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:06:00.299701', 'directory_id': 588, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_195 task is created\n", - "Creating / Uploading data to directory NER_train_batch_195\n", - "{'client': , 'id': 590, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 590, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_196', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:06:22.310236', 'directory_id': 590, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_196 task is created\n", - "Creating / Uploading data to directory NER_train_batch_196\n", - "{'client': , 'id': 592, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 592, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_197', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:06:44.019689', 'directory_id': 592, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_197 task is created\n", - "Creating / Uploading data to directory NER_train_batch_197\n", - "{'client': , 'id': 594, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 594, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_198', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:07:06.159905', 'directory_id': 594, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_198 task is created\n", - "Creating / Uploading data to directory NER_train_batch_198\n", - "{'client': , 'id': 596, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 596, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_199', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:07:28.271234', 'directory_id': 596, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_199 task is created\n", - "Creating / Uploading data to directory NER_train_batch_199\n", - "{'client': , 'id': 598, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 598, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_200', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:07:49.857399', 'directory_id': 598, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_200 task is created\n", - "Creating / Uploading data to directory NER_train_batch_200\n", - "{'client': , 'id': 600, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 600, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_201', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:08:12.203327', 'directory_id': 600, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_201 task is created\n", - "Creating / Uploading data to directory NER_train_batch_201\n", - "{'client': , 'id': 602, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 602, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_202', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:08:34.666499', 'directory_id': 602, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_202 task is created\n", - "Creating / Uploading data to directory NER_train_batch_202\n", - "{'client': , 'id': 604, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 604, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_203', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:08:56.679399', 'directory_id': 604, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_203 task is created\n", - "Creating / Uploading data to directory NER_train_batch_203\n", - "{'client': , 'id': 606, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 606, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_204', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:09:19.163519', 'directory_id': 606, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_204 task is created\n", - "Creating / Uploading data to directory NER_train_batch_204\n", - "{'client': , 'id': 608, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 608, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_205', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:09:41.692826', 'directory_id': 608, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_205 task is created\n", - "Creating / Uploading data to directory NER_train_batch_205\n", - "{'client': , 'id': 610, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 610, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_206', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:10:04.013762', 'directory_id': 610, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_206 task is created\n", - "Creating / Uploading data to directory NER_train_batch_206\n", - "{'client': , 'id': 612, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 612, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_207', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:10:26.443547', 'directory_id': 612, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_207 task is created\n", - "Creating / Uploading data to directory NER_train_batch_207\n", - "{'client': , 'id': 614, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 614, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_208', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:10:48.761788', 'directory_id': 614, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_208 task is created\n", - "Creating / Uploading data to directory NER_train_batch_208\n", - "{'client': , 'id': 616, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 616, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_209', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:11:11.298009', 'directory_id': 616, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_209 task is created\n", - "Creating / Uploading data to directory NER_train_batch_209\n", - "{'client': , 'id': 618, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 618, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_210', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:11:33.514133', 'directory_id': 618, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_210 task is created\n", - "Creating / Uploading data to directory NER_train_batch_210\n", - "{'client': , 'id': 620, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 620, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_211', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:11:56.023345', 'directory_id': 620, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_211 task is created\n", - "Creating / Uploading data to directory NER_train_batch_211\n", - "{'client': , 'id': 622, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 622, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_212', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:12:18.669819', 'directory_id': 622, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_212 task is created\n", - "Creating / Uploading data to directory NER_train_batch_212\n", - "{'client': , 'id': 624, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 624, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_213', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:12:43.000991', 'directory_id': 624, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_213 task is created\n", - "Creating / Uploading data to directory NER_train_batch_213\n", - "{'client': , 'id': 626, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 626, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_214', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:13:09.294388', 'directory_id': 626, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_214 task is created\n", - "Creating / Uploading data to directory NER_train_batch_214\n", - "{'client': , 'id': 628, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 628, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_215', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:13:33.595321', 'directory_id': 628, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_215 task is created\n", - "Creating / Uploading data to directory NER_train_batch_215\n", - "{'client': , 'id': 630, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 630, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_216', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:13:56.623858', 'directory_id': 630, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_216 task is created\n", - "Creating / Uploading data to directory NER_train_batch_216\n", - "{'client': , 'id': 632, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 632, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_217', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:14:19.364199', 'directory_id': 632, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_217 task is created\n", - "Creating / Uploading data to directory NER_train_batch_217\n", - "{'client': , 'id': 634, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 634, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_218', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:14:42.379137', 'directory_id': 634, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_218 task is created\n", - "Creating / Uploading data to directory NER_train_batch_218\n", - "{'client': , 'id': 636, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 636, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_219', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:15:04.857553', 'directory_id': 636, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_219 task is created\n", - "Creating / Uploading data to directory NER_train_batch_219\n", - "{'client': , 'id': 638, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 638, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_220', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:15:27.183850', 'directory_id': 638, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_220 task is created\n", - "Creating / Uploading data to directory NER_train_batch_220\n", - "{'client': , 'id': 640, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 640, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_221', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:15:49.864680', 'directory_id': 640, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_221 task is created\n", - "Creating / Uploading data to directory NER_train_batch_221\n", - "{'client': , 'id': 642, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 642, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_222', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:16:12.633445', 'directory_id': 642, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_222 task is created\n", - "Creating / Uploading data to directory NER_train_batch_222\n", - "{'client': , 'id': 644, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 644, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_223', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:16:35.910483', 'directory_id': 644, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_223 task is created\n", - "Creating / Uploading data to directory NER_train_batch_223\n", - "{'client': , 'id': 646, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 646, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_224', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:17:00.612772', 'directory_id': 646, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_224 task is created\n", - "Creating / Uploading data to directory NER_train_batch_224\n", - "{'client': , 'id': 648, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 648, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_225', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:17:24.563246', 'directory_id': 648, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_225 task is created\n", - "Creating / Uploading data to directory NER_train_batch_225\n", - "{'client': , 'id': 650, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 650, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_226', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:17:48.454594', 'directory_id': 650, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_226 task is created\n", - "Creating / Uploading data to directory NER_train_batch_226\n", - "{'client': , 'id': 652, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 652, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_227', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:18:11.842622', 'directory_id': 652, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_227 task is created\n", - "Creating / Uploading data to directory NER_train_batch_227\n", - "{'client': , 'id': 654, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 654, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_228', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:18:34.867144', 'directory_id': 654, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_228 task is created\n", - "Creating / Uploading data to directory NER_train_batch_228\n", - "{'client': , 'id': 656, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 656, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_229', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:18:57.598607', 'directory_id': 656, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_229 task is created\n", - "Creating / Uploading data to directory NER_train_batch_229\n", - "{'client': , 'id': 658, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 658, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_230', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:19:20.329860', 'directory_id': 658, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_230 task is created\n", - "Creating / Uploading data to directory NER_train_batch_230\n", - "{'client': , 'id': 660, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 660, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_231', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:19:44.290080', 'directory_id': 660, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_231 task is created\n", - "Creating / Uploading data to directory NER_train_batch_231\n", - "{'client': , 'id': 662, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 662, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_232', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:20:07.788919', 'directory_id': 662, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_232 task is created\n", - "Creating / Uploading data to directory NER_train_batch_232\n", - "{'client': , 'id': 664, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 664, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_233', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:20:31.670496', 'directory_id': 664, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_233 task is created\n", - "Creating / Uploading data to directory NER_train_batch_233\n", - "{'client': , 'id': 666, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 666, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_234', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:20:55.378552', 'directory_id': 666, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_234 task is created\n", - "Creating / Uploading data to directory NER_train_batch_234\n", - "{'client': , 'id': 668, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 668, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_235', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:21:19.268880', 'directory_id': 668, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_235 task is created\n", - "Creating / Uploading data to directory NER_train_batch_235\n", - "{'client': , 'id': 670, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 670, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_236', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:21:42.999225', 'directory_id': 670, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_236 task is created\n", - "Creating / Uploading data to directory NER_train_batch_236\n", - "{'client': , 'id': 672, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 672, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_237', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:22:06.795164', 'directory_id': 672, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_237 task is created\n", - "Creating / Uploading data to directory NER_train_batch_237\n", - "{'client': , 'id': 674, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 674, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_238', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:22:30.736716', 'directory_id': 674, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_238 task is created\n", - "Creating / Uploading data to directory NER_train_batch_238\n", - "{'client': , 'id': 676, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 676, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_239', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:22:54.487006', 'directory_id': 676, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_239 task is created\n", - "Creating / Uploading data to directory NER_train_batch_239\n", - "{'client': , 'id': 678, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 678, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_240', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:23:18.662140', 'directory_id': 678, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_240 task is created\n", - "Creating / Uploading data to directory NER_train_batch_240\n", - "{'client': , 'id': 680, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 680, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_241', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:23:42.443456', 'directory_id': 680, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_241 task is created\n", - "Creating / Uploading data to directory NER_train_batch_241\n", - "{'client': , 'id': 682, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 682, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_242', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:24:05.777620', 'directory_id': 682, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_242 task is created\n", - "Creating / Uploading data to directory NER_train_batch_242\n", - "{'client': , 'id': 684, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 684, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_243', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:24:29.272457', 'directory_id': 684, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_243 task is created\n", - "Creating / Uploading data to directory NER_train_batch_243\n", - "{'client': , 'id': 686, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 686, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_244', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:24:53.067149', 'directory_id': 686, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_244 task is created\n", - "Creating / Uploading data to directory NER_train_batch_244\n", - "{'client': , 'id': 688, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 688, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_245', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:25:17.127248', 'directory_id': 688, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_245 task is created\n", - "Creating / Uploading data to directory NER_train_batch_245\n", - "{'client': , 'id': 690, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 690, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_246', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:25:43.201219', 'directory_id': 690, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_246 task is created\n", - "Creating / Uploading data to directory NER_train_batch_246\n", - "{'client': , 'id': 692, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 692, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_247', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:26:08.392911', 'directory_id': 692, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_247 task is created\n", - "Creating / Uploading data to directory NER_train_batch_247\n", - "{'client': , 'id': 694, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 694, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_248', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:26:33.620282', 'directory_id': 694, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_248 task is created\n", - "Creating / Uploading data to directory NER_train_batch_248\n", - "{'client': , 'id': 696, 'file_list_metadata': {'annotation_status': 'All', 'date_from': None, 'date_to': None, 'directory_id': 696, 'end_index': 0, 'file': {}, 'file_count': 0, 'file_view_mode': 'ids_only', 'issues_filter': None, 'job_id': None, 'label': {'start_index': 0}, 'length_current_page': 0, 'limit': 5000, 'machine_made_setting': 'All', 'media_type': 'All', 'next_page': None, 'no_results_match_search': True, 'page': 1, 'prev_page': 0, 'query': None, 'regen_url': True, 'search_term': None, 'start_index': 0, 'total_pages': 0, 'with_children_files': False}, 'nickname': 'NER_train_batch_249', 'file_id_list': [], 'diffgram_file_id_list': [], 'max_size_cache': 1073741824, 'pool': , 'custom_signer_fn': None, 'file_cache': {}, '_internal_file_list': [], 'current_file_index': 0, 'project': , 'created_time': '2025-02-19T15:26:58.296520', 'directory_id': 696, 'has_changes': None, 'jobs_to_sync': {'job_ids': []}}\n", - "The NER_train_JOB_249 task is created\n", - "Creating / Uploading data to directory NER_train_batch_249\n" - ] - } - ], - "source": [ - "create_datasets(diffgram_documents[2112:], NUM_TRAINING_DATA, BATCH_SIZE, train_dataset_suffix, test_dataset_suffix, JOB_TRAIN_SUFFIX, JOB_TEST_SUFFIX)" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "c0601d03-0651-4edf-837b-d1756037f5ea", - "metadata": {}, - "outputs": [], - "source": [] - } - ], - "metadata": { - "kernelspec": { - "display_name": "Python 3 (ipykernel)", - "language": "python", - "name": "python3" - }, - "language_info": { - "codemirror_mode": { - "name": "ipython", - "version": 3 - }, - "file_extension": ".py", - "mimetype": "text/x-python", - "name": "python", - "nbconvert_exporter": "python", - "pygments_lexer": "ipython3", - "version": "3.11.11" - } - }, - "nbformat": 4, - "nbformat_minor": 5 -} diff --git a/examples/NERDiffgram/step_5_AI_validation.ipynb b/examples/NERDiffgram/step_5_AI_validation.ipynb index 99410475e..290e8ec91 100644 --- a/examples/NERDiffgram/step_5_AI_validation.ipynb +++ b/examples/NERDiffgram/step_5_AI_validation.ipynb @@ -19,7 +19,8 @@ "source": [ "!pip install torch transformers diffgram neo4j anthropic pandas tqdm\n", "!pip install llama_index\n", - "!pip install boto3" + "!pip install boto3\n", + "!pip install pandas" ] }, { @@ -38,16 +39,7 @@ "execution_count": 1, "id": "6d66e7d3-8bb5-404f-b7d8-1dd64df2f052", "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/usr/local/lib/python3.11/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" - ] - } - ], + "outputs": [], "source": [ "import torch\n", "from transformers import BertTokenizerFast, BertForTokenClassification\n", @@ -196,7 +188,7 @@ " }\n", "]\n", "Schema 'ENTITY_TRAINING_SCHEMA' already exists with id: 11\n", - "{'B-CHUNK_ID', 'B-REQUIREMENT', 'B-AUTHORITY', 'I-METADATA_VALUE', 'I-DEFINITION', 'I-SEQUENCE_ID', 'I-ACT_ID', 'B-SECTION_ID', 'B-METADATA_FIELD', 'B-SECTION_NAME', 'B-ACT_ID', 'I-SECTION_NAME', 'I-CHUNK_ID', 'I-REGULATION_ID', 'I-SECTION_ID', 'B-METADATA_VALUE', 'I-ACT_NAME', 'B-REGULATION_ID', 'I-SUBSECTION_REF', 'I-REQUIREMENT', 'O', 'B-DEFINITION', 'I-METADATA_FIELD', 'I-AUTHORITY', 'B-SEQUENCE_ID', 'I-SECTION_REF', 'B-SECTION_REF', 'B-ACT_NAME', 'B-SUBSECTION_REF'}\n" + "{'B-ACT_ID', 'B-AUTHORITY', 'B-METADATA_VALUE', 'B-DEFINITION', 'B-SUBSECTION_REF', 'I-REGULATION_ID', 'I-METADATA_VALUE', 'O', 'I-REQUIREMENT', 'I-SEQUENCE_ID', 'B-SECTION_ID', 'B-METADATA_FIELD', 'B-SECTION_NAME', 'I-CHUNK_ID', 'B-REQUIREMENT', 'I-SUBSECTION_REF', 'I-ACT_NAME', 'B-CHUNK_ID', 'B-SECTION_REF', 'B-SEQUENCE_ID', 'I-METADATA_FIELD', 'I-DEFINITION', 'I-AUTHORITY', 'B-ACT_NAME', 'B-REGULATION_ID', 'I-SECTION_NAME', 'I-SECTION_REF', 'I-ACT_ID', 'I-SECTION_ID'}\n" ] } ], @@ -266,7 +258,7 @@ }, { "cell_type": "code", - "execution_count": 17, + "execution_count": 7, "id": "af043435-eed9-441c-b42c-e1f9de7599b7", "metadata": {}, "outputs": [], @@ -290,7 +282,7 @@ }, { "cell_type": "code", - "execution_count": 18, + "execution_count": 8, "id": "34eb37da-e112-4888-bcc1-5728dce75f3e", "metadata": {}, "outputs": [], @@ -354,7 +346,7 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 9, "id": "cd2fc04b-db61-4887-a993-2f911bc6ad61", "metadata": {}, "outputs": [], @@ -364,7 +356,7 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 10, "id": "11e83d2f-db1b-4d90-a2f0-0849a1997caf", "metadata": {}, "outputs": [], @@ -374,7 +366,7 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 11, "id": "0fc2431e-4a5e-45da-ae27-1fb963743bd4", "metadata": {}, "outputs": [], @@ -384,7 +376,7 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 12, "id": "987640d3-0c15-4f7e-ae25-fa2033f42600", "metadata": {}, "outputs": [ @@ -402,7 +394,7 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 13, "id": "b03fa38f-bdf3-4a9e-bf12-72672ff5982c", "metadata": {}, "outputs": [], @@ -435,12 +427,12 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 15, "id": "069f7ff8-8f8d-418b-a957-49443b1b264a", "metadata": {}, "outputs": [], "source": [ - "def vallidate_annotation(completed_annotations, files_that_need_annotation, failed_to_annotate, annotation_not_complete, job_index, incorrect_count):\n", + "def vallidate_annotation_old(completed_annotations, files_that_need_annotation, failed_to_annotate, annotation_not_complete, job_index, incorrect_count):\n", " for completed_annotation in completed_annotations:\n", " #print(f\"{completed_annotation} ----\")\n", " if (completed_annotation != 'attribute_groups_reference') \\\n", @@ -486,7 +478,78 @@ }, { "cell_type": "code", - "execution_count": 15, + "execution_count": 16, + "id": "a8688c18-ee6a-4e90-8a95-28939fa7ac34", + "metadata": {}, + "outputs": [], + "source": [ + "import pandas as pd\n", + "\n", + "# Create an empty DataFrame to store annotation errors\n", + "annotation_errors_df = pd.DataFrame(columns=[\"job_nickname\", \"index\", \"file_id\", \"error_type\", \"word_count\", \"annotated_count\", \"diff\"])\n", + "\n", + "def validate_annotation(completed_annotations, df, job_index):\n", + " \"\"\"\n", + " Validate annotations and log errors into the DataFrame.\n", + "\n", + " Parameters:\n", + " completed_annotations (dict): Dictionary containing annotation data.\n", + " df (DataFrame): The DataFrame to store annotation errors.\n", + " job_index (dict): Dictionary containing job nickname and index.\n", + "\n", + " Returns:\n", + " None (modifies the DataFrame in-place).\n", + " \"\"\"\n", + "\n", + " for completed_annotation in completed_annotations:\n", + " if completed_annotation in [\"attribute_groups_reference\", \"export_info\", \"label_map\", \"readme\", \"label_colour_map\"]:\n", + " continue\n", + "\n", + " # Retrieve file from Diffgram\n", + " file = project_local.file.get_by_id(completed_annotation, with_instances=True)\n", + " url = file.__dict__['text']['tokens_url_signed']\n", + " data = extract_word_data(url)\n", + "\n", + " # Count total words\n", + " word_count = sum(1 for word in data['nltk']['words'] if word['value'] != '\\n')\n", + "\n", + " # Count annotated words\n", + " annotated_count = len(completed_annotations[completed_annotation]['instance_list'])\n", + " num_annotated_text_index = len(file.__dict__['instance_list'])\n", + "\n", + " # Job Metadata\n", + " job_value = {\n", + " \"job_nickname\": job_index['nickname'],\n", + " \"index\": job_index['index'],\n", + " \"file_id\": completed_annotation,\n", + " \"word_count\": word_count,\n", + " \"annotated_count\": annotated_count,\n", + " \"diff\": abs(word_count - num_annotated_text_index)\n", + " }\n", + "\n", + " # Validation Rules\n", + " if word_count == annotated_count:\n", + " continue # Correctly annotated, no issue.\n", + "\n", + " elif (word_count - num_annotated_text_index) < 4:\n", + " job_value[\"error_type\"] = \"Incorrect Count (Minor)\"\n", + " df.loc[len(df)] = job_value\n", + " print(f\"⚠ Skipping file {completed_annotation} for task {job_index['nickname']} (diff {job_value['diff']})\")\n", + " \n", + " else:\n", + " if annotated_count == 0:\n", + " job_value[\"error_type\"] = \"Failed to Annotate\"\n", + " else:\n", + " job_value[\"error_type\"] = \"Annotation Not Complete\"\n", + "\n", + " df.loc[len(df)] = job_value # Append to DataFrame\n", + " print(f\"❌ ERROR: File {completed_annotation} - Annotated {annotated_count} / Expected {word_count}\")\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 17, "id": "1eb97e64-200a-4f00-b605-4cd5fcc804c2", "metadata": {}, "outputs": [ @@ -496,7 +559,7 @@ "250" ] }, - "execution_count": 15, + "execution_count": 17, "metadata": {}, "output_type": "execute_result" } @@ -505,25 +568,20 @@ "len(jobs_with_data_index)" ] }, + { + "cell_type": "markdown", + "id": "403e0a19-5044-444b-b06e-811691b2b363", + "metadata": {}, + "source": [ + "## The older valdiation scanning function" + ] + }, { "cell_type": "code", "execution_count": null, - "id": "e33c4a22-6f43-4110-bca2-53c1bcc10720", + "id": "af21fcb8-ee61-4770-b1c8-e863a52c5ba8", "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "The job nickname is NER_train_batch_249 and the index is 0\n", - "The job nickname is NER_train_batch_248 and the index is 1\n", - "skipping: file id 20693 of task NER_train_batch_248 of index 1 diff 2\n", - "skipping: file id 20718 of task NER_train_batch_248 of index 1 diff 1\n", - "The job nickname is NER_train_batch_247 and the index is 2\n", - "The job nickname is NER_train_batch_246 and the index is 3\n" - ] - } - ], + "outputs": [], "source": [ "files_that_need_annotation = []\n", "failed_to_annotate = []\n", @@ -533,18 +591,1460 @@ " print(f\"The job nickname is {job_index['nickname']} and the index is {job_index['index']}\")\n", " results.refresh_from_dict(get_job[job_index['index']])\n", " completed_annotations = results.generate_export()\n", - " vallidate_annotation(completed_annotations,files_that_need_annotation, failed_to_annotate, annotation_not_complete, job_index, incorrect_count)\n", + " vallidate_annotation_old(completed_annotations,files_that_need_annotation, failed_to_annotate, annotation_not_complete, job_index, incorrect_count)\n", " #files_index_in_job = []\n", " #get_file_number(completed_annotations, files_index_in_job, )\n", " #print(files_index_in_job)\n", " ## Extract the file data:\n", - "print(len(files_that_need_annotation)) " + "print(len(files_that_need_annotation))" + ] + }, + { + "cell_type": "markdown", + "id": "296e4497-f434-4540-8894-c9b0d7609c08", + "metadata": {}, + "source": [ + "## Improved valdiation scanning function " + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "103053a2-1b1a-4c34-b660-527ec67044ab", + "metadata": {}, + "outputs": [], + "source": [ + "# Initialize an empty DataFrame for errors\n", + "annotation_errors_df = pd.DataFrame(columns=[\"job_nickname\", \"index\", \"file_id\", \"error_type\", \"word_count\", \"annotated_count\", \"diff\"])\n", + "\n", + "for job_index in jobs_with_data_index:\n", + " print(f\"The job nickname is {job_index['nickname']} and the index is {job_index['index']}\")\n", + " \n", + " # Get annotation results\n", + " results.refresh_from_dict(get_job[job_index['index']])\n", + " completed_annotations = results.generate_export()\n", + "\n", + " # Validate and log errors into the DataFrame\n", + " validate_annotation(completed_annotations, annotation_errors_df, job_index)\n", + "\n", + "# Display the DataFrame in Jupyter Notebook\n", + "import ace_tools as tools\n", + "tools.display_dataframe_to_user(name=\"Annotation Errors\", dataframe=annotation_errors_df)\n" + ] + }, + { + "cell_type": "markdown", + "id": "28582f08-e19c-4aa2-b972-7ee11853ca23", + "metadata": {}, + "source": [ + "## Latest validation scanning function" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "id": "ca7c57d9-5082-4b64-8958-cb3a74ede8a4", + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/tmp/ipykernel_22/2636093873.py:3: DeprecationWarning: Importing display from IPython.core.display is deprecated since IPython 7.14, please import from IPython.display\n", + " from IPython.core.display import display, HTML\n" + ] + } + ], + "source": [ + "import pandas as pd\n", + "import requests\n", + "from IPython.core.display import display, HTML\n", + "\n", + "# Initialize an empty DataFrame for annotation errors\n", + "annotation_errors_df = pd.DataFrame(columns=[\"Task Name\", \"File number\", \"Error Type\", \"URL\"])\n", + "\n", + "def get_diffgram_task_url(job_id, file_id, auth):\n", + " \"\"\"\n", + " Fetches the task URL for a given job ID and file ID in Diffgram.\n", + "\n", + " Parameters:\n", + " job_id (int): The job ID.\n", + " file_id (int): The file ID.\n", + " auth (object): Diffgram session authentication.\n", + "\n", + " Returns:\n", + " str: The URL to the annotation task, or None if not found.\n", + " \"\"\"\n", + " url = f\"{DIFFGRAM_CONFIG['host']}/api/v1/job/{job_id}/task/list\"\n", + " data = {\"page_number\": 0, \"job_id\": str(job_id), \"mode_data\": \"direct_route\", \"status\": \"all\", \"limit_count\": 32}\n", + " \n", + " response = requests.post(url, json=data, auth=auth)\n", + " if response.status_code == 200:\n", + " for task in response.json().get(\"task_list\", []):\n", + " #print(f\"{task['id']} file id in task: {task['file']['id']} file id {file_id}\")\n", + " if int(task[\"file\"][\"id\"]) == int(file_id):\n", + " return f\"{DIFFGRAM_CONFIG['host']}/task/{task['id']}?file={file_id}&\"\n", + " return None\n", + "\n", + "def validate_annotation(completed_annotations, job_index, job_id, auth, df):\n", + " \"\"\"\n", + " Validates annotations and logs errors in the DataFrame with clickable links.\n", + "\n", + " Parameters:\n", + " completed_annotations (dict): Annotation data.\n", + " job_index (dict): Job metadata.\n", + " job_id (int): The Diffgram job ID.\n", + " auth (object): Diffgram session authentication.\n", + " df (DataFrame): DataFrame to store annotation errors.\n", + "\n", + " Returns:\n", + " None (modifies df in-place)\n", + " \"\"\"\n", + "\n", + " for file_id in completed_annotations:\n", + " if file_id in [\"attribute_groups_reference\", \"export_info\", \"label_map\", \"readme\", \"label_colour_map\"]:\n", + " continue\n", + "\n", + " # Retrieve file details\n", + " file = project_local.file.get_by_id(file_id, with_instances=True)\n", + " url = file.__dict__[\"text\"][\"tokens_url_signed\"]\n", + " data = extract_word_data(url)\n", + "\n", + " # Count total words\n", + " word_count = sum(1 for word in data[\"nltk\"][\"words\"] if word[\"value\"] != \"\\n\")\n", + "\n", + " # Count annotations\n", + " annotated_count = len(completed_annotations[file_id][\"instance_list\"])\n", + " num_annotated_text_index = len(file.__dict__[\"instance_list\"])\n", + "\n", + " # Determine error type\n", + " error_type = None\n", + " if word_count == annotated_count:\n", + " continue # Skip valid files\n", + " elif abs(word_count - num_annotated_text_index) < 4:\n", + " error_type = \"Incorrect Count (Minor)\"\n", + " elif annotated_count == 0:\n", + " error_type = \"Failed to Annotate\"\n", + " else:\n", + " error_type = \"Annotation Incomplete\"\n", + "\n", + " if error_type:\n", + " task_url = get_diffgram_task_url(job_id, file_id, auth) # Fetch clickable URL\n", + " \n", + " # Append error details to DataFrame\n", + " df.loc[len(df)] = {\n", + " \"Task Name\": job_index[\"nickname\"],\n", + " \"File number\": file_id,\n", + " \"Error Type\": error_type,\n", + " \"URL\": f'{task_url.replace(\"dispatcher\", \"localhost\")}' if task_url else \"URL Not Found\"\n", + " }\n", + " if error_type == \"Incorrect Count (Minor)\":\n", + " error_symbol = \"⚠\"\n", + " else:\n", + " error_symbol = \"❌\"\n", + " print(f\"{error_symbol} ERROR: {error_type} | File ID {file_id} | Task: {job_index['nickname']} | {task_url.replace('dispatcher', 'localhost')}\")\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "1521d133-9445-442b-b919-70cdde2b1a23", + "metadata": {}, + "outputs": [], + "source": [ + "# Initialize DataFrame for tracking errors\n", + "annotation_errors_df = pd.DataFrame(columns=[\"Task Name\", \"File number\", \"Error Type\", \"URL\"])\n", + "\n", + "for job_index in jobs_with_data_index:\n", + " job_id = get_job[job_index[\"index\"]][\"id\"] # Extract job ID\n", + "\n", + " print(f\"Processing Job: {job_index['nickname']} (ID: {job_id})\")\n", + "\n", + " # Refresh job data\n", + " results.refresh_from_dict(get_job[job_index[\"index\"]])\n", + " completed_annotations = results.generate_export()\n", + "\n", + " # Validate and log errors\n", + " validate_annotation(completed_annotations, job_index, job_id, project.session.auth, annotation_errors_df)\n", + "\n", + "# Display errors as a clickable DataFrame\n", + "display(HTML(annotation_errors_df.to_html(escape=False)))\n", + "\n", + "# Optionally save to CSV for review\n", + "annotation_errors_df.to_csv(\"annotation_errors.csv\", index=False)\n" + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "id": "bc9275cf-6085-4cec-8173-b05cbe5273e4", + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/tmp/ipykernel_22/2002397665.py:13: DeprecationWarning: Importing display from IPython.core.display is deprecated since IPython 7.14, please import from IPython.display\n", + " from IPython.core.display import display, HTML\n" + ] + }, + { + "data": { + "text/html": [ + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
Task NameFile numberError TypeURL
123NER_train_batch_7515162Annotation Incompletehttp://localhost:8085/task/31348?file=15162&
141NER_train_batch_4214111Annotation Incompletehttp://localhost:8085/task/30297?file=14111&
147NER_train_batch_2813669Annotation Incompletehttp://localhost:8085/task/29855?file=13669&
122NER_train_batch_8315434Annotation Incompletehttp://localhost:8085/task/31620?file=15434&
68NER_train_batch_15317653Annotation Incompletehttp://localhost:8085/task/33839?file=17653&
112NER_train_batch_9715889Annotation Incompletehttp://localhost:8085/task/32075?file=15889&
152NER_train_batch_2213480Annotation Incompletehttp://localhost:8085/task/29666?file=13480&
102NER_train_batch_10716203Annotation Incompletehttp://localhost:8085/task/32389?file=16203&
137NER_train_batch_5114410Annotation Incompletehttp://localhost:8085/task/30596?file=14410&
157NER_train_batch_1613298Annotation Incompletehttp://localhost:8085/task/29484?file=13298&
76NER_train_batch_14917554Annotation Incompletehttp://localhost:8085/task/33740?file=17554&
109NER_train_batch_10115999Annotation Incompletehttp://localhost:8085/task/32185?file=15999&
131NER_train_batch_5914658Annotation Incompletehttp://localhost:8085/task/30844?file=14658&
118NER_train_batch_8915628Annotation Incompletehttp://localhost:8085/task/31814?file=15628&
82NER_train_batch_13617113Annotation Incompletehttp://localhost:8085/task/33299?file=17113&
167NER_train_batch_512875Annotation Incompletehttp://localhost:8085/task/29119?file=12875&
83NER_train_batch_13517084Annotation Incompletehttp://localhost:8085/task/33270?file=17084&
133NER_train_batch_5714588Annotation Incompletehttp://localhost:8085/task/30774?file=14588&
116NER_train_batch_9215714Incorrect Count (Minor)http://localhost:8085/task/31900?file=15714&
110NER_train_batch_10015964Incorrect Count (Minor)http://localhost:8085/task/32150?file=15964&
117NER_train_batch_8915605Incorrect Count (Minor)http://localhost:8085/task/31791?file=15605&
114NER_train_batch_9215701Incorrect Count (Minor)http://localhost:8085/task/31887?file=15701&
113NER_train_batch_9515824Incorrect Count (Minor)http://localhost:8085/task/32010?file=15824&
119NER_train_batch_8815583Incorrect Count (Minor)http://localhost:8085/task/31769?file=15583&
111NER_train_batch_9815897Incorrect Count (Minor)http://localhost:8085/task/32083?file=15897&
120NER_train_batch_8715568Incorrect Count (Minor)http://localhost:8085/task/31754?file=15568&
121NER_train_batch_8315412Incorrect Count (Minor)http://localhost:8085/task/31598?file=15412&
115NER_train_batch_9215713Incorrect Count (Minor)http://localhost:8085/task/31899?file=15713&
0NER_train_batch_24820693Incorrect Count (Minor)http://localhost:8085/task/36879?file=20693&
107NER_train_batch_10216050Incorrect Count (Minor)http://localhost:8085/task/32236?file=16050&
90NER_train_batch_12716850Incorrect Count (Minor)http://localhost:8085/task/33036?file=16850&
91NER_train_batch_12616791Incorrect Count (Minor)http://localhost:8085/task/32977?file=16791&
92NER_train_batch_12516785Incorrect Count (Minor)http://localhost:8085/task/32971?file=16785&
93NER_train_batch_12416724Incorrect Count (Minor)http://localhost:8085/task/32910?file=16724&
94NER_train_batch_12416747Incorrect Count (Minor)http://localhost:8085/task/32933?file=16747&
95NER_train_batch_12116640Incorrect Count (Minor)http://localhost:8085/task/32826?file=16640&
96NER_train_batch_12016596Incorrect Count (Minor)http://localhost:8085/task/32782?file=16596&
97NER_train_batch_11816561Incorrect Count (Minor)http://localhost:8085/task/32747?file=16561&
98NER_train_batch_11616472Incorrect Count (Minor)http://localhost:8085/task/32658?file=16472&
99NER_train_batch_11516455Incorrect Count (Minor)http://localhost:8085/task/32641?file=16455&
100NER_train_batch_11516462Incorrect Count (Minor)http://localhost:8085/task/32648?file=16462&
101NER_train_batch_11016304Incorrect Count (Minor)http://localhost:8085/task/32490?file=16304&
103NER_train_batch_10616162Incorrect Count (Minor)http://localhost:8085/task/32348?file=16162&
104NER_train_batch_10516116Incorrect Count (Minor)http://localhost:8085/task/32302?file=16116&
106NER_train_batch_10216046Incorrect Count (Minor)http://localhost:8085/task/32232?file=16046&
108NER_train_batch_10115994Incorrect Count (Minor)http://localhost:8085/task/32180?file=15994&
105NER_train_batch_10416086Incorrect Count (Minor)http://localhost:8085/task/32272?file=16086&
128NER_train_batch_6514849Incorrect Count (Minor)http://localhost:8085/task/31035?file=14849&
125NER_train_batch_7115037Incorrect Count (Minor)http://localhost:8085/task/31223?file=15037&
153NER_train_batch_1913385Incorrect Count (Minor)http://localhost:8085/task/29571?file=13385&
154NER_train_batch_1813358Incorrect Count (Minor)http://localhost:8085/task/29544?file=13358&
155NER_train_batch_1713302Incorrect Count (Minor)http://localhost:8085/task/29488?file=13302&
156NER_train_batch_1613283Incorrect Count (Minor)http://localhost:8085/task/29469?file=13283&
158NER_train_batch_1413155Incorrect Count (Minor)http://localhost:8085/task/29399?file=13155&
159NER_train_batch_1413173Incorrect Count (Minor)http://localhost:8085/task/29417?file=13173&
160NER_train_batch_1313128Incorrect Count (Minor)http://localhost:8085/task/29372?file=13128&
151NER_train_batch_2313521Incorrect Count (Minor)http://localhost:8085/task/29707?file=13521&
161NER_train_batch_1313140Incorrect Count (Minor)http://localhost:8085/task/29384?file=13140&
163NER_train_batch_712922Incorrect Count (Minor)http://localhost:8085/task/29166?file=12922&
164NER_train_batch_712924Incorrect Count (Minor)http://localhost:8085/task/29168?file=12924&
165NER_train_batch_712944Incorrect Count (Minor)http://localhost:8085/task/29188?file=12944&
166NER_train_batch_612901Incorrect Count (Minor)http://localhost:8085/task/29145?file=12901&
168NER_train_batch_512885Incorrect Count (Minor)http://localhost:8085/task/29129?file=12885&
169NER_train_batch_412834Incorrect Count (Minor)http://localhost:8085/task/29078?file=12834&
170NER_train_batch_412842Incorrect Count (Minor)http://localhost:8085/task/29086?file=12842&
162NER_train_batch_1113066Incorrect Count (Minor)http://localhost:8085/task/29310?file=13066&
150NER_train_batch_2413530Incorrect Count (Minor)http://localhost:8085/task/29716?file=13530&
149NER_train_batch_2713635Incorrect Count (Minor)http://localhost:8085/task/29821?file=13635&
148NER_train_batch_2813678Incorrect Count (Minor)http://localhost:8085/task/29864?file=13678&
126NER_train_batch_6614872Incorrect Count (Minor)http://localhost:8085/task/31058?file=14872&
127NER_train_batch_6614894Incorrect Count (Minor)http://localhost:8085/task/31080?file=14894&
89NER_train_batch_12716842Incorrect Count (Minor)http://localhost:8085/task/33028?file=16842&
129NER_train_batch_6214757Incorrect Count (Minor)http://localhost:8085/task/30943?file=14757&
130NER_train_batch_6014684Incorrect Count (Minor)http://localhost:8085/task/30870?file=14684&
132NER_train_batch_5814641Incorrect Count (Minor)http://localhost:8085/task/30827?file=14641&
134NER_train_batch_5614568Incorrect Count (Minor)http://localhost:8085/task/30754?file=14568&
135NER_train_batch_5114397Incorrect Count (Minor)http://localhost:8085/task/30583?file=14397&
136NER_train_batch_5114407Incorrect Count (Minor)http://localhost:8085/task/30593?file=14407&
138NER_train_batch_4814291Incorrect Count (Minor)http://localhost:8085/task/30477?file=14291&
139NER_train_batch_4814307Incorrect Count (Minor)http://localhost:8085/task/30493?file=14307&
140NER_train_batch_4514196Incorrect Count (Minor)http://localhost:8085/task/30382?file=14196&
142NER_train_batch_4214115Incorrect Count (Minor)http://localhost:8085/task/30301?file=14115&
143NER_train_batch_3713951Incorrect Count (Minor)http://localhost:8085/task/30137?file=13951&
144NER_train_batch_3613915Incorrect Count (Minor)http://localhost:8085/task/30101?file=13915&
145NER_train_batch_3413848Incorrect Count (Minor)http://localhost:8085/task/30034?file=13848&
146NER_train_batch_2813651Incorrect Count (Minor)http://localhost:8085/task/29837?file=13651&
124NER_train_batch_7215072Incorrect Count (Minor)http://localhost:8085/task/31258?file=15072&
88NER_train_batch_12916901Incorrect Count (Minor)http://localhost:8085/task/33087?file=16901&
86NER_train_batch_13016932Incorrect Count (Minor)http://localhost:8085/task/33118?file=16932&
171NER_train_batch_312794Incorrect Count (Minor)http://localhost:8085/task/29038?file=12794&
22NER_train_batch_21319589Incorrect Count (Minor)http://localhost:8085/task/35775?file=19589&
23NER_train_batch_20919465Incorrect Count (Minor)http://localhost:8085/task/35651?file=19465&
24NER_train_batch_20819424Incorrect Count (Minor)http://localhost:8085/task/35610?file=19424&
25NER_train_batch_20519318Incorrect Count (Minor)http://localhost:8085/task/35504?file=19318&
26NER_train_batch_20419295Incorrect Count (Minor)http://localhost:8085/task/35481?file=19295&
27NER_train_batch_20219234Incorrect Count (Minor)http://localhost:8085/task/35420?file=19234&
28NER_train_batch_20219243Incorrect Count (Minor)http://localhost:8085/task/35429?file=19243&
29NER_train_batch_20019167Incorrect Count (Minor)http://localhost:8085/task/35353?file=19167&
30NER_train_batch_19919127Incorrect Count (Minor)http://localhost:8085/task/35313?file=19127&
31NER_train_batch_19819117Incorrect Count (Minor)http://localhost:8085/task/35303?file=19117&
32NER_train_batch_19619041Incorrect Count (Minor)http://localhost:8085/task/35227?file=19041&
33NER_train_batch_19519014Incorrect Count (Minor)http://localhost:8085/task/35200?file=19014&
34NER_train_batch_19519021Incorrect Count (Minor)http://localhost:8085/task/35207?file=19021&
35NER_train_batch_19519024Incorrect Count (Minor)http://localhost:8085/task/35210?file=19024&
36NER_train_batch_19418964Incorrect Count (Minor)http://localhost:8085/task/35150?file=18964&
37NER_train_batch_19318936Incorrect Count (Minor)http://localhost:8085/task/35122?file=18936&
38NER_train_batch_19318937Incorrect Count (Minor)http://localhost:8085/task/35123?file=18937&
21NER_train_batch_21719711Incorrect Count (Minor)http://localhost:8085/task/35897?file=19711&
39NER_train_batch_19318953Incorrect Count (Minor)http://localhost:8085/task/35139?file=18953&
20NER_train_batch_21719702Incorrect Count (Minor)http://localhost:8085/task/35888?file=19702&
18NER_train_batch_21919767Incorrect Count (Minor)http://localhost:8085/task/35953?file=19767&
1NER_train_batch_24820718Incorrect Count (Minor)http://localhost:8085/task/36904?file=20718&
2NER_train_batch_24120481Incorrect Count (Minor)http://localhost:8085/task/36667?file=20481&
3NER_train_batch_23920421Incorrect Count (Minor)http://localhost:8085/task/36607?file=20421&
4NER_train_batch_23920429Incorrect Count (Minor)http://localhost:8085/task/36615?file=20429&
5NER_train_batch_23820377Incorrect Count (Minor)http://localhost:8085/task/36563?file=20377&
6NER_train_batch_23720359Incorrect Count (Minor)http://localhost:8085/task/36545?file=20359&
7NER_train_batch_23620327Incorrect Count (Minor)http://localhost:8085/task/36513?file=20327&
8NER_train_batch_23320211Incorrect Count (Minor)http://localhost:8085/task/36397?file=20211&
9NER_train_batch_23120174Incorrect Count (Minor)http://localhost:8085/task/36360?file=20174&
10NER_train_batch_23020142Incorrect Count (Minor)http://localhost:8085/task/36328?file=20142&
11NER_train_batch_22820069Incorrect Count (Minor)http://localhost:8085/task/36255?file=20069&
12NER_train_batch_22820076Incorrect Count (Minor)http://localhost:8085/task/36262?file=20076&
13NER_train_batch_22419932Incorrect Count (Minor)http://localhost:8085/task/36118?file=19932&
14NER_train_batch_22319897Incorrect Count (Minor)http://localhost:8085/task/36083?file=19897&
15NER_train_batch_22319911Incorrect Count (Minor)http://localhost:8085/task/36097?file=19911&
16NER_train_batch_22019798Incorrect Count (Minor)http://localhost:8085/task/35984?file=19798&
17NER_train_batch_22019812Incorrect Count (Minor)http://localhost:8085/task/35998?file=19812&
19NER_train_batch_21819747Incorrect Count (Minor)http://localhost:8085/task/35933?file=19747&
40NER_train_batch_18718745Incorrect Count (Minor)http://localhost:8085/task/34931?file=18745&
41NER_train_batch_18718749Incorrect Count (Minor)http://localhost:8085/task/34935?file=18749&
42NER_train_batch_18718764Incorrect Count (Minor)http://localhost:8085/task/34950?file=18764&
65NER_train_batch_15817842Incorrect Count (Minor)http://localhost:8085/task/34028?file=17842&
66NER_train_batch_15717798Incorrect Count (Minor)http://localhost:8085/task/33984?file=17798&
67NER_train_batch_15517722Incorrect Count (Minor)http://localhost:8085/task/33908?file=17722&
69NER_train_batch_15217633Incorrect Count (Minor)http://localhost:8085/task/33819?file=17633&
70NER_train_batch_15217644Incorrect Count (Minor)http://localhost:8085/task/33830?file=17644&
71NER_train_batch_15117595Incorrect Count (Minor)http://localhost:8085/task/33781?file=17595&
72NER_train_batch_15017580Incorrect Count (Minor)http://localhost:8085/task/33766?file=17580&
73NER_train_batch_14917524Incorrect Count (Minor)http://localhost:8085/task/33710?file=17524&
74NER_train_batch_14917525Incorrect Count (Minor)http://localhost:8085/task/33711?file=17525&
75NER_train_batch_14917535Incorrect Count (Minor)http://localhost:8085/task/33721?file=17535&
77NER_train_batch_14717470Incorrect Count (Minor)http://localhost:8085/task/33656?file=17470&
78NER_train_batch_14517424Incorrect Count (Minor)http://localhost:8085/task/33610?file=17424&
79NER_train_batch_14217317Incorrect Count (Minor)http://localhost:8085/task/33503?file=17317&
80NER_train_batch_14217327Incorrect Count (Minor)http://localhost:8085/task/33513?file=17327&
81NER_train_batch_13917211Incorrect Count (Minor)http://localhost:8085/task/33397?file=17211&
84NER_train_batch_13517093Incorrect Count (Minor)http://localhost:8085/task/33279?file=17093&
85NER_train_batch_13217004Incorrect Count (Minor)http://localhost:8085/task/33190?file=17004&
64NER_train_batch_15817833Incorrect Count (Minor)http://localhost:8085/task/34019?file=17833&
63NER_train_batch_15817823Incorrect Count (Minor)http://localhost:8085/task/34009?file=17823&
62NER_train_batch_16117922Incorrect Count (Minor)http://localhost:8085/task/34108?file=17922&
61NER_train_batch_16317977Incorrect Count (Minor)http://localhost:8085/task/34163?file=17977&
43NER_train_batch_18418651Incorrect Count (Minor)http://localhost:8085/task/34837?file=18651&
44NER_train_batch_18318622Incorrect Count (Minor)http://localhost:8085/task/34808?file=18622&
45NER_train_batch_18018528Incorrect Count (Minor)http://localhost:8085/task/34714?file=18528&
46NER_train_batch_18018545Incorrect Count (Minor)http://localhost:8085/task/34731?file=18545&
47NER_train_batch_17818454Incorrect Count (Minor)http://localhost:8085/task/34640?file=18454&
48NER_train_batch_17818478Incorrect Count (Minor)http://localhost:8085/task/34664?file=18478&
49NER_train_batch_17518360Incorrect Count (Minor)http://localhost:8085/task/34546?file=18360&
50NER_train_batch_17518365Incorrect Count (Minor)http://localhost:8085/task/34551?file=18365&
87NER_train_batch_12916900Incorrect Count (Minor)http://localhost:8085/task/33086?file=16900&
51NER_train_batch_17318301Incorrect Count (Minor)http://localhost:8085/task/34487?file=18301&
53NER_train_batch_17118250Incorrect Count (Minor)http://localhost:8085/task/34436?file=18250&
54NER_train_batch_17018211Incorrect Count (Minor)http://localhost:8085/task/34397?file=18211&
55NER_train_batch_17018222Incorrect Count (Minor)http://localhost:8085/task/34408?file=18222&
56NER_train_batch_17018225Incorrect Count (Minor)http://localhost:8085/task/34411?file=18225&
57NER_train_batch_16818148Incorrect Count (Minor)http://localhost:8085/task/34334?file=18148&
58NER_train_batch_16718110Incorrect Count (Minor)http://localhost:8085/task/34296?file=18110&
59NER_train_batch_16718124Incorrect Count (Minor)http://localhost:8085/task/34310?file=18124&
60NER_train_batch_16418023Incorrect Count (Minor)http://localhost:8085/task/34209?file=18023&
52NER_train_batch_17218282Incorrect Count (Minor)http://localhost:8085/task/34468?file=18282&
172NER_train_batch_112749Incorrect Count (Minor)http://localhost:8085/task/28993?file=12749&
" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Define a custom sorting order for error types\n", + "error_priority = {\n", + " \"Failed to Annotate\": 1, # Most critical\n", + " \"Annotation Incomplete\": 2,\n", + " \"Incorrect Count (Minor)\": 3 # Least critical\n", + "}\n", + "\n", + "# Apply sorting based on the custom priority order\n", + "annotation_errors_df[\"Priority\"] = annotation_errors_df[\"Error Type\"].map(error_priority)\n", + "annotation_errors_df = annotation_errors_df.sort_values(by=\"Priority\", ascending=True).drop(columns=[\"Priority\"])\n", + "\n", + "# Display the sorted DataFrame\n", + "from IPython.core.display import display, HTML\n", + "display(HTML(annotation_errors_df.to_html(escape=False)))" ] }, { "cell_type": "code", "execution_count": null, - "id": "685434cd-2e01-4601-aeb0-b2bc90e7f6cf", + "id": "d31c51ae-d874-4bd0-aa28-4a28c7c1784a", "metadata": {}, "outputs": [], "source": [] diff --git a/web/frontend-feedback-analytics/presentation/index.html b/web/frontend-feedback-analytics/presentation/index.html index 7d792efb8..127c47831 100644 --- a/web/frontend-feedback-analytics/presentation/index.html +++ b/web/frontend-feedback-analytics/presentation/index.html @@ -77,10 +77,10 @@

What we will cover

/>
- + src="https://raw.githubusercontent.com/bcgov/citz-imb-ai/main/assets/answer_flow.jpg" + />

RAG Pipeline

@@ -112,8 +112,10 @@

RAG Pipeline

/>
- +
@@ -240,6 +242,16 @@

Active Learning Integration

src="https://raw.githubusercontent.com/bcgov/citz-imb-ai/main/assets/active_learning.jpg" />
+
+ +

Human in the Loop

@@ -268,7 +280,8 @@

Data Annotation (NER)

the data.

- This can be done manually with tools such as Diffgram or Doccano or can be automated using an AI model to pre-annotate. + This can be done manually with tools such as Diffgram or Doccano + or can be automated using an AI model to pre-annotate.

@@ -281,29 +294,47 @@

Doccano

Assisted Annotation Process

  • - Need large amounts of training data. - Initial results suggest thousands of samples would be needed for reliable results. + Need large amounts of training data. Initial results suggest + thousands of samples would be needed for reliable results.
  • - Manually annotating this data takes people resources, but AI annotation is less accurate. For 5000 records: + Manually annotating this data takes people resources, but AI + annotation is less accurate. For 5000 records:
    • Manually: 8-10 days with high accuracy.
    • - Automated with generative AI: only hours but is not accurate so far. + Automated with generative AI: only hours but is not accurate + so far.
+
+

Improved A.I training pipeline

+
+
+ +

Public Cloud

- +