training_l2r_log_2025-06-12_20-52-17.log

2025-06-12 20:52:17,809 - INFO - 📝 Logging initialized. Log file created at: ../tmp/logs/training_l2r_log_2025-06-12_20-52-17.log - [learning2rank.py:287:setup_logger]
2025-06-12 20:52:17,809 - INFO - ================================================================================ - [learning2rank.py:109:log_section]
2025-06-12 20:52:17,809 - INFO - =                      📌 INITIALIZING TRAINING ENVIRONMENT                       = - [learning2rank.py:110:log_section]
2025-06-12 20:52:17,809 - INFO - ================================================================================ - [learning2rank.py:113:log_section]
2025-06-12 20:52:17,809 - INFO - 🚀 Setting up data paths and environment variables... - [learning2rank.py:3785:main]
2025-06-12 20:52:17,810 - INFO - 🛠️ Command-line Arguments: - [learning2rank.py:303:print_args]
2025-06-12 20:52:17,810 - 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: 5
  🔹 metric_for_best_model: ndcg@25
  🔹 learning_rate: 0.0001
  🔹 warmup_steps: 0
  🔹 generate_report: False
  🔹 logfile_path: ../tmp/logs/training_l2r_log_2025-06-12_20-52-17.log
  🔹 source: /home/ubuntu/.xcube/data/mimic4_demo - [learning2rank.py:304:print_args]
2025-06-12 20:52:17,810 - INFO - ➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖ - [learning2rank.py:305:print_args]
2025-06-12 20:52:17,821 - INFO - 
🚀 Quick Git Info: 📁 xcube | 🌿 plant | 🔍 b97f5b9 | 👤 Debjyoti Saha Roy | ⚡ MIXED (1 staged, 1 unstaged) | 🔬 git show b97f5b9 - [learning2rank.py:3796:main]
2025-06-12 20:52:17,821 - INFO - 📁 Using L2R boot directory: ../tmp/MIMIC4_DEMO/mimic4_l2rboot_mistral7b - [learning2rank.py:3802:main]
2025-06-12 20:52:17,821 - INFO - 📂 Using output directory: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b - [learning2rank.py:3804:main]
2025-06-12 20:52:17,821 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:109:log_section]
2025-06-12 20:52:17,821 - INFO - +                               ✨ LOADING DATASETS                               + - [learning2rank.py:110:log_section]
2025-06-12 20:52:17,821 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:113:log_section]
2025-06-12 20:52:17,821 - INFO - 📊 Loading main dataset and L2R dataset... - [learning2rank.py:3807:main]
2025-06-12 20:52:17,821 - INFO - 📂 Loading main data from: /home/ubuntu/.xcube/data/mimic4_demo/mimic4_icd10_full.csv - [learning2rank.py:333:get_data]
2025-06-12 20:52:26,226 - INFO - ✅ Successfully loaded main data: 122279 rows - [learning2rank.py:346:get_data]
2025-06-12 20:52:26,226 - INFO - 📂 Loading L2R data from: ../tmp/MIMIC4_DEMO/mimic4_l2rboot_mistral7b/mimic4_icd10_tok_rank_per_lbl.ft - [learning2rank.py:352:get_data]
2025-06-12 20:52:26,226 - INFO - 📂 Loading L2R tokens from: ../tmp/MIMIC4_DEMO/mimic4_l2rboot_mistral7b/mimic4_icd10_tok.ft - [learning2rank.py:355:get_data]
2025-06-12 20:52:26,226 - INFO - 📂 Loading L2R labels from: ../tmp/MIMIC4_DEMO/mimic4_l2rboot_mistral7b/mimic4_icd10_lbl.ft - [learning2rank.py:358:get_data]
2025-06-12 20:52:27,974 - INFO - ✅ Successfully loaded L2R data: 260243456 rows - [learning2rank.py:365:get_data]
2025-06-12 20:52:27,975 - INFO - ✅ Successfully loaded L2R tokens: 32768 tokens - [learning2rank.py:366:get_data]
2025-06-12 20:52:27,975 - INFO - ✅ Successfully loaded L2R labels: 7942 rows - [learning2rank.py:367:get_data]
2025-06-12 20:52:27,975 - INFO - 🔄 Total data loaded: 122279 main rows, 260243456 L2R rows - [learning2rank.py:374:get_data]
2025-06-12 20:52:27,975 - INFO - ✨ Successfully loaded both datasets: - [learning2rank.py:398:load_datasets]
2025-06-12 20:52:27,975 - INFO -    - 📄 Main dataset: 122279 records - [learning2rank.py:399:load_datasets]
2025-06-12 20:52:27,975 - INFO -    - 📄 L2R dataset: 260243456 records - [learning2rank.py:400:load_datasets]
2025-06-12 20:52:27,975 - INFO -    - 🔤 Tokens: 32768 items - [learning2rank.py:401:load_datasets]
2025-06-12 20:52:27,975 - INFO -    - 🏷️ Labels: 7942 items - [learning2rank.py:402:load_datasets]
2025-06-12 20:52:27,982 - INFO - ✅ Data loading completed successfully - [learning2rank.py:410:load_datasets]
2025-06-12 20:52:29,271 - INFO - ⏳ Starting quantization of ranks for DataFrame with 260243456 rows. Containing 32768 unique tokens & 7942 unique labels - [learning2rank.py:529:quantize_l2r_data]
2025-06-12 20:52:29,272 - INFO - 🔄 Quantizing those 32768 unique token ranks into 101 quantization levels for each label - [learning2rank.py:554:quantize_l2r_data]
2025-06-12 20:53:15,689 - INFO - ✅ Completed quantization: Produced tensor of shape torch.Size([7942, 32768, 4]) with 101 quantization levels per label - [learning2rank.py:608:quantize_l2r_data]
2025-06-12 20:53:15,715 - WARNING - Label 2051: Only 1 tokens with top relevance score (need 50) - [learning2rank.py:724:test_scored_tokens]
2025-06-12 20:53:15,720 - WARNING - Label 3536: Only 1 tokens with top relevance score (need 50) - [learning2rank.py:724:test_scored_tokens]
2025-06-12 20:53:15,724 - WARNING - Label 1179: Only 1 tokens with top relevance score (need 50) - [learning2rank.py:724:test_scored_tokens]
2025-06-12 20:53:15,728 - WARNING - Label 6454: Only 1 tokens with top relevance score (need 50) - [learning2rank.py:724:test_scored_tokens]
2025-06-12 20:53:15,731 - WARNING - Label 1892: Only 1 tokens with top relevance score (need 50) - [learning2rank.py:724:test_scored_tokens]
2025-06-12 20:53:15,759 - INFO - ******************************************************************************** - [learning2rank.py:109:log_section]
2025-06-12 20:53:15,759 - INFO - *                   🌟 STARTING LEARNING TO RANK MODEL TRAINING                   * - [learning2rank.py:110:log_section]
2025-06-12 20:53:15,759 - INFO - ******************************************************************************** - [learning2rank.py:113:log_section]
2025-06-12 20:53:15,759 - INFO - 🔐 Loaded authentication token from environment - [learning2rank.py:3836:main]
2025-06-12 20:53:15,759 - INFO - 🏷️ Hub Model ID for this Learning to Rank task: deb101/mistral-7b-instruct-v0.3-mimic4-adapt-l2r - [learning2rank.py:3840:main]
2025-06-12 20:53:15,760 - INFO - -------------------------------------------------------------------------------- - [learning2rank.py:109:log_section]
2025-06-12 20:53:15,760 - INFO - -                            📋 MODEL EXISTENCE CHECK                             - - [learning2rank.py:110:log_section]
2025-06-12 20:53:15,760 - INFO - -------------------------------------------------------------------------------- - [learning2rank.py:113:log_section]
2025-06-12 20:53:15,760 - INFO - 🔍 Checking model existence locally and on Hugging Face Hub... - [learning2rank.py:430:check_model_existence]
2025-06-12 20:53:15,760 - INFO - ✅ Model exists locally at: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b - [learning2rank.py:435:check_model_existence]
2025-06-12 20:53:15,806 - INFO - ✅ Model exists on Hugging Face Hub with ID: deb101/mistral-7b-instruct-v0.3-mimic4-adapt-l2r - [learning2rank.py:449:check_model_existence]
2025-06-12 20:53:15,806 - INFO - 📁 Model exists either locally or on Hub - [learning2rank.py:475:check_model_existence]
2025-06-12 20:53:15,807 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:109:log_section]
2025-06-12 20:53:15,807 - INFO - +                           ✨ STARTING FRESH TRAINING                            + - [learning2rank.py:110:log_section]
2025-06-12 20:53:15,807 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:113:log_section]
2025-06-12 20:53:15,807 - INFO - 🔄 Starting fresh training (either forced or model not found)... - [learning2rank.py:3853:main]
2025-06-12 20:53:15,834 - 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]
2025-06-12 20:53:15,834 - INFO - 🔑 Successfully authenticated with Hugging Face Hub - [learning2rank.py:311:authenticate_hf]
2025-06-12 20:53:15,834 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:109:log_section]
2025-06-12 20:53:15,834 - INFO - +                              ✨ LOADING BASE MODEL                              + - [learning2rank.py:110:log_section]
2025-06-12 20:53:15,834 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:113:log_section]
2025-06-12 20:53:15,834 - INFO - 📥 Loading pretrained model and tokenizer... - [learning2rank.py:3895:main]
2025-06-12 20:53:15,834 - INFO - 🚀 Starting model and tokenizer loading process... - [learning2rank.py:939:load_base_model_and_tokenizer]
2025-06-12 20:53:15,835 - 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:948:load_base_model_and_tokenizer]
2025-06-12 20:53:15,835 - INFO - 🔤 Loading tokenizer for model: mistralai/Mistral-7B-Instruct-v0.3... - [learning2rank.py:952:load_base_model_and_tokenizer]
2025-06-12 20:53:16,125 - INFO - 📝 Setting pad token to eos token... - [learning2rank.py:956:load_base_model_and_tokenizer]
2025-06-12 20:53:16,125 - INFO - 🧠 Loading base model with quantization... - [learning2rank.py:964:load_base_model_and_tokenizer]
2025-06-12 20:53:16,629 - 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]
2025-06-12 20:53:21,863 - INFO - 🔧 Setting up default LoRA configuration... - [learning2rank.py:987:load_base_model_and_tokenizer]
2025-06-12 20:53:21,863 - INFO - 🔍 LoRA config: r=16, alpha=32, targets={'k_proj', 'o_proj', 'q_proj', 'v_proj'}, dropout=0.05 - [learning2rank.py:1010:load_base_model_and_tokenizer]
2025-06-12 20:53:21,863 - INFO - 🧩 Applying LoRA adapters to model... - [learning2rank.py:1017:load_base_model_and_tokenizer]
2025-06-12 20:53:22,044 - INFO - 📊 trainable params: 13,631,488 || all params: 7,261,655,040 || trainable%: 0.1877 - [learning2rank.py:135:log_print_output]
2025-06-12 20:53:22,044 - INFO - ✅ Model and tokenizer successfully loaded! - [learning2rank.py:1024:load_base_model_and_tokenizer]
2025-06-12 20:53:22,044 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:109:log_section]
2025-06-12 20:53:22,044 - INFO - +                              ✨ DATA PREPROCESSING                              + - [learning2rank.py:110:log_section]
2025-06-12 20:53:22,044 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:113:log_section]
2025-06-12 20:53:22,044 - INFO - 🔄 Loading and preprocessing training data... - [learning2rank.py:3903:main]
2025-06-12 20:53:23,121 - INFO - 🔍 Verifying uniqueness of token IDs per label in scored_tokens... - [learning2rank.py:1302:preprocess_data]
2025-06-12 20:53:23,927 - INFO - ✅ All labels have unique token IDs in scored_tokens. - [learning2rank.py:1314:preprocess_data]
2025-06-12 20:53:23,927 - INFO - 🚀 Building a 2D lookup table for efficient token-to-relevance mapping across all labels! 🚀 - [learning2rank.py:1317:preprocess_data]
2025-06-12 20:53:23,927 - INFO - 🔢 Total labels = 7942 - [learning2rank.py:1320:preprocess_data]
2025-06-12 20:53:23,927 - INFO - 🔍 Precomputing token indices and corresponding relevance_values for each label... - [learning2rank.py:1321:preprocess_data]
2025-06-12 20:53:24,155 - INFO - 📊 Lookup table dimensions: 32768 vocabulary size × 7942 labels - [learning2rank.py:1328:preprocess_data]
2025-06-12 20:53:24,155 - INFO - ⚡ This approach eliminates token comparison broadcasting and provides O(1) lookup time for relevance scores! - [learning2rank.py:1331:preprocess_data]
2025-06-12 20:53:24,155 - INFO - 🧮 Processing relevance calculations vectorized for maximum speed 🔥 - [learning2rank.py:1334:preprocess_data]
2025-06-12 20:53:24,311 - INFO - 🔍 Verifying token mappings with 10 samples... - [learning2rank.py:1367:verify_token_mappings]
2025-06-12 20:53:24,473 - INFO - ✅ Token mappings verification completed successfully! 🎉 - [learning2rank.py:1458:verify_token_mappings]
2025-06-12 20:53:24,477 - INFO - 🔄 Processing dataset with map... - [learning2rank.py:1522:preprocess_data]
2025-06-12 20:53:24,801 - INFO - ✅ Dataset built in 0h 0m 0.32s - [learning2rank.py:1545:preprocess_data]
2025-06-12 20:53:24,813 - INFO - The size of Training set: 173 🏋️ (Training Data) - [learning2rank.py:1576:preprocess_data]
2025-06-12 20:53:24,813 - INFO - The size of Evaluation set: 35 🔍 (Test Data) - [learning2rank.py:1577:preprocess_data]
2025-06-12 20:53:24,813 - INFO - 🚀 Created HuggingFace Dataset with 208 samples, 7942 labels - [learning2rank.py:1585:preprocess_data]
2025-06-12 20:53:24,814 - INFO - 🏷️ Number of unique ICD-10 codes: 7942 - [learning2rank.py:3916:main]
2025-06-12 20:53:24,814 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:109:log_section]
2025-06-12 20:53:24,814 - INFO - +                             ✨ MODEL INITIALIZATION                             + - [learning2rank.py:110:log_section]
2025-06-12 20:53:24,814 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:113:log_section]
2025-06-12 20:53:24,814 - INFO - 🧠 Initializing custom L2R model for outputting per-token relevance scores per ICD-10 codes. - [learning2rank.py:3919:main]
2025-06-12 20:53:26,376 - INFO - 🔧 Registering LTRModel with transformers AutoModel 🚀 - [learning2rank.py:1725:define_model]
2025-06-12 20:53:26,377 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:109:log_section]
2025-06-12 20:53:26,377 - INFO - +                             ✨ TRAINING PREPARATION                             + - [learning2rank.py:110:log_section]
2025-06-12 20:53:26,377 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:113:log_section]
2025-06-12 20:53:26,377 - INFO - ⚙️ Preparing training components and optimizers... - [learning2rank.py:3926:main]
2025-06-12 20:53:26,409 - INFO - 🖥️ Device: NVIDIA GH200 480GB - [learning2rank.py:1887:log_training_configuration]
2025-06-12 20:53:26,409 - INFO - 🔋 CUDA Available: True - [learning2rank.py:1890:log_training_configuration]
2025-06-12 20:53:26,409 - INFO - 💾 CUDA Device Count: 1 - [learning2rank.py:1891:log_training_configuration]
2025-06-12 20:53:26,410 - INFO - 
📋 Training Configuration 📋
+----------+-----------------------------+--------------------------------------------------+
| 🌟 Emoji |         🏷️ Parameter         |                     📊 Value                     |
+----------+-----------------------------+--------------------------------------------------+
|    📁    |      Output Directory       |   ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b   |
|    🔁    |       Training Epochs       |                        5                         |
|    🏋️     |      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     |                       215                        |
|    🔢    |      Evaluation Steps       |                        35                        |
|    📊    |    Training Dataset Size    |                  173 samples 🏋️                   |
|    📊    |   Evaluation Dataset Size   |                  35 samples 🔍                   |
+----------+-----------------------------+--------------------------------------------------+ - [learning2rank.py:1879:log_training_args]
2025-06-12 20:53:26,410 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:109:log_section]
2025-06-12 20:53:26,410 - INFO - +                                ✨ MODEL TRAINING                                + - [learning2rank.py:110:log_section]
2025-06-12 20:53:26,410 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:113:log_section]
2025-06-12 20:53:26,410 - INFO - 🏋️ Starting model training process... - [learning2rank.py:3946:main]
2025-06-12 20:53:26,410 - INFO - 🏁 Preparing Custom Trainer 🛠️ - [learning2rank.py:3084:train_model]
2025-06-12 20:53:26,454 - INFO - We are registering the tokenizer mistralai/Mistral-7B-Instruct-v0.3 in Custom Trainer - [learning2rank.py:2519:__init__]
2025-06-12 20:53:26,454 - INFO - 🏋️ Commencing Model Training 💪 - [learning2rank.py:3125:train_model]
2025-06-12 20:53:26,720 - INFO - 🚀 Starting Training... - [learning2rank.py:2269:on_train_begin]
2025-06-12 20:53:45,702 - INFO - 
🚂 Training Metrics (Step 10) 🚂
+---------------+-------------+
| Metric        |       Value |
+===============+=============+
| loss          | -4.7327e+16 |
+---------------+-------------+
| grad_norm     |         nan |
+---------------+-------------+
| learning_rate |      0.0001 |
+---------------+-------------+
| epoch         |    0.231214 |
+---------------+-------------+ - [learning2rank.py:2187:on_log]
2025-06-12 20:53:59,752 - INFO - 
🚂 Training Metrics (Step 20) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -3.66103e+17 |
+---------------+--------------+
| grad_norm     |          nan |
+---------------+--------------+
| learning_rate |       0.0001 |
+---------------+--------------+
| epoch         |     0.462428 |
+---------------+--------------+ - [learning2rank.py:2187:on_log]
2025-06-12 20:54:13,802 - INFO - 
🚂 Training Metrics (Step 30) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -6.47362e+16 |
+---------------+--------------+
| grad_norm     |          nan |
+---------------+--------------+
| learning_rate |       0.0001 |
+---------------+--------------+
| epoch         |     0.693642 |
+---------------+--------------+ - [learning2rank.py:2187:on_log]
2025-06-12 20:54:27,786 - INFO - 
🚂 Training Metrics (Step 40) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -8.20245e+17 |
+---------------+--------------+
| grad_norm     |          nan |
+---------------+--------------+
| learning_rate |       0.0001 |
+---------------+--------------+
| epoch         |     0.924855 |
+---------------+--------------+ - [learning2rank.py:2187:on_log]
2025-06-12 20:54:32,360 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [learning2rank.py:2635:evaluate]
2025-06-12 20:57:48,058 - WARNING - No valid samples found for metric 'precision@25'. - [learning2rank.py:2739:evaluate]
2025-06-12 20:57:48,058 - INFO - 
🔍 Evaluation Metrics 🔍
+-------------------+--------------+
| Metric            |        Value |
+===================+==============+
| eval_loss         | -1.38641e+17 |
+-------------------+--------------+
| eval_ndcg         |     0.955604 |
+-------------------+--------------+
| eval_ndcg@25      |     0.196457 |
+-------------------+--------------+
| eval_precision@25 |            0 |
+-------------------+--------------+ - [learning2rank.py:2206:on_evaluate]
2025-06-12 20:57:51,683 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-44 - [learning2rank.py:2759:_save]
2025-06-12 20:57:51,711 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-44 - [learning2rank.py:2764:_save]
2025-06-12 20:57:51,712 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-44:
+---------+--------------------+------------+
|   Index | Saved File         | Size       |
+=========+====================+============+
|       1 | training_args.bin  | 0.01 MB    |
+---------+--------------------+------------+
|       2 | optimizer.pt       | 0.00 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:2785:_save]
2025-06-12 20:58:04,954 - INFO - 
🚂 Training Metrics (Step 50) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -2.51752e+18 |
+---------------+--------------+
| grad_norm     |          nan |
+---------------+--------------+
| learning_rate |       0.0001 |
+---------------+--------------+
| epoch         |      1.13873 |
+---------------+--------------+ - [learning2rank.py:2187:on_log]
2025-06-12 20:58:19,125 - INFO - 
🚂 Training Metrics (Step 60) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -1.03164e+17 |
+---------------+--------------+
| grad_norm     |          nan |
+---------------+--------------+
| learning_rate |      9.9e-05 |
+---------------+--------------+
| epoch         |      1.36994 |
+---------------+--------------+ - [learning2rank.py:2187:on_log]
2025-06-12 20:58:33,206 - INFO - 
🚂 Training Metrics (Step 70) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -6.56896e+18 |
+---------------+--------------+
| grad_norm     |  1.68516e+18 |
+---------------+--------------+
| learning_rate |      9.5e-05 |
+---------------+--------------+
| epoch         |      1.60116 |
+---------------+--------------+ - [learning2rank.py:2187:on_log]
2025-06-12 20:58:47,239 - INFO - 
🚂 Training Metrics (Step 80) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -9.21762e+16 |
+---------------+--------------+
| grad_norm     |  1.31801e+18 |
+---------------+--------------+
| learning_rate |      9.1e-05 |
+---------------+--------------+
| epoch         |      1.83237 |
+---------------+--------------+ - [learning2rank.py:2187:on_log]
2025-06-12 20:58:57,383 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [learning2rank.py:2635:evaluate]
2025-06-12 21:02:12,488 - INFO - 
🔍 Evaluation Metrics 🔍
+-------------------+--------------+
| Metric            |        Value |
+===================+==============+
| eval_loss         | -3.25692e+17 |
+-------------------+--------------+
| eval_ndcg         |     0.956481 |
+-------------------+--------------+
| eval_ndcg@25      |      0.64998 |
+-------------------+--------------+
| eval_precision@25 |     0.545143 |
+-------------------+--------------+ - [learning2rank.py:2206:on_evaluate]
2025-06-12 21:02:14,368 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-88 - [learning2rank.py:2759:_save]
2025-06-12 21:02:14,395 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-88 - [learning2rank.py:2764:_save]
2025-06-12 21:02:14,397 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-88:
+---------+--------------------+------------+
|   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:2785:_save]
2025-06-12 21:02:22,258 - INFO - 
🚂 Training Metrics (Step 90) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -9.98789e+17 |
+---------------+--------------+
| grad_norm     |  3.42546e+17 |
+---------------+--------------+
| learning_rate |      8.7e-05 |
+---------------+--------------+
| epoch         |      2.04624 |
+---------------+--------------+ - [learning2rank.py:2187:on_log]
2025-06-12 21:02:36,292 - INFO - 
🚂 Training Metrics (Step 100) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -2.14719e+17 |
+---------------+--------------+
| grad_norm     |  6.88191e+17 |
+---------------+--------------+
| learning_rate |      8.2e-05 |
+---------------+--------------+
| epoch         |      2.27746 |
+---------------+--------------+ - [learning2rank.py:2187:on_log]
2025-06-12 21:02:50,369 - INFO - 
🚂 Training Metrics (Step 110) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -4.48427e+18 |
+---------------+--------------+
| grad_norm     |          nan |
+---------------+--------------+
| learning_rate |      7.8e-05 |
+---------------+--------------+
| epoch         |      2.50867 |
+---------------+--------------+ - [learning2rank.py:2187:on_log]
2025-06-12 21:03:04,458 - INFO - 
🚂 Training Metrics (Step 120) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -4.49499e+17 |
+---------------+--------------+
| grad_norm     |  1.00208e+18 |
+---------------+--------------+
| learning_rate |      7.3e-05 |
+---------------+--------------+
| epoch         |      2.73988 |
+---------------+--------------+ - [learning2rank.py:2187:on_log]
2025-06-12 21:03:18,518 - INFO - 
🚂 Training Metrics (Step 130) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -1.38663e+18 |
+---------------+--------------+
| grad_norm     |  2.64355e+17 |
+---------------+--------------+
| learning_rate |      6.9e-05 |
+---------------+--------------+
| epoch         |       2.9711 |
+---------------+--------------+ - [learning2rank.py:2187:on_log]
2025-06-12 21:03:20,282 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [learning2rank.py:2635:evaluate]
2025-06-12 21:06:35,391 - INFO - 
🔍 Evaluation Metrics 🔍
+-------------------+-------------+
| Metric            |       Value |
+===================+=============+
| eval_loss         | -4.3741e+17 |
+-------------------+-------------+
| eval_ndcg         |    0.956946 |
+-------------------+-------------+
| eval_ndcg@25      |    0.787928 |
+-------------------+-------------+
| eval_precision@25 |    0.908571 |
+-------------------+-------------+ - [learning2rank.py:2206:on_evaluate]
2025-06-12 21:06:37,242 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-132 - [learning2rank.py:2759:_save]
2025-06-12 21:06:37,269 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-132 - [learning2rank.py:2764:_save]
2025-06-12 21:06:37,270 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-132:
+---------+--------------------+------------+
|   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:2785:_save]
2025-06-12 21:06:53,565 - INFO - 
🚂 Training Metrics (Step 140) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -1.09894e+19 |
+---------------+--------------+
| grad_norm     |  1.94154e+17 |
+---------------+--------------+
| learning_rate |      6.5e-05 |
+---------------+--------------+
| epoch         |      3.18497 |
+---------------+--------------+ - [learning2rank.py:2187:on_log]
2025-06-12 21:07:07,672 - INFO - 
🚂 Training Metrics (Step 150) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -6.84143e+18 |
+---------------+--------------+
| grad_norm     |  2.59061e+17 |
+---------------+--------------+
| learning_rate |      6.1e-05 |
+---------------+--------------+
| epoch         |      3.41619 |
+---------------+--------------+ - [learning2rank.py:2187:on_log]
2025-06-12 21:07:21,752 - INFO - 
🚂 Training Metrics (Step 160) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -4.95167e+17 |
+---------------+--------------+
| grad_norm     |  2.42175e+17 |
+---------------+--------------+
| learning_rate |      5.6e-05 |
+---------------+--------------+
| epoch         |       3.6474 |
+---------------+--------------+ - [learning2rank.py:2187:on_log]
2025-06-12 21:07:35,824 - INFO - 
🚂 Training Metrics (Step 170) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -3.52079e+17 |
+---------------+--------------+
| grad_norm     |  2.65202e+17 |
+---------------+--------------+
| learning_rate |      5.2e-05 |
+---------------+--------------+
| epoch         |      3.87861 |
+---------------+--------------+ - [learning2rank.py:2187:on_log]
2025-06-12 21:07:43,199 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [learning2rank.py:2635:evaluate]
2025-06-12 21:10:58,474 - INFO - 
🔍 Evaluation Metrics 🔍
+-------------------+--------------+
| Metric            |        Value |
+===================+==============+
| eval_loss         | -4.41614e+17 |
+-------------------+--------------+
| eval_ndcg         |     0.957167 |
+-------------------+--------------+
| eval_ndcg@25      |     0.842648 |
+-------------------+--------------+
| eval_precision@25 |     0.914286 |
+-------------------+--------------+ - [learning2rank.py:2206:on_evaluate]
2025-06-12 21:11:01,532 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-176 - [learning2rank.py:2759:_save]
2025-06-12 21:11:01,560 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-176 - [learning2rank.py:2764:_save]
2025-06-12 21:11:01,561 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-176:
+---------+--------------------+------------+
|   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:2785:_save]
2025-06-12 21:11:12,194 - INFO - 
🚂 Training Metrics (Step 180) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -1.75799e+18 |
+---------------+--------------+
| grad_norm     |  4.09451e+16 |
+---------------+--------------+
| learning_rate |      4.7e-05 |
+---------------+--------------+
| epoch         |      4.09249 |
+---------------+--------------+ - [learning2rank.py:2187:on_log]
2025-06-12 21:11:26,251 - INFO - 
🚂 Training Metrics (Step 190) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -1.50435e+18 |
+---------------+--------------+
| grad_norm     |  9.34133e+17 |
+---------------+--------------+
| learning_rate |      4.2e-05 |
+---------------+--------------+
| epoch         |       4.3237 |
+---------------+--------------+ - [learning2rank.py:2187:on_log]
2025-06-12 21:11:40,349 - INFO - 
🚂 Training Metrics (Step 200) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -7.57569e+17 |
+---------------+--------------+
| grad_norm     |  2.45933e+17 |
+---------------+--------------+
| learning_rate |      3.8e-05 |
+---------------+--------------+
| epoch         |      4.55491 |
+---------------+--------------+ - [learning2rank.py:2187:on_log]
2025-06-12 21:11:54,405 - INFO - 
🚂 Training Metrics (Step 210) 🚂
+---------------+--------------+
| Metric        |        Value |
+===============+==============+
| loss          | -4.55401e+18 |
+---------------+--------------+
| grad_norm     |  1.51256e+17 |
+---------------+--------------+
| learning_rate |      3.3e-05 |
+---------------+--------------+
| epoch         |      4.78613 |
+---------------+--------------+ - [learning2rank.py:2187:on_log]
2025-06-12 21:12:03,394 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-215 - [learning2rank.py:2759:_save]
2025-06-12 21:12:03,424 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-215 - [learning2rank.py:2764:_save]
2025-06-12 21:12:03,425 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-215:
+---------+--------------------+------------+
|   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 | 0.01 MB    |
+---------+--------------------+------------+
|       8 | rng_state.pth      | 0.01 MB    |
+---------+--------------------+------------+ - [learning2rank.py:2785:_save]
2025-06-12 21:12:06,059 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [learning2rank.py:2635:evaluate]
2025-06-12 21:15:21,367 - INFO - 
🔍 Evaluation Metrics 🔍
+-------------------+--------------+
| Metric            |        Value |
+===================+==============+
| eval_loss         | -4.43631e+17 |
+-------------------+--------------+
| eval_ndcg         |      0.95719 |
+-------------------+--------------+
| eval_ndcg@25      |     0.832013 |
+-------------------+--------------+
| eval_precision@25 |     0.913143 |
+-------------------+--------------+ - [learning2rank.py:2206:on_evaluate]
2025-06-12 21:15:24,175 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-215 - [learning2rank.py:2759:_save]
2025-06-12 21:15:24,203 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-215 - [learning2rank.py:2764:_save]
2025-06-12 21:15:24,205 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-215:
+---------+--------------------+------------+
|   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 | 0.01 MB    |
+---------+--------------------+------------+
|       8 | rng_state.pth      | 0.01 MB    |
+---------+--------------------+------------+ - [learning2rank.py:2785:_save]
2025-06-12 21:15:24,455 - INFO - 📂 Loading best model from ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-176 - [learning2rank.py:2841:_load_best_model]
2025-06-12 21:15:24,455 - INFO - 🖥️ Model is on device: cuda:0 - [learning2rank.py:2851:_load_best_model]
2025-06-12 21:15:24,518 - 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:2875:_load_best_model]
2025-06-12 21:15:25,345 - INFO - ✅ Loaded best model weights from ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/checkpoint-176/model.safetensors - [learning2rank.py:2892:_load_best_model]
2025-06-12 21:15:25,385 - INFO - ✔️ Weight for label_embeddings.weight matches between saved and loaded state_dict - [learning2rank.py:2904:_load_best_model]
2025-06-12 21:15:25,441 - INFO - ✔️ Weight for ground_model.base_model.model.model.embed_tokens.weight matches between saved and loaded state_dict - [learning2rank.py:2904:_load_best_model]
2025-06-12 21:15:25,459 - INFO - 
🚂 Training Metrics (Step 215) 🚂
+--------------------------+--------------+
| Metric                   |        Value |
+==========================+==============+
| train_runtime            |      1318.74 |
+--------------------------+--------------+
| train_samples_per_second |        0.656 |
+--------------------------+--------------+
| train_steps_per_second   |        0.163 |
+--------------------------+--------------+
| total_flos               |  9.47661e+15 |
+--------------------------+--------------+
| train_loss               | -2.42904e+18 |
+--------------------------+--------------+
| epoch                    |      4.90173 |
+--------------------------+--------------+ - [learning2rank.py:2187:on_log]
2025-06-12 21:15:25,459 - INFO - ✨ Training Completed! ✨ - [learning2rank.py:2336:on_train_end]
2025-06-12 21:15:25,535 - INFO - 📊 Training loss plot saved as '../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/train_loss_plot.png' - [learning2rank.py:2439:on_train_end]
2025-06-12 21:15:25,598 - INFO - 📊 Evaluation loss plot saved as '../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/eval_loss_plot.png' - [learning2rank.py:2453:on_train_end]
2025-06-12 21:15:25,660 - INFO - 📊 Evaluation metric plot saved as '../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/eval_ndcg@25_plot.png' - [learning2rank.py:2474:on_train_end]
2025-06-12 21:15:25,660 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:109:log_section]
2025-06-12 21:15:25,661 - INFO - +                                 ✨ MODEL SAVING                                 + - [learning2rank.py:110:log_section]
2025-06-12 21:15:25,661 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:113:log_section]
2025-06-12 21:15:25,661 - INFO - 💾 Saving trained model and pushing to Hugging Face Hub... - [learning2rank.py:3961:main]
2025-06-12 21:15:25,661 - INFO - 📁 Creating/using output directory: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b - [learning2rank.py:3159:save_and_push]
2025-06-12 21:15:29,152 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b - [learning2rank.py:2759:_save]
2025-06-12 21:15:29,180 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b - [learning2rank.py:2764:_save]
2025-06-12 21:15:29,183 - 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 | tokenizer.model                          | 0.56 MB    |
+---------+------------------------------------------+------------+
|       4 | tokenizer.json                           | 3.50 MB    |
+---------+------------------------------------------+------------+
|       5 | model.safetensors                        | 4122.74 MB |
+---------+------------------------------------------+------------+
|       6 | eval_ndcg@25_plot.png                    | 0.03 MB    |
+---------+------------------------------------------+------------+
|       7 | config.json                              | 0.38 MB    |
+---------+------------------------------------------+------------+
|       8 | special_tokens_map.json                  | 0.00 MB    |
+---------+------------------------------------------+------------+
|       9 | lookup_table.pt                          | 992.75 MB  |
+---------+------------------------------------------+------------+
|      10 | tokenizer_config.json                    | 0.13 MB    |
+---------+------------------------------------------+------------+
|      11 | train_loss_plot.png                      | 0.04 MB    |
+---------+------------------------------------------+------------+
|      12 | training_l2r_log_2025-06-12_16-06-10.log | 0.05 MB    |
+---------+------------------------------------------+------------+
|      13 | README.md                                | 0.00 MB    |
+---------+------------------------------------------+------------+
|      14 | checkpoint-44/training_args.bin          | 0.01 MB    |
+---------+------------------------------------------+------------+
|      15 | checkpoint-44/optimizer.pt               | 0.00 MB    |
+---------+------------------------------------------+------------+
|      16 | checkpoint-44/model.safetensors          | 4122.74 MB |
+---------+------------------------------------------+------------+
|      17 | checkpoint-44/scaler.pt                  | 0.00 MB    |
+---------+------------------------------------------+------------+
|      18 | checkpoint-44/config.json                | 0.38 MB    |
+---------+------------------------------------------+------------+
|      19 | checkpoint-44/scheduler.pt               | 0.00 MB    |
+---------+------------------------------------------+------------+
|      20 | checkpoint-44/trainer_state.json         | 0.00 MB    |
+---------+------------------------------------------+------------+
|      21 | checkpoint-44/rng_state.pth              | 0.01 MB    |
+---------+------------------------------------------+------------+
|      22 | ground_model/adapter_config.json         | 0.00 MB    |
+---------+------------------------------------------+------------+
|      23 | ground_model/adapter_model.safetensors   | 52.03 MB   |
+---------+------------------------------------------+------------+
|      24 | ground_model/README.md                   | 0.00 MB    |
+---------+------------------------------------------+------------+
|      25 | checkpoint-176/training_args.bin         | 0.01 MB    |
+---------+------------------------------------------+------------+
|      26 | checkpoint-176/optimizer.pt              | 352.39 MB  |
+---------+------------------------------------------+------------+
|      27 | checkpoint-176/model.safetensors         | 4122.74 MB |
+---------+------------------------------------------+------------+
|      28 | checkpoint-176/scaler.pt                 | 0.00 MB    |
+---------+------------------------------------------+------------+
|      29 | checkpoint-176/config.json               | 0.38 MB    |
+---------+------------------------------------------+------------+
|      30 | checkpoint-176/scheduler.pt              | 0.00 MB    |
+---------+------------------------------------------+------------+
|      31 | checkpoint-176/trainer_state.json        | 0.00 MB    |
+---------+------------------------------------------+------------+
|      32 | checkpoint-176/rng_state.pth             | 0.01 MB    |
+---------+------------------------------------------+------------+
|      33 | checkpoint-215/training_args.bin         | 0.01 MB    |
+---------+------------------------------------------+------------+
|      34 | checkpoint-215/optimizer.pt              | 352.39 MB  |
+---------+------------------------------------------+------------+
|      35 | checkpoint-215/model.safetensors         | 4122.74 MB |
+---------+------------------------------------------+------------+
|      36 | checkpoint-215/scaler.pt                 | 0.00 MB    |
+---------+------------------------------------------+------------+
|      37 | checkpoint-215/config.json               | 0.38 MB    |
+---------+------------------------------------------+------------+
|      38 | checkpoint-215/scheduler.pt              | 0.00 MB    |
+---------+------------------------------------------+------------+
|      39 | checkpoint-215/trainer_state.json        | 0.01 MB    |
+---------+------------------------------------------+------------+
|      40 | checkpoint-215/rng_state.pth             | 0.01 MB    |
+---------+------------------------------------------+------------+
|      41 | checkpoint-88/training_args.bin          | 0.01 MB    |
+---------+------------------------------------------+------------+
|      42 | checkpoint-88/optimizer.pt               | 352.39 MB  |
+---------+------------------------------------------+------------+
|      43 | checkpoint-88/model.safetensors          | 4122.74 MB |
+---------+------------------------------------------+------------+
|      44 | checkpoint-88/scaler.pt                  | 0.00 MB    |
+---------+------------------------------------------+------------+
|      45 | checkpoint-88/config.json                | 0.38 MB    |
+---------+------------------------------------------+------------+
|      46 | checkpoint-88/scheduler.pt               | 0.00 MB    |
+---------+------------------------------------------+------------+
|      47 | checkpoint-88/trainer_state.json         | 0.00 MB    |
+---------+------------------------------------------+------------+
|      48 | checkpoint-88/rng_state.pth              | 0.01 MB    |
+---------+------------------------------------------+------------+
|      49 | checkpoint-132/training_args.bin         | 0.01 MB    |
+---------+------------------------------------------+------------+
|      50 | checkpoint-132/optimizer.pt              | 352.39 MB  |
+---------+------------------------------------------+------------+
|      51 | checkpoint-132/model.safetensors         | 4122.74 MB |
+---------+------------------------------------------+------------+
|      52 | checkpoint-132/scaler.pt                 | 0.00 MB    |
+---------+------------------------------------------+------------+
|      53 | checkpoint-132/config.json               | 0.38 MB    |
+---------+------------------------------------------+------------+
|      54 | checkpoint-132/scheduler.pt              | 0.00 MB    |
+---------+------------------------------------------+------------+
|      55 | checkpoint-132/trainer_state.json        | 0.00 MB    |
+---------+------------------------------------------+------------+
|      56 | checkpoint-132/rng_state.pth             | 0.01 MB    |
+---------+------------------------------------------+------------+ - [learning2rank.py:2785:_save]
2025-06-12 21:15:32,942 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b - [learning2rank.py:2759:_save]
2025-06-12 21:15:32,970 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b - [learning2rank.py:2764:_save]
2025-06-12 21:15:32,973 - 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 | tokenizer.model                          | 0.56 MB    |
+---------+------------------------------------------+------------+
|       4 | tokenizer.json                           | 3.50 MB    |
+---------+------------------------------------------+------------+
|       5 | model.safetensors                        | 4122.74 MB |
+---------+------------------------------------------+------------+
|       6 | eval_ndcg@25_plot.png                    | 0.03 MB    |
+---------+------------------------------------------+------------+
|       7 | config.json                              | 0.38 MB    |
+---------+------------------------------------------+------------+
|       8 | special_tokens_map.json                  | 0.00 MB    |
+---------+------------------------------------------+------------+
|       9 | lookup_table.pt                          | 992.75 MB  |
+---------+------------------------------------------+------------+
|      10 | tokenizer_config.json                    | 0.13 MB    |
+---------+------------------------------------------+------------+
|      11 | train_loss_plot.png                      | 0.04 MB    |
+---------+------------------------------------------+------------+
|      12 | training_l2r_log_2025-06-12_16-06-10.log | 0.05 MB    |
+---------+------------------------------------------+------------+
|      13 | README.md                                | 0.00 MB    |
+---------+------------------------------------------+------------+
|      14 | checkpoint-44/training_args.bin          | 0.01 MB    |
+---------+------------------------------------------+------------+
|      15 | checkpoint-44/optimizer.pt               | 0.00 MB    |
+---------+------------------------------------------+------------+
|      16 | checkpoint-44/model.safetensors          | 4122.74 MB |
+---------+------------------------------------------+------------+
|      17 | checkpoint-44/scaler.pt                  | 0.00 MB    |
+---------+------------------------------------------+------------+
|      18 | checkpoint-44/config.json                | 0.38 MB    |
+---------+------------------------------------------+------------+
|      19 | checkpoint-44/scheduler.pt               | 0.00 MB    |
+---------+------------------------------------------+------------+
|      20 | checkpoint-44/trainer_state.json         | 0.00 MB    |
+---------+------------------------------------------+------------+
|      21 | checkpoint-44/rng_state.pth              | 0.01 MB    |
+---------+------------------------------------------+------------+
|      22 | ground_model/adapter_config.json         | 0.00 MB    |
+---------+------------------------------------------+------------+
|      23 | ground_model/adapter_model.safetensors   | 52.03 MB   |
+---------+------------------------------------------+------------+
|      24 | ground_model/README.md                   | 0.00 MB    |
+---------+------------------------------------------+------------+
|      25 | checkpoint-176/training_args.bin         | 0.01 MB    |
+---------+------------------------------------------+------------+
|      26 | checkpoint-176/optimizer.pt              | 352.39 MB  |
+---------+------------------------------------------+------------+
|      27 | checkpoint-176/model.safetensors         | 4122.74 MB |
+---------+------------------------------------------+------------+
|      28 | checkpoint-176/scaler.pt                 | 0.00 MB    |
+---------+------------------------------------------+------------+
|      29 | checkpoint-176/config.json               | 0.38 MB    |
+---------+------------------------------------------+------------+
|      30 | checkpoint-176/scheduler.pt              | 0.00 MB    |
+---------+------------------------------------------+------------+
|      31 | checkpoint-176/trainer_state.json        | 0.00 MB    |
+---------+------------------------------------------+------------+
|      32 | checkpoint-176/rng_state.pth             | 0.01 MB    |
+---------+------------------------------------------+------------+
|      33 | checkpoint-215/training_args.bin         | 0.01 MB    |
+---------+------------------------------------------+------------+
|      34 | checkpoint-215/optimizer.pt              | 352.39 MB  |
+---------+------------------------------------------+------------+
|      35 | checkpoint-215/model.safetensors         | 4122.74 MB |
+---------+------------------------------------------+------------+
|      36 | checkpoint-215/scaler.pt                 | 0.00 MB    |
+---------+------------------------------------------+------------+
|      37 | checkpoint-215/config.json               | 0.38 MB    |
+---------+------------------------------------------+------------+
|      38 | checkpoint-215/scheduler.pt              | 0.00 MB    |
+---------+------------------------------------------+------------+
|      39 | checkpoint-215/trainer_state.json        | 0.01 MB    |
+---------+------------------------------------------+------------+
|      40 | checkpoint-215/rng_state.pth             | 0.01 MB    |
+---------+------------------------------------------+------------+
|      41 | checkpoint-88/training_args.bin          | 0.01 MB    |
+---------+------------------------------------------+------------+
|      42 | checkpoint-88/optimizer.pt               | 352.39 MB  |
+---------+------------------------------------------+------------+
|      43 | checkpoint-88/model.safetensors          | 4122.74 MB |
+---------+------------------------------------------+------------+
|      44 | checkpoint-88/scaler.pt                  | 0.00 MB    |
+---------+------------------------------------------+------------+
|      45 | checkpoint-88/config.json                | 0.38 MB    |
+---------+------------------------------------------+------------+
|      46 | checkpoint-88/scheduler.pt               | 0.00 MB    |
+---------+------------------------------------------+------------+
|      47 | checkpoint-88/trainer_state.json         | 0.00 MB    |
+---------+------------------------------------------+------------+
|      48 | checkpoint-88/rng_state.pth              | 0.01 MB    |
+---------+------------------------------------------+------------+
|      49 | checkpoint-132/training_args.bin         | 0.01 MB    |
+---------+------------------------------------------+------------+
|      50 | checkpoint-132/optimizer.pt              | 352.39 MB  |
+---------+------------------------------------------+------------+
|      51 | checkpoint-132/model.safetensors         | 4122.74 MB |
+---------+------------------------------------------+------------+
|      52 | checkpoint-132/scaler.pt                 | 0.00 MB    |
+---------+------------------------------------------+------------+
|      53 | checkpoint-132/config.json               | 0.38 MB    |
+---------+------------------------------------------+------------+
|      54 | checkpoint-132/scheduler.pt              | 0.00 MB    |
+---------+------------------------------------------+------------+
|      55 | checkpoint-132/trainer_state.json        | 0.00 MB    |
+---------+------------------------------------------+------------+
|      56 | checkpoint-132/rng_state.pth             | 0.01 MB    |
+---------+------------------------------------------+------------+ - [learning2rank.py:2785:_save]
2025-06-12 21:16:57,552 - INFO - 💾 Model saved to: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b - [learning2rank.py:3163:save_and_push]
2025-06-12 21:17:02,465 - INFO - ✅ Model, ground_model, and lookup_table saved to ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b - [core.py:404:save_pretrained]
2025-06-12 21:17:02,465 - INFO - 💾 Model and config explicitly saved to: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b - [learning2rank.py:3169:save_and_push]
2025-06-12 21:17:02,499 - INFO - 🖌️ Tokenizer saved to: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b - [learning2rank.py:3173:save_and_push]
2025-06-12 21:17:03,375 - INFO - 📊 Lookup table saved to: ../tmp/MIMIC4_DEMO/mimic4_l2rtrain_mistral7b/lookup_table.pt - [learning2rank.py:3178:save_and_push]