training_l2r_log_2025-06-09_21-34-43.log

2025-06-09 21:34:43,739 - INFO - 📝 Logging initialized. Log file created at: ../tmp/logs/training_l2r_log_2025-06-09_21-34-43.log - [learning2rank.py:288:setup_logging]
2025-06-09 21:34:43,739 - INFO - ================================================================================ - [learning2rank.py:110:log_section]
2025-06-09 21:34:43,740 - INFO - =                      📌 INITIALIZING TRAINING ENVIRONMENT                       = - [learning2rank.py:111:log_section]
2025-06-09 21:34:43,740 - INFO - ================================================================================ - [learning2rank.py:114:log_section]
2025-06-09 21:34:43,740 - INFO - 🚀 Setting up data paths and environment variables... - [learning2rank.py:3918:main]
2025-06-09 21:34:43,740 - INFO - 🛠️ Command-line Arguments: - [learning2rank.py:304:print_args]
2025-06-09 21:34:43,740 - 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: False
  🔹 task: l2r
  🔹 num_train_epochs: 2
  🔹 metric_for_best_model: ndcg@25
  🔹 learning_rate: 0.0001
  🔹 warmup_steps: 0
  🔹 generate_report: False
  🔹 logfile_path: ../tmp/logs/training_l2r_log_2025-06-09_21-34-43.log
  🔹 source: /home/ubuntu/.xcube/data/mimic4_demo - [learning2rank.py:305:print_args]
2025-06-09 21:34:43,740 - INFO - ➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖ - [learning2rank.py:306:print_args]
2025-06-09 21:34:43,740 - INFO - 📁 Using L2R boot directory: ../tmp/MIMIC4_DEMO/mimic4_l2rboot_mistral7b - [learning2rank.py:3932:main]
2025-06-09 21:34:43,740 - INFO - 📂 Using output directory: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b - [learning2rank.py:3934:main]
2025-06-09 21:34:43,740 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:110:log_section]
2025-06-09 21:34:43,740 - INFO - +                               ✨ LOADING DATASETS                               + - [learning2rank.py:111:log_section]
2025-06-09 21:34:43,740 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:114:log_section]
2025-06-09 21:34:43,740 - INFO - 📊 Loading main dataset and L2R dataset... - [learning2rank.py:3937:main]
2025-06-09 21:34:43,741 - INFO - 📂 Loading main data from: /home/ubuntu/.xcube/data/mimic4_demo/mimic4_icd10_full.csv - [learning2rank.py:334:get_data]
2025-06-09 21:34:51,980 - INFO - ✅ Successfully loaded main data: 122279 rows - [learning2rank.py:347:get_data]
2025-06-09 21:34:51,980 - INFO - 📂 Loading L2R data from: ../tmp/MIMIC4_DEMO/mimic4_l2rboot_mistral7b/mimic4_icd10_tok_rank_per_lbl.ft - [learning2rank.py:353:get_data]
2025-06-09 21:34:51,980 - INFO - 📂 Loading L2R tokens from: ../tmp/MIMIC4_DEMO/mimic4_l2rboot_mistral7b/mimic4_icd10_tok.ft - [learning2rank.py:356:get_data]
2025-06-09 21:34:51,980 - INFO - 📂 Loading L2R labels from: ../tmp/MIMIC4_DEMO/mimic4_l2rboot_mistral7b/mimic4_icd10_lbl.ft - [learning2rank.py:359:get_data]
2025-06-09 21:34:53,688 - INFO - ✅ Successfully loaded L2R data: 260243456 rows - [learning2rank.py:366:get_data]
2025-06-09 21:34:53,688 - INFO - ✅ Successfully loaded L2R tokens: 32768 tokens - [learning2rank.py:367:get_data]
2025-06-09 21:34:53,688 - INFO - ✅ Successfully loaded L2R labels: 7942 rows - [learning2rank.py:368:get_data]
2025-06-09 21:34:53,688 - INFO - 🔄 Total data loaded: 122279 main rows, 260243456 L2R rows - [learning2rank.py:375:get_data]
2025-06-09 21:34:53,688 - INFO - ✨ Successfully loaded both datasets: - [learning2rank.py:399:load_datasets]
2025-06-09 21:34:53,688 - INFO -    - 📄 Main dataset: 122279 records - [learning2rank.py:400:load_datasets]
2025-06-09 21:34:53,689 - INFO -    - 📄 L2R dataset: 260243456 records - [learning2rank.py:401:load_datasets]
2025-06-09 21:34:53,689 - INFO -    - 🔤 Tokens: 32768 items - [learning2rank.py:402:load_datasets]
2025-06-09 21:34:53,689 - INFO -    - 🏷️ Labels: 7942 items - [learning2rank.py:403:load_datasets]
2025-06-09 21:34:53,696 - INFO - ✅ Data loading completed successfully - [learning2rank.py:411:load_datasets]
2025-06-09 21:34:54,974 - INFO - ⏳ Starting quantization of ranks for DataFrame with 260243456 rows. Containing 32768 unique tokens & 7942 unique labels - [learning2rank.py:530:quantize_l2r_data]
2025-06-09 21:34:54,974 - INFO - 🔄 Quantizing those 32768 unique token ranks into 101 quantization levels for each label - [learning2rank.py:555:quantize_l2r_data]
2025-06-09 21:35:41,455 - INFO - ✅ Completed quantization: Produced tensor of shape torch.Size([7942, 32768, 4]) with 101 quantization levels per label - [learning2rank.py:609:quantize_l2r_data]
2025-06-09 21:35:41,484 - WARNING - Label 4612: Only 1 tokens with top relevance score (need 50) - [learning2rank.py:725:test_scored_tokens]
2025-06-09 21:35:41,489 - WARNING - Label 7202: Only 1 tokens with top relevance score (need 50) - [learning2rank.py:725:test_scored_tokens]
2025-06-09 21:35:41,493 - WARNING - Label 5529: Only 1 tokens with top relevance score (need 50) - [learning2rank.py:725:test_scored_tokens]
2025-06-09 21:35:41,497 - WARNING - Label 7311: Only 1 tokens with top relevance score (need 50) - [learning2rank.py:725:test_scored_tokens]
2025-06-09 21:35:41,500 - WARNING - Label 5138: Only 1 tokens with top relevance score (need 50) - [learning2rank.py:725:test_scored_tokens]
2025-06-09 21:35:41,529 - INFO - ******************************************************************************** - [learning2rank.py:110:log_section]
2025-06-09 21:35:41,529 - INFO - *                   🌟 STARTING LEARNING TO RANK MODEL TRAINING                   * - [learning2rank.py:111:log_section]
2025-06-09 21:35:41,529 - INFO - ******************************************************************************** - [learning2rank.py:114:log_section]
2025-06-09 21:35:41,529 - INFO - 🔐 Loaded authentication token from environment - [learning2rank.py:3966:main]
2025-06-09 21:35:41,529 - INFO - 🏷️ Hub Model ID for this Learning to Rank task: deb101/mistral-7b-instruct-v0.3-mimic4-adapt-l2r - [learning2rank.py:3970:main]
2025-06-09 21:35:41,529 - INFO - -------------------------------------------------------------------------------- - [learning2rank.py:110:log_section]
2025-06-09 21:35:41,529 - INFO - -                            📋 MODEL EXISTENCE CHECK                             - - [learning2rank.py:111:log_section]
2025-06-09 21:35:41,529 - INFO - -------------------------------------------------------------------------------- - [learning2rank.py:114:log_section]
2025-06-09 21:35:41,529 - INFO - 🔍 Checking model existence locally and on Hugging Face Hub... - [learning2rank.py:431:check_model_existence]
2025-06-09 21:35:41,529 - INFO - ❌ Model not found locally at: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b - [learning2rank.py:438:check_model_existence]
2025-06-09 21:35:41,650 - INFO - ✅ Model exists on Hugging Face Hub with ID: deb101/mistral-7b-instruct-v0.3-mimic4-adapt-l2r - [learning2rank.py:450:check_model_existence]
2025-06-09 21:35:41,650 - INFO - 📁 Model exists either locally or on Hub - [learning2rank.py:476:check_model_existence]
2025-06-09 21:35:41,650 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:110:log_section]
2025-06-09 21:35:41,650 - INFO - +                           ✨ STARTING FRESH TRAINING                            + - [learning2rank.py:111:log_section]
2025-06-09 21:35:41,650 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:114:log_section]
2025-06-09 21:35:41,650 - INFO - 🔄 Starting fresh training (either forced or model not found)... - [learning2rank.py:3983:main]
2025-06-09 21:35:41,665 - 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]
2025-06-09 21:35:41,665 - INFO - 🔑 Successfully authenticated with Hugging Face Hub - [learning2rank.py:312:authenticate_hf]
2025-06-09 21:35:41,665 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:110:log_section]
2025-06-09 21:35:41,665 - INFO - +                              ✨ LOADING BASE MODEL                              + - [learning2rank.py:111:log_section]
2025-06-09 21:35:41,665 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:114:log_section]
2025-06-09 21:35:41,665 - INFO - 📥 Loading pretrained model and tokenizer... - [learning2rank.py:4025:main]
2025-06-09 21:35:41,665 - INFO - 🚀 Starting model and tokenizer loading process... - [learning2rank.py:940:load_base_model_and_tokenizer]
2025-06-09 21:35:41,666 - 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]
2025-06-09 21:35:41,666 - INFO - 🔤 Loading tokenizer for model: mistralai/Mistral-7B-Instruct-v0.3... - [learning2rank.py:953:load_base_model_and_tokenizer]
2025-06-09 21:35:41,946 - INFO - 📝 Setting pad token to eos token... - [learning2rank.py:957:load_base_model_and_tokenizer]
2025-06-09 21:35:41,946 - INFO - 🧠 Loading base model with quantization... - [learning2rank.py:965:load_base_model_and_tokenizer]
2025-06-09 21:35:42,461 - 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]
2025-06-09 21:35:47,769 - INFO - 🔧 Setting up default LoRA configuration... - [learning2rank.py:988:load_base_model_and_tokenizer]
2025-06-09 21:35:47,769 - INFO - 🔍 LoRA config: r=16, alpha=32, targets={'o_proj', 'q_proj', 'k_proj', 'v_proj'}, dropout=0.05 - [learning2rank.py:1011:load_base_model_and_tokenizer]
2025-06-09 21:35:47,769 - INFO - 🧩 Applying LoRA adapters to model... - [learning2rank.py:1018:load_base_model_and_tokenizer]
2025-06-09 21:35:47,946 - INFO - 📊 trainable params: 13,631,488 || all params: 7,261,655,040 || trainable%: 0.1877 - [learning2rank.py:136:log_print_output]
2025-06-09 21:35:47,946 - INFO - ✅ Model and tokenizer successfully loaded! - [learning2rank.py:1025:load_base_model_and_tokenizer]
2025-06-09 21:35:47,946 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:110:log_section]
2025-06-09 21:35:47,946 - INFO - +                              ✨ DATA PREPROCESSING                              + - [learning2rank.py:111:log_section]
2025-06-09 21:35:47,946 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:114:log_section]
2025-06-09 21:35:47,946 - INFO - 🔄 Loading and preprocessing training data... - [learning2rank.py:4033:main]
2025-06-09 21:35:49,021 - INFO - 🔍 Verifying uniqueness of token IDs per label in scored_tokens... - [learning2rank.py:1303:preprocess_data]
2025-06-09 21:35:49,854 - INFO - ✅ All labels have unique token IDs in scored_tokens. - [learning2rank.py:1315:preprocess_data]
2025-06-09 21:35:49,854 - INFO - 🚀 Building a 2D lookup table for efficient token-to-relevance mapping across all labels! 🚀 - [learning2rank.py:1318:preprocess_data]
2025-06-09 21:35:49,854 - INFO - 🔢 Total labels = 7942 - [learning2rank.py:1321:preprocess_data]
2025-06-09 21:35:49,854 - INFO - 🔍 Precomputing token indices and corresponding relevance_values for each label... - [learning2rank.py:1322:preprocess_data]
2025-06-09 21:35:50,084 - INFO - 📊 Lookup table dimensions: 32768 vocabulary size × 7942 labels - [learning2rank.py:1329:preprocess_data]
2025-06-09 21:35:50,084 - INFO - ⚡ This approach eliminates token comparison broadcasting and provides O(1) lookup time for relevance scores! - [learning2rank.py:1332:preprocess_data]
2025-06-09 21:35:50,084 - INFO - 🧮 Processing relevance calculations vectorized for maximum speed 🔥 - [learning2rank.py:1335:preprocess_data]
2025-06-09 21:35:50,247 - INFO - 🔍 Verifying token mappings with 10 samples... - [learning2rank.py:1368:verify_token_mappings]
2025-06-09 21:35:50,411 - INFO - ✅ Token mappings verification completed successfully! 🎉 - [learning2rank.py:1459:verify_token_mappings]
2025-06-09 21:35:50,416 - INFO - 🔄 Processing dataset with map... - [learning2rank.py:1523:preprocess_data]
2025-06-09 21:35:50,735 - INFO - ✅ Dataset built in 0h 0m 0.32s - [learning2rank.py:1546:preprocess_data]
2025-06-09 21:35:50,747 - INFO - The size of Training set: 173 🏋️ (Training Data) - [learning2rank.py:1577:preprocess_data]
2025-06-09 21:35:50,747 - INFO - The size of Evaluation set: 35 🔍 (Test Data) - [learning2rank.py:1578:preprocess_data]
2025-06-09 21:35:50,747 - INFO - 🚀 Created HuggingFace Dataset with 208 samples, 7942 labels - [learning2rank.py:1586:preprocess_data]
2025-06-09 21:35:50,748 - INFO - 🏷️ Number of unique ICD-10 codes: 7942 - [learning2rank.py:4046:main]
2025-06-09 21:35:50,748 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:110:log_section]
2025-06-09 21:35:50,748 - INFO - +                             ✨ MODEL INITIALIZATION                             + - [learning2rank.py:111:log_section]
2025-06-09 21:35:50,748 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:114:log_section]
2025-06-09 21:35:50,748 - INFO - 🧠 Initializing custom L2R model for outputting per-token relevance scores per ICD-10 codes. - [learning2rank.py:4049:main]
2025-06-09 21:35:52,296 - INFO - 🔧 Registering LTRModel with transformers AutoModel 🚀 - [learning2rank.py:1900:define_model]
2025-06-09 21:35:52,297 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:110:log_section]
2025-06-09 21:35:52,297 - INFO - +                             ✨ TRAINING PREPARATION                             + - [learning2rank.py:111:log_section]
2025-06-09 21:35:52,297 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:114:log_section]
2025-06-09 21:35:52,297 - INFO - ⚙️ Preparing training components and optimizers... - [learning2rank.py:4056:main]
2025-06-09 21:35:52,328 - INFO - 🖥️ Device: NVIDIA GH200 480GB - [learning2rank.py:2062:log_training_configuration]
2025-06-09 21:35:52,329 - INFO - 🔋 CUDA Available: True - [learning2rank.py:2065:log_training_configuration]
2025-06-09 21:35:52,329 - INFO - 💾 CUDA Device Count: 1 - [learning2rank.py:2066:log_training_configuration]
2025-06-09 21:35:52,329 - INFO - 
📋 Training Configuration 📋
+----------+-----------------------------+--------------------------------------------------+
| 🌟 Emoji |         🏷️ Parameter         |                     📊 Value                     |
+----------+-----------------------------+--------------------------------------------------+
|    📁    |      Output Directory       |   ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b   |
|    🔁    |       Training Epochs       |                        2                         |
|    🏋️     |      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     |                        86                        |
|    🔢    |      Evaluation Steps       |                        35                        |
|    📊    |    Training Dataset Size    |                  173 samples 🏋️                   |
|    📊    |   Evaluation Dataset Size   |                  35 samples 🔍                   |
+----------+-----------------------------+--------------------------------------------------+ - [learning2rank.py:2054:log_training_args]
2025-06-09 21:35:52,330 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:110:log_section]
2025-06-09 21:35:52,330 - INFO - +                                ✨ MODEL TRAINING                                + - [learning2rank.py:111:log_section]
2025-06-09 21:35:52,330 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:114:log_section]
2025-06-09 21:35:52,330 - INFO - 🏋️ Starting model training process... - [learning2rank.py:4076:main]
2025-06-09 21:35:52,330 - INFO - 🏁 Preparing Custom Trainer 🛠️ - [learning2rank.py:3255:train_model]
2025-06-09 21:35:52,368 - INFO - We are registering the tokenizer mistralai/Mistral-7B-Instruct-v0.3 in Custom Trainer - [learning2rank.py:2694:__init__]
2025-06-09 21:35:52,368 - INFO - 🏋️ Commencing Model Training 💪 - [learning2rank.py:3296:train_model]
2025-06-09 21:35:52,635 - INFO - 🚀 Starting Training... - [learning2rank.py:2444:on_train_begin]
2025-06-09 21:36:11,953 - INFO - 
🚂 Training Metrics (Step 10) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -4.60936e+16 |
+---------------+--------------+
| grad_norm     |          nan |
+---------------+--------------+
| learning_rate |       0.0001 |
+---------------+--------------+
| epoch         |     0.231214 |
+---------------+--------------+ - [learning2rank.py:2362:on_log]
2025-06-09 21:36:26,309 - INFO - 
🚂 Training Metrics (Step 20) 🚂
+---------------+-------------+
| Metric        |       Value |
+===============+=============+
| loss          | -4.4735e+17 |
+---------------+-------------+
| grad_norm     |         nan |
+---------------+-------------+
| learning_rate |      0.0001 |
+---------------+-------------+
| epoch         |    0.462428 |
+---------------+-------------+ - [learning2rank.py:2362:on_log]
2025-06-09 21:36:40,724 - INFO - 
🚂 Training Metrics (Step 30) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -6.33176e+16 |
+---------------+--------------+
| grad_norm     |          nan |
+---------------+--------------+
| learning_rate |       0.0001 |
+---------------+--------------+
| epoch         |     0.693642 |
+---------------+--------------+ - [learning2rank.py:2362:on_log]
2025-06-09 21:36:55,109 - INFO - 
🚂 Training Metrics (Step 40) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -9.37807e+17 |
+---------------+--------------+
| grad_norm     |          nan |
+---------------+--------------+
| learning_rate |       0.0001 |
+---------------+--------------+
| epoch         |     0.924855 |
+---------------+--------------+ - [learning2rank.py:2362:on_log]
2025-06-09 21:36:59,791 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [learning2rank.py:2810:evaluate]
2025-06-09 21:40:15,245 - INFO - 
🔍 Evaluation Metrics 🔍
+-------------------+--------------+
| Metric            |        Value |
+===================+==============+
| eval_loss         | -7.40296e+16 |
+-------------------+--------------+
| eval_ndcg         |     0.955492 |
+-------------------+--------------+
| eval_ndcg@25      |     0.193171 |
+-------------------+--------------+
| eval_precision@25 |         0.04 |
+-------------------+--------------+ - [learning2rank.py:2381:on_evaluate]
2025-06-09 21:40:16,429 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-44 - [learning2rank.py:2934:_save]
2025-06-09 21:40:16,456 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-44 - [learning2rank.py:2939:_save]
2025-06-09 21:40:16,457 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-44:
+---------+-------------------+------------+
|   Index | Saved File        | Size       |
+=========+===================+============+
|       1 | training_args.bin | 0.01 MB    |
+---------+-------------------+------------+
|       2 | model.safetensors | 4122.74 MB |
+---------+-------------------+------------+
|       3 | config.json       | 0.38 MB    |
+---------+-------------------+------------+ - [learning2rank.py:2956:_save]
2025-06-09 21:40:29,984 - INFO - 
🚂 Training Metrics (Step 50) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -4.47773e+18 |
+---------------+--------------+
| grad_norm     |          nan |
+---------------+--------------+
| learning_rate |       0.0001 |
+---------------+--------------+
| epoch         |      1.13873 |
+---------------+--------------+ - [learning2rank.py:2362:on_log]
2025-06-09 21:40:44,487 - INFO - 
🚂 Training Metrics (Step 60) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -1.18825e+17 |
+---------------+--------------+
| grad_norm     |          nan |
+---------------+--------------+
| learning_rate |      9.7e-05 |
+---------------+--------------+
| epoch         |      1.36994 |
+---------------+--------------+ - [learning2rank.py:2362:on_log]
2025-06-09 21:40:58,984 - INFO - 
🚂 Training Metrics (Step 70) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -6.58701e+18 |
+---------------+--------------+
| grad_norm     |  2.93869e+18 |
+---------------+--------------+
| learning_rate |      8.7e-05 |
+---------------+--------------+
| epoch         |      1.60116 |
+---------------+--------------+ - [learning2rank.py:2362:on_log]
2025-06-09 21:41:13,512 - INFO - 
🚂 Training Metrics (Step 80) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -9.29575e+16 |
+---------------+--------------+
| grad_norm     |  1.82087e+18 |
+---------------+--------------+
| learning_rate |      7.6e-05 |
+---------------+--------------+
| epoch         |      1.83237 |
+---------------+--------------+ - [learning2rank.py:2362:on_log]
2025-06-09 21:41:23,377 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-86 - [learning2rank.py:2934:_save]
2025-06-09 21:41:23,404 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-86 - [learning2rank.py:2939:_save]
2025-06-09 21:41:23,405 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-86:
+---------+-------------------+------------+
|   Index | Saved File        | Size       |
+=========+===================+============+
|       1 | training_args.bin | 0.01 MB    |
+---------+-------------------+------------+
|       2 | model.safetensors | 4122.74 MB |
+---------+-------------------+------------+
|       3 | config.json       | 0.38 MB    |
+---------+-------------------+------------+ - [learning2rank.py:2956:_save]
2025-06-09 21:41:23,625 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [learning2rank.py:2810:evaluate]
2025-06-09 21:44:38,246 - INFO - 
🔍 Evaluation Metrics 🔍
+-------------------+--------------+
| Metric            |        Value |
+===================+==============+
| eval_loss         | -2.99807e+17 |
+-------------------+--------------+
| eval_ndcg         |     0.956147 |
+-------------------+--------------+
| eval_ndcg@25      |     0.573301 |
+-------------------+--------------+
| eval_precision@25 |     0.445714 |
+-------------------+--------------+ - [learning2rank.py:2381:on_evaluate]
2025-06-09 21:44:42,152 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-86 - [learning2rank.py:2934:_save]
2025-06-09 21:44:42,180 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-86 - [learning2rank.py:2939:_save]
2025-06-09 21:44:42,181 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-86:
+---------+--------------------+------------+
|   Index | Saved File         | Size       |
+=========+====================+============+
|       1 | training_args.bin  | 0.01 MB    |
+---------+--------------------+------------+
|       2 | optimizer.pt       | 352.39 MB  |
+---------+--------------------+------------+
|       3 | model.safetensors  | 4122.74 MB |
+---------+--------------------+------------+
|       4 | scaler.pt          | 0.00 MB    |
+---------+--------------------+------------+
|       5 | config.json        | 0.38 MB    |
+---------+--------------------+------------+
|       6 | scheduler.pt       | 0.00 MB    |
+---------+--------------------+------------+
|       7 | trainer_state.json | 0.00 MB    |
+---------+--------------------+------------+
|       8 | rng_state.pth      | 0.01 MB    |
+---------+--------------------+------------+ - [learning2rank.py:2956:_save]
2025-06-09 21:44:42,737 - INFO - 📂 Loading best model from ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-86 - [learning2rank.py:3012:_load_best_model]
2025-06-09 21:44:42,737 - INFO - 🖥️ Model is on device: cuda:0 - [learning2rank.py:3022:_load_best_model]
2025-06-09 21:44:42,794 - 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:3046:_load_best_model]
2025-06-09 21:44:43,614 - INFO - ✅ Loaded best model weights from ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-86/model.safetensors - [learning2rank.py:3063:_load_best_model]
2025-06-09 21:44:43,654 - INFO - ✔️ Weight for label_embeddings.weight matches between saved and loaded state_dict - [learning2rank.py:3075:_load_best_model]
2025-06-09 21:44:43,710 - INFO - ✔️ Weight for ground_model.base_model.model.model.embed_tokens.weight matches between saved and loaded state_dict - [learning2rank.py:3075:_load_best_model]
2025-06-09 21:44:43,726 - INFO - 
🚂 Training Metrics (Step 86) 🚂
+--------------------------+--------------+
| Metric                   |        Value |
+==========================+==============+
| train_runtime            |      531.093 |
+--------------------------+--------------+
| train_samples_per_second |        0.651 |
+--------------------------+--------------+
| train_steps_per_second   |        0.162 |
+--------------------------+--------------+
| total_flos               |  3.81076e+15 |
+--------------------------+--------------+
| train_loss               | -1.59528e+18 |
+--------------------------+--------------+
| epoch                    |       1.9711 |
+--------------------------+--------------+ - [learning2rank.py:2362:on_log]
2025-06-09 21:44:43,727 - INFO - ✨ Training Completed! ✨ - [learning2rank.py:2511:on_train_end]
2025-06-09 21:44:43,804 - INFO - 📊 Training loss plot saved as '../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/train_loss_plot.png' - [learning2rank.py:2614:on_train_end]
2025-06-09 21:44:43,860 - INFO - 📊 Evaluation loss plot saved as '../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/eval_loss_plot.png' - [learning2rank.py:2628:on_train_end]
2025-06-09 21:44:43,919 - INFO - 📊 Evaluation metric plot saved as '../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/eval_ndcg@25_plot.png' - [learning2rank.py:2649:on_train_end]
2025-06-09 21:44:43,919 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:110:log_section]
2025-06-09 21:44:43,920 - INFO - +                                 ✨ MODEL SAVING                                 + - [learning2rank.py:111:log_section]
2025-06-09 21:44:43,920 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:114:log_section]
2025-06-09 21:44:43,920 - INFO - 💾 Saving trained model and pushing to Hugging Face Hub... - [learning2rank.py:4091:main]
2025-06-09 21:45:29,938 - INFO - 📁 Creating/using output directory: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b - [learning2rank.py:3330:save_and_push]
2025-06-09 21:45:31,142 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b - [learning2rank.py:2934:_save]
2025-06-09 21:45:31,168 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b - [learning2rank.py:2939:_save]
2025-06-09 21:45:31,170 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b:
+---------+-----------------------+------------+
|   Index | Saved File            | Size       |
+=========+=======================+============+
|       1 | eval_loss_plot.png    | 0.03 MB    |
+---------+-----------------------+------------+
|       2 | training_args.bin     | 0.01 MB    |
+---------+-----------------------+------------+
|       3 | model.safetensors     | 4122.74 MB |
+---------+-----------------------+------------+
|       4 | eval_ndcg@25_plot.png | 0.04 MB    |
+---------+-----------------------+------------+
|       5 | config.json           | 0.38 MB    |
+---------+-----------------------+------------+
|       6 | train_loss_plot.png   | 0.03 MB    |
+---------+-----------------------+------------+ - [learning2rank.py:2956:_save]
2025-06-09 21:45:35,067 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b - [learning2rank.py:2934:_save]
2025-06-09 21:45:35,094 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b - [learning2rank.py:2939:_save]
2025-06-09 21:45:35,096 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b:
+---------+-----------------------+------------+
|   Index | Saved File            | Size       |
+=========+=======================+============+
|       1 | eval_loss_plot.png    | 0.03 MB    |
+---------+-----------------------+------------+
|       2 | training_args.bin     | 0.01 MB    |
+---------+-----------------------+------------+
|       3 | model.safetensors     | 4122.74 MB |
+---------+-----------------------+------------+
|       4 | eval_ndcg@25_plot.png | 0.04 MB    |
+---------+-----------------------+------------+
|       5 | config.json           | 0.38 MB    |
+---------+-----------------------+------------+
|       6 | train_loss_plot.png   | 0.03 MB    |
+---------+-----------------------+------------+ - [learning2rank.py:2956:_save]
2025-06-09 21:46:51,111 - INFO - 💾 Model saved to: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b - [learning2rank.py:3334:save_and_push]
2025-06-09 21:46:51,141 - INFO - 🖌️ Tokenizer saved to: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b - [learning2rank.py:3338:save_and_push]
2025-06-09 21:46:51,580 - INFO - 📊 Lookup table saved to: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/lookup_table.pt - [learning2rank.py:3343:save_and_push]