training_l2r_log_2025-06-10_17-29-48.log

2025-06-10 17:29:48,925 - INFO - 📝 Logging initialized. Log file created at: ../tmp/logs/training_l2r_log_2025-06-10_17-29-48.log - [learning2rank.py:288:setup_logging]
2025-06-10 17:29:48,925 - INFO - ================================================================================ - [learning2rank.py:110:log_section]
2025-06-10 17:29:48,925 - INFO - =                      📌 INITIALIZING TRAINING ENVIRONMENT                       = - [learning2rank.py:111:log_section]
2025-06-10 17:29:48,925 - INFO - ================================================================================ - [learning2rank.py:114:log_section]
2025-06-10 17:29:48,926 - INFO - 🚀 Setting up data paths and environment variables... - [learning2rank.py:3924:main]
2025-06-10 17:29:48,926 - INFO - 🛠️ Command-line Arguments: - [learning2rank.py:304:print_args]
2025-06-10 17:29:48,926 - INFO - 
  🔹 output_dir: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b
  🔹 source_url: XURLs.MIMIC4_DEMO
  🔹 data: mimic4_icd10_full
  🔹 data_l2r_fname_prefix: mimic4_icd10
  🔹 logfile: training_l2r_log
  🔹 base_dir: ../tmp/MIMIC4_DEMO
  🔹 l2r_boot_dir: ../tmp/MIMIC4_DEMO/mimic4_l2rboot_mistral7b
  🔹 hub_model_id: deb101/mistral-7b-instruct-v0.3-mimic4-adapt
  🔹 model_name: mistralai/Mistral-7B-Instruct-v0.3
  🔹 max_length: 512
  🔹 do_fresh_training: True
  🔹 load_from_checkpoint: True
  🔹 task: l2r
  🔹 num_train_epochs: 3
  🔹 metric_for_best_model: ndcg@25
  🔹 learning_rate: 0.0001
  🔹 warmup_steps: 0
  🔹 generate_report: False
  🔹 logfile_path: ../tmp/logs/training_l2r_log_2025-06-10_17-29-48.log
  🔹 source: /home/ubuntu/.xcube/data/mimic4_demo - [learning2rank.py:305:print_args]
2025-06-10 17:29:48,926 - INFO - ➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖ - [learning2rank.py:306:print_args]
2025-06-10 17:29:48,926 - INFO - 📁 Using L2R boot directory: ../tmp/MIMIC4_DEMO/mimic4_l2rboot_mistral7b - [learning2rank.py:3938:main]
2025-06-10 17:29:48,926 - INFO - 📂 Using output directory: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b - [learning2rank.py:3940:main]
2025-06-10 17:29:48,926 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:110:log_section]
2025-06-10 17:29:48,926 - INFO - +                               ✨ LOADING DATASETS                               + - [learning2rank.py:111:log_section]
2025-06-10 17:29:48,927 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:114:log_section]
2025-06-10 17:29:48,927 - INFO - 📊 Loading main dataset and L2R dataset... - [learning2rank.py:3943:main]
2025-06-10 17:29:48,927 - INFO - 📂 Loading main data from: /home/ubuntu/.xcube/data/mimic4_demo/mimic4_icd10_full.csv - [learning2rank.py:334:get_data]
2025-06-10 17:29:58,580 - INFO - ✅ Successfully loaded main data: 122279 rows - [learning2rank.py:347:get_data]
2025-06-10 17:29:58,580 - INFO - 📂 Loading L2R data from: ../tmp/MIMIC4_DEMO/mimic4_l2rboot_mistral7b/mimic4_icd10_tok_rank_per_lbl.ft - [learning2rank.py:353:get_data]
2025-06-10 17:29:58,580 - INFO - 📂 Loading L2R tokens from: ../tmp/MIMIC4_DEMO/mimic4_l2rboot_mistral7b/mimic4_icd10_tok.ft - [learning2rank.py:356:get_data]
2025-06-10 17:29:58,580 - INFO - 📂 Loading L2R labels from: ../tmp/MIMIC4_DEMO/mimic4_l2rboot_mistral7b/mimic4_icd10_lbl.ft - [learning2rank.py:359:get_data]
2025-06-10 17:30:04,132 - INFO - ✅ Successfully loaded L2R data: 260243456 rows - [learning2rank.py:366:get_data]
2025-06-10 17:30:04,132 - INFO - ✅ Successfully loaded L2R tokens: 32768 tokens - [learning2rank.py:367:get_data]
2025-06-10 17:30:04,132 - INFO - ✅ Successfully loaded L2R labels: 7942 rows - [learning2rank.py:368:get_data]
2025-06-10 17:30:04,133 - INFO - 🔄 Total data loaded: 122279 main rows, 260243456 L2R rows - [learning2rank.py:375:get_data]
2025-06-10 17:30:04,133 - INFO - ✨ Successfully loaded both datasets: - [learning2rank.py:399:load_datasets]
2025-06-10 17:30:04,133 - INFO -    - 📄 Main dataset: 122279 records - [learning2rank.py:400:load_datasets]
2025-06-10 17:30:04,133 - INFO -    - 📄 L2R dataset: 260243456 records - [learning2rank.py:401:load_datasets]
2025-06-10 17:30:04,133 - INFO -    - 🔤 Tokens: 32768 items - [learning2rank.py:402:load_datasets]
2025-06-10 17:30:04,133 - INFO -    - 🏷️ Labels: 7942 items - [learning2rank.py:403:load_datasets]
2025-06-10 17:30:04,143 - INFO - ✅ Data loading completed successfully - [learning2rank.py:411:load_datasets]
2025-06-10 17:30:05,571 - INFO - ⏳ Starting quantization of ranks for DataFrame with 260243456 rows. Containing 32768 unique tokens & 7942 unique labels - [learning2rank.py:530:quantize_l2r_data]
2025-06-10 17:30:05,572 - INFO - 🔄 Quantizing those 32768 unique token ranks into 101 quantization levels for each label - [learning2rank.py:555:quantize_l2r_data]
2025-06-10 17:31:14,594 - INFO - ✅ Completed quantization: Produced tensor of shape torch.Size([7942, 32768, 4]) with 101 quantization levels per label - [learning2rank.py:609:quantize_l2r_data]
2025-06-10 17:31:15,150 - WARNING - Label 893: Only 1 tokens with top relevance score (need 50) - [learning2rank.py:725:test_scored_tokens]
2025-06-10 17:31:15,160 - WARNING - Label 7230: Only 1 tokens with top relevance score (need 50) - [learning2rank.py:725:test_scored_tokens]
2025-06-10 17:31:15,165 - WARNING - Label 1461: Only 1 tokens with top relevance score (need 50) - [learning2rank.py:725:test_scored_tokens]
2025-06-10 17:31:15,170 - WARNING - Label 7348: Only 1 tokens with top relevance score (need 50) - [learning2rank.py:725:test_scored_tokens]
2025-06-10 17:31:15,175 - WARNING - Label 4714: Only 1 tokens with top relevance score (need 50) - [learning2rank.py:725:test_scored_tokens]
2025-06-10 17:31:15,351 - INFO - ******************************************************************************** - [learning2rank.py:110:log_section]
2025-06-10 17:31:15,352 - INFO - *                   🌟 STARTING LEARNING TO RANK MODEL TRAINING                   * - [learning2rank.py:111:log_section]
2025-06-10 17:31:15,352 - INFO - ******************************************************************************** - [learning2rank.py:114:log_section]
2025-06-10 17:31:15,352 - INFO - 🔐 Loaded authentication token from environment - [learning2rank.py:3972:main]
2025-06-10 17:31:15,352 - INFO - 🏷️ Hub Model ID for this Learning to Rank task: deb101/mistral-7b-instruct-v0.3-mimic4-adapt-l2r - [learning2rank.py:3976:main]
2025-06-10 17:31:15,352 - INFO - -------------------------------------------------------------------------------- - [learning2rank.py:110:log_section]
2025-06-10 17:31:15,352 - INFO - -                            📋 MODEL EXISTENCE CHECK                             - - [learning2rank.py:111:log_section]
2025-06-10 17:31:15,352 - INFO - -------------------------------------------------------------------------------- - [learning2rank.py:114:log_section]
2025-06-10 17:31:15,352 - INFO - 🔍 Checking model existence locally and on Hugging Face Hub... - [learning2rank.py:431:check_model_existence]
2025-06-10 17:31:15,352 - INFO - ❌ Model not found locally at: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b - [learning2rank.py:438:check_model_existence]
2025-06-10 17:31:15,424 - INFO - ✅ Model exists on Hugging Face Hub with ID: deb101/mistral-7b-instruct-v0.3-mimic4-adapt-l2r - [learning2rank.py:450:check_model_existence]
2025-06-10 17:31:15,424 - INFO - 📁 Model exists either locally or on Hub - [learning2rank.py:476:check_model_existence]
2025-06-10 17:31:15,424 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:110:log_section]
2025-06-10 17:31:15,424 - INFO - +                           ✨ STARTING FRESH TRAINING                            + - [learning2rank.py:111:log_section]
2025-06-10 17:31:15,424 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:114:log_section]
2025-06-10 17:31:15,424 - INFO - 🔄 Starting fresh training (either forced or model not found)... - [learning2rank.py:3989:main]
2025-06-10 17:31:15,451 - WARNING - Note: Environment variable`HF_TOKEN` is set and is the current active token independently from the token you've just configured. - [_login.py:415:_login]
2025-06-10 17:31:15,451 - INFO - 🔑 Successfully authenticated with Hugging Face Hub - [learning2rank.py:312:authenticate_hf]
2025-06-10 17:31:15,451 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:110:log_section]
2025-06-10 17:31:15,451 - INFO - +                              ✨ DATA PREPROCESSING                              + - [learning2rank.py:111:log_section]
2025-06-10 17:31:15,451 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:114:log_section]
2025-06-10 17:31:15,451 - INFO - 🔄 Loading and preprocessing training data... - [learning2rank.py:3996:main]
2025-06-10 17:31:15,451 - INFO - 🔤 Loading tokenizer for model: deb101/mistral-7b-instruct-v0.3-mimic4-adapt-l2r... - [learning2rank.py:3868:load_tokenizer]
2025-06-10 17:31:15,484 - INFO - 📅 Repository last modified: 2025-06-10 16:57:21+00:00 - [learning2rank.py:3876:load_tokenizer]
2025-06-10 17:31:16,184 - INFO - ✅ Tokenizer loaded successfully for model: deb101/mistral-7b-instruct-v0.3-mimic4-adapt-l2r - [learning2rank.py:3887:load_tokenizer]
2025-06-10 17:31:18,371 - INFO - 🔍 Verifying uniqueness of token IDs per label in scored_tokens... - [learning2rank.py:1303:preprocess_data]
2025-06-10 17:31:19,434 - INFO - ✅ All labels have unique token IDs in scored_tokens. - [learning2rank.py:1315:preprocess_data]
2025-06-10 17:31:19,434 - INFO - 🚀 Building a 2D lookup table for efficient token-to-relevance mapping across all labels! 🚀 - [learning2rank.py:1318:preprocess_data]
2025-06-10 17:31:19,434 - INFO - 🔢 Total labels = 7942 - [learning2rank.py:1321:preprocess_data]
2025-06-10 17:31:19,434 - INFO - 🔍 Precomputing token indices and corresponding relevance_values for each label... - [learning2rank.py:1322:preprocess_data]
2025-06-10 17:31:19,451 - INFO - 📊 Lookup table dimensions: 32768 vocabulary size × 7942 labels - [learning2rank.py:1329:preprocess_data]
2025-06-10 17:31:19,451 - INFO - ⚡ This approach eliminates token comparison broadcasting and provides O(1) lookup time for relevance scores! - [learning2rank.py:1332:preprocess_data]
2025-06-10 17:31:19,452 - INFO - 🧮 Processing relevance calculations vectorized for maximum speed 🔥 - [learning2rank.py:1335:preprocess_data]
2025-06-10 17:31:19,633 - INFO - 🔍 Verifying token mappings with 10 samples... - [learning2rank.py:1368:verify_token_mappings]
2025-06-10 17:31:19,819 - INFO - ✅ Token mappings verification completed successfully! 🎉 - [learning2rank.py:1459:verify_token_mappings]
2025-06-10 17:31:19,827 - INFO - 🔄 Processing dataset with map... - [learning2rank.py:1523:preprocess_data]
2025-06-10 17:31:20,228 - INFO - ✅ Dataset built in 0h 0m 0.40s - [learning2rank.py:1546:preprocess_data]
2025-06-10 17:31:20,243 - INFO - The size of Training set: 173 🏋️ (Training Data) - [learning2rank.py:1577:preprocess_data]
2025-06-10 17:31:20,243 - INFO - The size of Evaluation set: 35 🔍 (Test Data) - [learning2rank.py:1578:preprocess_data]
2025-06-10 17:31:20,243 - INFO - 🚀 Created HuggingFace Dataset with 208 samples, 7942 labels - [learning2rank.py:1586:preprocess_data]
2025-06-10 17:31:20,244 - INFO - 🏷️ Number of unique ICD-10 codes: 7942 - [learning2rank.py:4010:main]
2025-06-10 17:31:20,244 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:110:log_section]
2025-06-10 17:31:20,244 - INFO - +                           ✨ LOADING FROM CHECKPOINT                            + - [learning2rank.py:111:log_section]
2025-06-10 17:31:20,244 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:114:log_section]
2025-06-10 17:31:20,244 - INFO - 📥 Loading existing model from checkpoint... - [learning2rank.py:4013:main]
2025-06-10 17:31:20,244 - INFO - 🔍 Model exists locally: False - [learning2rank.py:3669:load_custom_task_model_and_tokenizer]
2025-06-10 17:31:20,244 - INFO - 🌐 Loading model from Hub: deb101/mistral-7b-instruct-v0.3-mimic4-adapt-l2r - [learning2rank.py:3677:load_custom_task_model_and_tokenizer]
2025-06-10 17:31:20,340 - INFO - 🌐 Loaded config from Hub: deb101/mistral-7b-instruct-v0.3-mimic4-adapt-l2r - [learning2rank.py:3695:load_custom_task_model_and_tokenizer]
2025-06-10 17:31:20,340 - INFO - 🔢 Num labels: 7942, Base model path: mistralai/Mistral-7B-Instruct-v0.3 - [learning2rank.py:3709:load_custom_task_model_and_tokenizer]
2025-06-10 17:31:20,340 - INFO - 🚀 Starting model and tokenizer loading process... - [learning2rank.py:940:load_base_model_and_tokenizer]
2025-06-10 17:31:20,341 - INFO - 📊 Quantization config: BitsAndBytesConfig {
  "_load_in_4bit": true,
  "_load_in_8bit": false,
  "bnb_4bit_compute_dtype": "bfloat16",
  "bnb_4bit_quant_storage": "uint8",
  "bnb_4bit_quant_type": "nf4",
  "bnb_4bit_use_double_quant": true,
  "llm_int8_enable_fp32_cpu_offload": false,
  "llm_int8_has_fp16_weight": false,
  "llm_int8_skip_modules": null,
  "llm_int8_threshold": 6.0,
  "load_in_4bit": true,
  "load_in_8bit": false,
  "quant_method": "bitsandbytes"
}
 - [learning2rank.py:949:load_base_model_and_tokenizer]
2025-06-10 17:31:20,341 - INFO - 🔤 Loading tokenizer for model: mistralai/Mistral-7B-Instruct-v0.3... - [learning2rank.py:953:load_base_model_and_tokenizer]
2025-06-10 17:31:20,657 - INFO - 📝 Setting pad token to eos token... - [learning2rank.py:957:load_base_model_and_tokenizer]
2025-06-10 17:31:20,657 - INFO - 🧠 Loading base model with quantization... - [learning2rank.py:965:load_base_model_and_tokenizer]
2025-06-10 17:31:21,190 - INFO - We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). - [modeling.py:991:get_balanced_memory]
2025-06-10 17:31:36,578 - INFO - 🔧 Setting up default LoRA configuration... - [learning2rank.py:988:load_base_model_and_tokenizer]
2025-06-10 17:31:36,578 - INFO - 🔍 LoRA config: r=16, alpha=32, targets={'o_proj', 'k_proj', 'v_proj', 'q_proj'}, dropout=0.05 - [learning2rank.py:1011:load_base_model_and_tokenizer]
2025-06-10 17:31:36,578 - INFO - 🧩 Applying LoRA adapters to model... - [learning2rank.py:1018:load_base_model_and_tokenizer]
2025-06-10 17:31:36,802 - INFO - 📊 trainable params: 13,631,488 || all params: 7,261,655,040 || trainable%: 0.1877 - [learning2rank.py:136:log_print_output]
2025-06-10 17:31:36,802 - INFO - ✅ Model and tokenizer successfully loaded! - [learning2rank.py:1025:load_base_model_and_tokenizer]
2025-06-10 17:31:36,802 - INFO - 🤖 Loaded base model from: mistralai/Mistral-7B-Instruct-v0.3 - [learning2rank.py:3713:load_custom_task_model_and_tokenizer]
2025-06-10 17:31:36,802 - INFO - Before preparing the model the % of trainable params are: - [learning2rank.py:3721:load_custom_task_model_and_tokenizer]
2025-06-10 17:31:36,807 - INFO - 📊 trainable params: 13,631,488 || all params: 3,771,994,112 || trainable%: 0.3614 - [learning2rank.py:1700:compute_trainable_params]
2025-06-10 17:31:37,216 - INFO - 🔧 Registering LTRModel with transformers AutoModel 🚀 - [learning2rank.py:1902:define_model]
2025-06-10 17:31:37,216 - INFO - 🏗️ Initialized L2R model with 7942 labels - [learning2rank.py:3724:load_custom_task_model_and_tokenizer]
2025-06-10 17:31:37,216 - INFO - After preparing the model the % of trainable params are: - [learning2rank.py:3725:load_custom_task_model_and_tokenizer]
2025-06-10 17:31:37,222 - INFO - 📊 trainable params: 46,161,920 || all params: 3,804,524,544 || trainable%: 1.2133 - [learning2rank.py:1883:compute_trainable_params]
2025-06-10 17:31:37,256 - INFO - 🖥️ Model moved to device: cuda - [learning2rank.py:3730:load_custom_task_model_and_tokenizer]
2025-06-10 17:31:37,510 - INFO - 💾 Loaded custom weights from Hub: /home/ubuntu/.cache/huggingface/hub/models--deb101--mistral-7b-instruct-v0.3-mimic4-adapt-l2r/snapshots/636d86657c46991a40a8430546490b793a0a909e/model.safetensors - [learning2rank.py:3753:load_custom_task_model_and_tokenizer]
2025-06-10 17:31:38,462 - INFO - ✅ Custom weights loaded into model - [learning2rank.py:3772:load_custom_task_model_and_tokenizer]
2025-06-10 17:31:38,481 - INFO - ✔️ Loaded weights match model's state_dict - [learning2rank.py:3783:load_custom_task_model_and_tokenizer]
2025-06-10 17:31:38,482 - INFO - 📋 Loaded files from Hub (directory: /home/ubuntu/.cache/huggingface/hub/models--deb101--mistral-7b-instruct-v0.3-mimic4-adapt-l2r/snapshots/636d86657c46991a40a8430546490b793a0a909e):
+---------+-------------------+------------+
|   Index | Loaded File       | Size       |
+=========+===================+============+
|       1 | config.json       | 0.38 MB    |
+---------+-------------------+------------+
|       2 | model.safetensors | 4122.74 MB |
+---------+-------------------+------------+ - [learning2rank.py:3823:load_custom_task_model_and_tokenizer]
2025-06-10 17:31:38,827 - INFO - 🖌️ Loaded tokenizer from: deb101/mistral-7b-instruct-v0.3-mimic4-adapt-l2r - [learning2rank.py:3838:load_custom_task_model_and_tokenizer]
2025-06-10 17:31:38,839 - INFO - 🖥️ Model moved to device: cuda - [learning2rank.py:3845:load_custom_task_model_and_tokenizer]
2025-06-10 17:31:38,853 - INFO - ✅ Successfully loaded from checkpoint, will now continue training for 3 epochs. - [learning2rank.py:4024:main]
2025-06-10 17:31:38,858 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:110:log_section]
2025-06-10 17:31:38,858 - INFO - +                             ✨ TRAINING PREPARATION                             + - [learning2rank.py:111:log_section]
2025-06-10 17:31:38,858 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:114:log_section]
2025-06-10 17:31:38,858 - INFO - ⚙️ Preparing training components and optimizers... - [learning2rank.py:4062:main]
2025-06-10 17:31:38,903 - INFO - 🖥️ Device: NVIDIA A100 80GB PCIe - [learning2rank.py:2064:log_training_configuration]
2025-06-10 17:31:38,903 - INFO - 🔋 CUDA Available: True - [learning2rank.py:2067:log_training_configuration]
2025-06-10 17:31:38,903 - INFO - 💾 CUDA Device Count: 1 - [learning2rank.py:2068:log_training_configuration]
2025-06-10 17:31:38,904 - INFO - 
📋 Training Configuration 📋
+----------+-----------------------------+--------------------------------------------------+
| 🌟 Emoji |        🏷️ Parameter         |                     📊 Value                     |
+----------+-----------------------------+--------------------------------------------------+
|    📁    |      Output Directory       |   ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b   |
|    🔁    |       Training Epochs       |                        3                         |
|    🏋️    |      Train Batch Size       |                        1                         |
|    🔍    |       Eval Batch Size       |                        1                         |
|    📊    | Gradient Accumulation Steps |                        4                         |
|    🚀    |        Learning Rate        |                      0.0001                      |
|    🌅    |        Warmup Steps         |                        0                         |
|    💾    |        Save Strategy        |                      epoch                       |
|    💾    |      Save Total Limit       |                        10                        |
|    📊    |     Evaluation Strategy     |                      epoch                       |
|    🎯    |      Best Model Metric      |                     ndcg@25                      |
|    📝    |      Logging Strategy       |              steps (every 10 steps)              |
|    🌐    |         Push to Hub         |                       True                       |
|    🌐    |        Hub Model ID         | deb101/mistral-7b-instruct-v0.3-mimic4-adapt-l2r |
|    🔢    |       Steps per Epoch       |                        43                        |
|    🔢    |    Total Training Steps     |                       129                        |
|    🔢    |      Evaluation Steps       |                        35                        |
|    📊    |    Training Dataset Size    |                  173 samples 🏋️                  |
|    📊    |   Evaluation Dataset Size   |                  35 samples 🔍                   |
+----------+-----------------------------+--------------------------------------------------+ - [learning2rank.py:2056:log_training_args]
2025-06-10 17:31:38,904 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:110:log_section]
2025-06-10 17:31:38,904 - INFO - +                                ✨ MODEL TRAINING                                + - [learning2rank.py:111:log_section]
2025-06-10 17:31:38,904 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:114:log_section]
2025-06-10 17:31:38,905 - INFO - 🏋️ Starting model training process... - [learning2rank.py:4082:main]
2025-06-10 17:31:38,905 - INFO - 🏁 Preparing Custom Trainer 🛠️ - [learning2rank.py:3257:train_model]
2025-06-10 17:31:38,992 - INFO - We are registering the tokenizer deb101/mistral-7b-instruct-v0.3-mimic4-adapt-l2r in Custom Trainer - [learning2rank.py:2696:__init__]
2025-06-10 17:31:38,992 - INFO - 🏋️ Commencing Model Training 💪 - [learning2rank.py:3298:train_model]
2025-06-10 17:31:39,424 - INFO - 🚀 Starting Training... - [learning2rank.py:2446:on_train_begin]
2025-06-10 17:32:01,446 - INFO - 
🚂 Training Metrics (Step 10) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -1.41465e+17 |
+---------------+--------------+
| grad_norm     |          nan |
+---------------+--------------+
| learning_rate |       0.0001 |
+---------------+--------------+
| epoch         |     0.231214 |
+---------------+--------------+ - [learning2rank.py:2364:on_log]
2025-06-10 17:32:23,074 - INFO - 
🚂 Training Metrics (Step 20) 🚂
+---------------+-------------+
| Metric        |       Value |
+===============+=============+
| loss          | -7.7045e+17 |
+---------------+-------------+
| grad_norm     |         nan |
+---------------+-------------+
| learning_rate |      0.0001 |
+---------------+-------------+
| epoch         |    0.462428 |
+---------------+-------------+ - [learning2rank.py:2364:on_log]
2025-06-10 17:32:44,788 - INFO - 
🚂 Training Metrics (Step 30) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -1.96148e+17 |
+---------------+--------------+
| grad_norm     |          nan |
+---------------+--------------+
| learning_rate |       0.0001 |
+---------------+--------------+
| epoch         |     0.693642 |
+---------------+--------------+ - [learning2rank.py:2364:on_log]
2025-06-10 17:33:06,592 - INFO - 
🚂 Training Metrics (Step 40) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -6.86576e+18 |
+---------------+--------------+
| grad_norm     |          nan |
+---------------+--------------+
| learning_rate |       0.0001 |
+---------------+--------------+
| epoch         |     0.924855 |
+---------------+--------------+ - [learning2rank.py:2364:on_log]
2025-06-10 17:33:13,692 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [learning2rank.py:2812:evaluate]
2025-06-10 17:34:55,537 - INFO - 
🔍 Evaluation Metrics 🔍
+-------------------+--------------+
| Metric            |        Value |
+===================+==============+
| eval_loss         | -2.40602e+17 |
+-------------------+--------------+
| eval_ndcg         |     0.956305 |
+-------------------+--------------+
| eval_ndcg@25      |     0.442205 |
+-------------------+--------------+
| eval_precision@25 |     0.221429 |
+-------------------+--------------+ - [learning2rank.py:2383:on_evaluate]
2025-06-10 17:35:03,463 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-44 - [learning2rank.py:2936:_save]
2025-06-10 17:35:03,497 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-44 - [learning2rank.py:2941:_save]
2025-06-10 17:35:03,500 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-44:
+---------+-------------------+------------+
|   Index | Saved File        | Size       |
+=========+===================+============+
|       1 | training_args.bin | 0.01 MB    |
+---------+-------------------+------------+
|       2 | config.json       | 0.38 MB    |
+---------+-------------------+------------+
|       3 | model.safetensors | 4122.74 MB |
+---------+-------------------+------------+ - [learning2rank.py:2958:_save]
2025-06-10 17:35:16,538 - INFO - 
🚂 Training Metrics (Step 50) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -5.27798e+18 |
+---------------+--------------+
| grad_norm     |          nan |
+---------------+--------------+
| learning_rate |       0.0001 |
+---------------+--------------+
| epoch         |      1.13873 |
+---------------+--------------+ - [learning2rank.py:2364:on_log]
2025-06-10 17:35:38,444 - INFO - 
🚂 Training Metrics (Step 60) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -2.68631e+17 |
+---------------+--------------+
| grad_norm     |          nan |
+---------------+--------------+
| learning_rate |      9.8e-05 |
+---------------+--------------+
| epoch         |      1.36994 |
+---------------+--------------+ - [learning2rank.py:2364:on_log]
2025-06-10 17:36:00,457 - INFO - 
🚂 Training Metrics (Step 70) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -7.06192e+18 |
+---------------+--------------+
| grad_norm     |  3.77714e+18 |
+---------------+--------------+
| learning_rate |      9.1e-05 |
+---------------+--------------+
| epoch         |      1.60116 |
+---------------+--------------+ - [learning2rank.py:2364:on_log]
2025-06-10 17:36:22,478 - INFO - 
🚂 Training Metrics (Step 80) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -1.70365e+17 |
+---------------+--------------+
| grad_norm     |  8.56735e+17 |
+---------------+--------------+
| learning_rate |      8.4e-05 |
+---------------+--------------+
| epoch         |      1.83237 |
+---------------+--------------+ - [learning2rank.py:2364:on_log]
2025-06-10 17:36:38,436 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [learning2rank.py:2812:evaluate]
2025-06-10 17:38:20,321 - INFO - 
🔍 Evaluation Metrics 🔍
+-------------------+--------------+
| Metric            |        Value |
+===================+==============+
| eval_loss         | -3.80036e+17 |
+-------------------+--------------+
| eval_ndcg         |     0.956906 |
+-------------------+--------------+
| eval_ndcg@25      |     0.774103 |
+-------------------+--------------+
| eval_precision@25 |     0.487059 |
+-------------------+--------------+ - [learning2rank.py:2383:on_evaluate]
2025-06-10 17:38:28,214 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-88 - [learning2rank.py:2936:_save]
2025-06-10 17:38:28,248 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-88 - [learning2rank.py:2941:_save]
2025-06-10 17:38:28,250 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-88:
+---------+-------------------+------------+
|   Index | Saved File        | Size       |
+=========+===================+============+
|       1 | training_args.bin | 0.01 MB    |
+---------+-------------------+------------+
|       2 | config.json       | 0.38 MB    |
+---------+-------------------+------------+
|       3 | model.safetensors | 4122.74 MB |
+---------+-------------------+------------+ - [learning2rank.py:2958:_save]
2025-06-10 17:38:33,235 - INFO - 
🚂 Training Metrics (Step 90) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -1.06889e+18 |
+---------------+--------------+
| grad_norm     |  2.01674e+17 |
+---------------+--------------+
| learning_rate |      7.7e-05 |
+---------------+--------------+
| epoch         |      2.04624 |
+---------------+--------------+ - [learning2rank.py:2364:on_log]
2025-06-10 17:38:55,022 - INFO - 
🚂 Training Metrics (Step 100) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -2.48904e+17 |
+---------------+--------------+
| grad_norm     |  7.86568e+17 |
+---------------+--------------+
| learning_rate |      6.9e-05 |
+---------------+--------------+
| epoch         |      2.27746 |
+---------------+--------------+ - [learning2rank.py:2364:on_log]
2025-06-10 17:39:16,930 - INFO - 
🚂 Training Metrics (Step 110) 🚂
+---------------+-------------+
| Metric        |       Value |
+===============+=============+
| loss          | -3.0905e+18 |
+---------------+-------------+
| grad_norm     |         nan |
+---------------+-------------+
| learning_rate |     6.3e-05 |
+---------------+-------------+
| epoch         |     2.50867 |
+---------------+-------------+ - [learning2rank.py:2364:on_log]
2025-06-10 17:39:38,940 - INFO - 
🚂 Training Metrics (Step 120) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -4.58167e+17 |
+---------------+--------------+
| grad_norm     |  4.35304e+17 |
+---------------+--------------+
| learning_rate |      5.5e-05 |
+---------------+--------------+
| epoch         |      2.73988 |
+---------------+--------------+ - [learning2rank.py:2364:on_log]
2025-06-10 17:40:07,539 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-129 - [learning2rank.py:2936:_save]
2025-06-10 17:40:07,573 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-129 - [learning2rank.py:2941:_save]
2025-06-10 17:40:07,574 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-129:
+---------+-------------------+------------+
|   Index | Saved File        | Size       |
+=========+===================+============+
|       1 | training_args.bin | 0.01 MB    |
+---------+-------------------+------------+
|       2 | config.json       | 0.38 MB    |
+---------+-------------------+------------+
|       3 | model.safetensors | 4122.74 MB |
+---------+-------------------+------------+ - [learning2rank.py:2958:_save]
2025-06-10 17:40:08,217 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [learning2rank.py:2812:evaluate]
2025-06-10 17:41:51,891 - INFO - 
🔍 Evaluation Metrics 🔍
+-------------------+--------------+
| Metric            |        Value |
+===================+==============+
| eval_loss         | -4.11511e+17 |
+-------------------+--------------+
| eval_ndcg         |     0.956901 |
+-------------------+--------------+
| eval_ndcg@25      |     0.716316 |
+-------------------+--------------+
| eval_precision@25 |     0.612571 |
+-------------------+--------------+ - [learning2rank.py:2383:on_evaluate]
2025-06-10 17:42:02,577 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-129 - [learning2rank.py:2936:_save]
2025-06-10 17:42:02,611 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-129 - [learning2rank.py:2941:_save]
2025-06-10 17:42:02,613 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-129:
+---------+--------------------+------------+
|   Index | Saved File         | Size       |
+=========+====================+============+
|       1 | trainer_state.json | 0.00 MB    |
+---------+--------------------+------------+
|       2 | training_args.bin  | 0.01 MB    |
+---------+--------------------+------------+
|       3 | config.json        | 0.38 MB    |
+---------+--------------------+------------+
|       4 | model.safetensors  | 4122.74 MB |
+---------+--------------------+------------+
|       5 | scheduler.pt       | 0.00 MB    |
+---------+--------------------+------------+
|       6 | scaler.pt          | 0.00 MB    |
+---------+--------------------+------------+
|       7 | rng_state.pth      | 0.01 MB    |
+---------+--------------------+------------+
|       8 | optimizer.pt       | 352.39 MB  |
+---------+--------------------+------------+ - [learning2rank.py:2958:_save]
2025-06-10 17:42:03,446 - INFO - 📂 Loading best model from ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-88 - [learning2rank.py:3014:_load_best_model]
2025-06-10 17:42:03,446 - INFO - 🖥️ Model is on device: cuda:0 - [learning2rank.py:3024:_load_best_model]
2025-06-10 17:42:03,509 - INFO - 🔑 Key order comparison:
+---------+--------------------------------------------------------------------------+-------------------------------------------------------------------------------------------+
|   Index | Saved state_dict Keys                                                    | Model state_dict Keys                                                                     |
+=========+==========================================================================+===========================================================================================+
|       1 | ground_model.base_model.model.lm_head.weight                             | label_embeddings.weight                                                                   |
+---------+--------------------------------------------------------------------------+-------------------------------------------------------------------------------------------+
|       2 | ground_model.base_model.model.model.embed_tokens.weight                  | ground_model.base_model.model.model.embed_tokens.weight                                   |
+---------+--------------------------------------------------------------------------+-------------------------------------------------------------------------------------------+
|       3 | ground_model.base_model.model.model.layers.0.input_layernorm.weight      | ground_model.base_model.model.model.layers.0.self_attn.q_proj.base_layer.weight           |
+---------+--------------------------------------------------------------------------+-------------------------------------------------------------------------------------------+
|       4 | ground_model.base_model.model.model.layers.0.mlp.down_proj.weight        | ground_model.base_model.model.model.layers.0.self_attn.q_proj.base_layer.weight.absmax    |
+---------+--------------------------------------------------------------------------+-------------------------------------------------------------------------------------------+
|       5 | ground_model.base_model.model.model.layers.0.mlp.down_proj.weight.absmax | ground_model.base_model.model.model.layers.0.self_attn.q_proj.base_layer.weight.quant_map |
+---------+--------------------------------------------------------------------------+-------------------------------------------------------------------------------------------+ - [learning2rank.py:3048:_load_best_model]
2025-06-10 17:42:04,126 - INFO - ✅ Loaded best model weights from ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-88/model.safetensors - [learning2rank.py:3065:_load_best_model]
2025-06-10 17:42:04,167 - INFO - ✔️ Weight for label_embeddings.weight matches between saved and loaded state_dict - [learning2rank.py:3077:_load_best_model]
2025-06-10 17:42:04,210 - INFO - ✔️ Weight for ground_model.base_model.model.model.embed_tokens.weight matches between saved and loaded state_dict - [learning2rank.py:3077:_load_best_model]
2025-06-10 17:42:04,359 - INFO - 
🚂 Training Metrics (Step 129) 🚂
+--------------------------+--------------+
| Metric                   |        Value |
+==========================+==============+
| train_runtime            |      624.937 |
+--------------------------+--------------+
| train_samples_per_second |         0.83 |
+--------------------------+--------------+
| train_steps_per_second   |        0.206 |
+--------------------------+--------------+
| total_flos               |  5.69938e+15 |
+--------------------------+--------------+
| train_loss               | -2.09116e+18 |
+--------------------------+--------------+
| epoch                    |      2.94798 |
+--------------------------+--------------+ - [learning2rank.py:2364:on_log]
2025-06-10 17:42:04,361 - INFO - ✨ Training Completed! ✨ - [learning2rank.py:2513:on_train_end]
2025-06-10 17:42:04,476 - INFO - 📊 Training loss plot saved as '../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/train_loss_plot.png' - [learning2rank.py:2616:on_train_end]
2025-06-10 17:42:04,566 - INFO - 📊 Evaluation loss plot saved as '../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/eval_loss_plot.png' - [learning2rank.py:2630:on_train_end]
2025-06-10 17:42:04,665 - INFO - 📊 Evaluation metric plot saved as '../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/eval_ndcg@25_plot.png' - [learning2rank.py:2651:on_train_end]
2025-06-10 17:42:04,665 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:110:log_section]
2025-06-10 17:42:04,665 - INFO - +                                 ✨ MODEL SAVING                                 + - [learning2rank.py:111:log_section]
2025-06-10 17:42:04,665 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:114:log_section]
2025-06-10 17:42:04,665 - INFO - 💾 Saving trained model and pushing to Hugging Face Hub... - [learning2rank.py:4097:main]
2025-06-10 17:42:04,665 - INFO - 📁 Creating/using output directory: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b - [learning2rank.py:3332:save_and_push]
2025-06-10 17:42:13,216 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b - [learning2rank.py:2936:_save]
2025-06-10 17:42:13,250 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b - [learning2rank.py:2941:_save]
2025-06-10 17:42:13,252 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b:
+---------+-----------------------+------------+
|   Index | Saved File            | Size       |
+=========+=======================+============+
|       1 | training_args.bin     | 0.01 MB    |
+---------+-----------------------+------------+
|       2 | eval_ndcg@25_plot.png | 0.04 MB    |
+---------+-----------------------+------------+
|       3 | eval_loss_plot.png    | 0.03 MB    |
+---------+-----------------------+------------+
|       4 | config.json           | 0.38 MB    |
+---------+-----------------------+------------+
|       5 | model.safetensors     | 4122.74 MB |
+---------+-----------------------+------------+
|       6 | train_loss_plot.png   | 0.04 MB    |
+---------+-----------------------+------------+ - [learning2rank.py:2958:_save]
2025-06-10 17:42:25,004 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b - [learning2rank.py:2936:_save]
2025-06-10 17:42:25,038 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b - [learning2rank.py:2941:_save]
2025-06-10 17:42:25,040 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b:
+---------+-----------------------+------------+
|   Index | Saved File            | Size       |
+=========+=======================+============+
|       1 | training_args.bin     | 0.01 MB    |
+---------+-----------------------+------------+
|       2 | eval_ndcg@25_plot.png | 0.04 MB    |
+---------+-----------------------+------------+
|       3 | eval_loss_plot.png    | 0.03 MB    |
+---------+-----------------------+------------+
|       4 | config.json           | 0.38 MB    |
+---------+-----------------------+------------+
|       5 | model.safetensors     | 4122.74 MB |
+---------+-----------------------+------------+
|       6 | train_loss_plot.png   | 0.04 MB    |
+---------+-----------------------+------------+ - [learning2rank.py:2958:_save]
2025-06-10 17:43:51,180 - INFO - 💾 Model saved to: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b - [learning2rank.py:3336:save_and_push]
2025-06-10 17:43:51,220 - INFO - 🖌️ Tokenizer saved to: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b - [learning2rank.py:3340:save_and_push]
2025-06-10 17:43:53,074 - INFO - 📊 Lookup table saved to: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/lookup_table.pt - [learning2rank.py:3345:save_and_push]