classification_log_2025-06-04_19-21-10.log

2025-06-04 19:21:10,615 - INFO - ================================================================================ - [multilabel_classify.py:97:log_section]
2025-06-04 19:21:10,616 - INFO - =                      📌 INITIALIZING TRAINING ENVIRONMENT                       = - [multilabel_classify.py:98:log_section]
2025-06-04 19:21:10,616 - INFO - ================================================================================ - [multilabel_classify.py:101:log_section]
2025-06-04 19:21:10,616 - INFO - 🚀 Setting up data paths and environment variables... - [multilabel_classify.py:3313:main]
2025-06-04 19:21:10,616 - INFO - 📂 Using output directory: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:3319:main]
2025-06-04 19:21:10,616 - INFO - 🛠️ Command-line Arguments: - [multilabel_classify.py:343:print_args]
2025-06-04 19:21:10,616 - INFO - 
  🔹 output_dir: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b
  🔹 source_url: XURLs.MIMIC4_DEMO
  🔹 data: mimic4_icd10_full
  🔹 logfile: classification_log
  🔹 base_dir: ../tmp/MIMIC4_DEMO
  🔹 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: multilabel-classify
  🔹 num_train_epochs: 4
  🔹 per_device_train_batch_size: 8
  🔹 per_device_eval_batch_size: 8
  🔹 metric_for_best_model: precision_at_15
  🔹 learning_rate: 0.0001
  🔹 final_lr_scheduling: 1e-06
  🔹 warmup_steps: 500
  🔹 logfile_path: ../tmp/logs/classification_log_2025-06-04_19-21-10.log
  🔹 source: /home/ubuntu/.xcube/data/mimic4_demo - [multilabel_classify.py:344:print_args]
2025-06-04 19:21:10,616 - INFO - ➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖ - [multilabel_classify.py:345:print_args]
2025-06-04 19:21:10,616 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:97:log_section]
2025-06-04 19:21:10,616 - INFO - +                               ✨ LOADING DATASETS                               + - [multilabel_classify.py:98:log_section]
2025-06-04 19:21:10,616 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:101:log_section]
2025-06-04 19:21:10,616 - INFO - 📊 Loading main datasets.... - [multilabel_classify.py:3325:main]
2025-06-04 19:21:19,148 - INFO - 🔍 Total unique labels in dataset: 7942 - [multilabel_classify.py:3115:sample_df_with_full_label_coverage]
2025-06-04 19:21:19,161 - INFO - 🧪 Attempt 1: Sampled 122 rows covering 863 labels. - [multilabel_classify.py:3129:sample_df_with_full_label_coverage]
2025-06-04 19:21:19,170 - INFO - 🧪 Attempt 2: Sampled 122 rows covering 816 labels. - [multilabel_classify.py:3129:sample_df_with_full_label_coverage]
2025-06-04 19:21:19,179 - INFO - 🧪 Attempt 3: Sampled 122 rows covering 885 labels. - [multilabel_classify.py:3129:sample_df_with_full_label_coverage]
2025-06-04 19:21:19,187 - INFO - 🧪 Attempt 4: Sampled 122 rows covering 828 labels. - [multilabel_classify.py:3129:sample_df_with_full_label_coverage]
2025-06-04 19:21:19,196 - INFO - 🧪 Attempt 5: Sampled 122 rows covering 879 labels. - [multilabel_classify.py:3129:sample_df_with_full_label_coverage]
2025-06-04 19:21:19,204 - INFO - 🧪 Attempt 6: Sampled 122 rows covering 852 labels. - [multilabel_classify.py:3129:sample_df_with_full_label_coverage]
2025-06-04 19:21:19,212 - INFO - 🧪 Attempt 7: Sampled 122 rows covering 838 labels. - [multilabel_classify.py:3129:sample_df_with_full_label_coverage]
2025-06-04 19:21:19,221 - INFO - 🧪 Attempt 8: Sampled 122 rows covering 851 labels. - [multilabel_classify.py:3129:sample_df_with_full_label_coverage]
2025-06-04 19:21:19,229 - INFO - 🧪 Attempt 9: Sampled 122 rows covering 825 labels. - [multilabel_classify.py:3129:sample_df_with_full_label_coverage]
2025-06-04 19:21:19,237 - INFO - 🧪 Attempt 10: Sampled 122 rows covering 833 labels. - [multilabel_classify.py:3129:sample_df_with_full_label_coverage]
2025-06-04 19:21:19,237 - INFO - ⚠️ Skipping label coverage fix. 7109 labels are missing. - [multilabel_classify.py:3147:sample_df_with_full_label_coverage]
2025-06-04 19:21:19,237 - INFO - ✅ Final row count: 122 (Valid: 20, Not-valid: 102) - [multilabel_classify.py:3152:sample_df_with_full_label_coverage]
2025-06-04 19:21:19,256 - INFO - ******************************************************************************** - [multilabel_classify.py:97:log_section]
2025-06-04 19:21:19,256 - INFO - *              🌟 STARTING MULTI_LABEL CLASSIFICATION MODEL TRAINING              * - [multilabel_classify.py:98:log_section]
2025-06-04 19:21:19,256 - INFO - ******************************************************************************** - [multilabel_classify.py:101:log_section]
2025-06-04 19:21:19,256 - INFO - 🔐 Loaded authentication token from environment - [multilabel_classify.py:3352:main]
2025-06-04 19:21:19,256 - INFO - 🏷️ Hub Model ID for this Classification task: deb101/mistral-7b-instruct-v0.3-mimic4-adapt-multilabel-classify - [multilabel_classify.py:3356:main]
2025-06-04 19:21:19,256 - INFO - -------------------------------------------------------------------------------- - [multilabel_classify.py:97:log_section]
2025-06-04 19:21:19,256 - INFO - -                            📋 MODEL EXISTENCE CHECK                             - - [multilabel_classify.py:98:log_section]
2025-06-04 19:21:19,256 - INFO - -------------------------------------------------------------------------------- - [multilabel_classify.py:101:log_section]
2025-06-04 19:21:19,257 - INFO - 🔍 Checking model existence locally and on Hugging Face Hub... - [multilabel_classify.py:3230:check_model_existence]
2025-06-04 19:21:19,257 - INFO - ❌ Model not found locally at: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:3237:check_model_existence]
2025-06-04 19:21:19,312 - INFO - ✅ Model exists on Hugging Face Hub with ID: deb101/mistral-7b-instruct-v0.3-mimic4-adapt-multilabel-classify - [multilabel_classify.py:3249:check_model_existence]
2025-06-04 19:21:19,312 - INFO - 📁 Model exists either locally or on Hub - [multilabel_classify.py:3275:check_model_existence]
2025-06-04 19:21:19,312 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:97:log_section]
2025-06-04 19:21:19,312 - INFO - +                           ✨ STARTING FRESH TRAINING                            + - [multilabel_classify.py:98:log_section]
2025-06-04 19:21:19,312 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:101:log_section]
2025-06-04 19:21:19,312 - INFO - 🔄 Starting fresh training (either forced or model not found)... - [multilabel_classify.py:3369:main]
2025-06-04 19:21:19,328 - 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]
2025-06-04 19:21:19,329 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:97:log_section]
2025-06-04 19:21:19,329 - INFO - +                              ✨ LOADING BASE MODEL                              + - [multilabel_classify.py:98:log_section]
2025-06-04 19:21:19,329 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:101:log_section]
2025-06-04 19:21:19,329 - INFO - 📥 Loading pretrained model and tokenizer... - [multilabel_classify.py:3399:main]
2025-06-04 19:21:19,329 - INFO - 🚀 Starting model and tokenizer loading process... - [multilabel_classify.py:1216:load_base_model_and_tokenizer]
2025-06-04 19:21:19,329 - 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"
}
 - [multilabel_classify.py:1225:load_base_model_and_tokenizer]
2025-06-04 19:21:19,330 - INFO - 🔤 Loading tokenizer for model: deb101/mistral-7b-instruct-v0.3-mimic4-adapt... - [multilabel_classify.py:1229:load_base_model_and_tokenizer]
2025-06-04 19:21:19,597 - INFO - 🔍 Checking if deb101/mistral-7b-instruct-v0.3-mimic4-adapt is a PEFT model... - [multilabel_classify.py:1241:load_base_model_and_tokenizer]
2025-06-04 19:21:19,616 - INFO - ✅ Detected PEFT model. Base model: mistralai/Mistral-7B-Instruct-v0.3 - [multilabel_classify.py:1245:load_base_model_and_tokenizer]
2025-06-04 19:21:19,616 - INFO - 🔍 Loading model configuration for mistralai/Mistral-7B-Instruct-v0.3... - [multilabel_classify.py:1255:load_base_model_and_tokenizer]
2025-06-04 19:21:19,637 - INFO - Model type: mistral, Architectures: ['MistralForCausalLM'] - [multilabel_classify.py:1261:load_base_model_and_tokenizer]
2025-06-04 19:21:19,637 - INFO - 🧠 Loading base model: mistralai/Mistral-7B-Instruct-v0.3... - [multilabel_classify.py:1324:load_base_model_and_tokenizer]
2025-06-04 19:21:20,158 - 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]
2025-06-04 19:21:25,492 - INFO - 🧩 Loading PEFT adapters for deb101/mistral-7b-instruct-v0.3-mimic4-adapt... - [multilabel_classify.py:1339:load_base_model_and_tokenizer]
2025-06-04 19:21:25,727 - INFO - 🔧 Before enabling PEFT adapters for training - [multilabel_classify.py:1341:load_base_model_and_tokenizer]
2025-06-04 19:21:25,732 - INFO - 🔧 After Enabling PEFT adapters for training - [multilabel_classify.py:1348:load_base_model_and_tokenizer]
2025-06-04 19:21:25,735 - INFO - ✅ Model and tokenizer successfully loaded! - [multilabel_classify.py:1389:load_base_model_and_tokenizer]
2025-06-04 19:21:25,735 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:97:log_section]
2025-06-04 19:21:25,735 - INFO - +                              ✨ DATA PREPROCESSING                              + - [multilabel_classify.py:98:log_section]
2025-06-04 19:21:25,735 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:101:log_section]
2025-06-04 19:21:25,735 - INFO - 🔄 Loading and preprocessing training data... - [multilabel_classify.py:3407:main]
2025-06-04 19:21:25,739 - INFO - Total number of labels: 833 - [multilabel_classify.py:1017:preprocess_data]
2025-06-04 19:21:25,739 - INFO - Rare labels (freq < 50): 832 - [multilabel_classify.py:1018:preprocess_data]
2025-06-04 19:21:25,739 - INFO - Not rare labels (freq >= 50): 1 - [multilabel_classify.py:1019:preprocess_data]
2025-06-04 19:21:25,740 - INFO - Label partitions and classes saved to ../tmp/MIMIC4_DEMO/labels_partition.json - [multilabel_classify.py:1020:preprocess_data]
2025-06-04 19:21:27,056 - INFO - The size of training set: 567 - [multilabel_classify.py:1116:preprocess_data]
2025-06-04 19:21:27,056 - INFO - The size of Evaluation set: 136 - [multilabel_classify.py:1117:preprocess_data]
2025-06-04 19:21:27,061 - INFO - Number of unique ICD-10 codes: 833 - [multilabel_classify.py:3413:main]
2025-06-04 19:21:27,061 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:97:log_section]
2025-06-04 19:21:27,062 - INFO - +                             ✨ MODEL INITIALIZATION                             + - [multilabel_classify.py:98:log_section]
2025-06-04 19:21:27,062 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:101:log_section]
2025-06-04 19:21:27,062 - INFO - 🧠 Initializing custom L2R model for outputting per-token relevance scores per ICD-10 codes. - [multilabel_classify.py:3416:main]
2025-06-04 19:21:27,062 - INFO - Will now start to create Multilabel-Classification Model from the base model - [multilabel_classify.py:535:__init__]
2025-06-04 19:21:27,065 - INFO - Trainable params: 6815744 / 3765178368 (0.18%) - [multilabel_classify.py:587:compute_trainable_params]
2025-06-04 19:21:27,403 - INFO - Creating the Multi-Label Classification Model from base model mistralai/Mistral-7B-Instruct-v0.3 completed!!! - [multilabel_classify.py:577:__init__]
2025-06-04 19:21:27,407 - INFO - Trainable params: 84177025 / 3842539649 (2.19%) - [multilabel_classify.py:587:compute_trainable_params]
2025-06-04 19:21:27,407 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:97:log_section]
2025-06-04 19:21:27,407 - INFO - +                             ✨ TRAINING PREPARATION                             + - [multilabel_classify.py:98:log_section]
2025-06-04 19:21:27,407 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:101:log_section]
2025-06-04 19:21:27,407 - INFO - ⚙️ Preparing training components and optimizers... - [multilabel_classify.py:3423:main]
2025-06-04 19:21:27,464 - INFO - 🖥️ Device: NVIDIA GH200 480GB - [multilabel_classify.py:864:log_training_configuration]
2025-06-04 19:21:27,464 - INFO - 🔋 CUDA Available: True - [multilabel_classify.py:867:log_training_configuration]
2025-06-04 19:21:27,464 - INFO - 💾 CUDA Device Count: 1 - [multilabel_classify.py:868:log_training_configuration]
2025-06-04 19:21:27,466 - INFO - 
📋 Training Configuration 📋
+----------+-----------------------------+------------------------------------------------------------------+
| 🌟 Emoji |         🏷️ Parameter         |                             📊 Value                             |
+----------+-----------------------------+------------------------------------------------------------------+
|    📁    |      Output Directory       |           ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b           |
|    🔁    |       Training Epochs       |                                4                                 |
|    🏋️     |      Train Batch Size       |                                8                                 |
|    🔍    |       Eval Batch Size       |                                8                                 |
|    📊    | Gradient Accumulation Steps |                                4                                 |
|    🚀    |        Learning Rate        |                              0.0001                              |
|    🌅    |        Warmup Steps         |                               500                                |
|    💾    |        Save Strategy        |                              epoch                               |
|    💾    |      Save Total Limit       |                                10                                |
|    📊    |     Evaluation Strategy     |                              epoch                               |
|    🎯    |      Best Model Metric      |                         precision_at_15                          |
|    📝    |      Logging Strategy       |                      steps (every 10 steps)                      |
|    🌐    |         Push to Hub         |                               True                               |
|    🌐    |        Hub Model ID         | deb101/mistral-7b-instruct-v0.3-mimic4-adapt-multilabel-classify |
|    🔢    |       Steps per Epoch       |                                17                                |
|    🔢    |    Total Training Steps     |                                68                                |
|    🔢    |      Evaluation Steps       |                                17                                |
|    📊    |    Training Dataset Size    |                          567 samples 🏋️                           |
|    📊    |   Evaluation Dataset Size   |                          136 samples 🔍                          |
+----------+-----------------------------+------------------------------------------------------------------+ - [multilabel_classify.py:856:log_training_args]
2025-06-04 19:21:27,466 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:97:log_section]
2025-06-04 19:21:27,467 - INFO - +                                ✨ MODEL TRAINING                                + - [multilabel_classify.py:98:log_section]
2025-06-04 19:21:27,467 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:101:log_section]
2025-06-04 19:21:27,467 - INFO - 🏋️ Starting model training process... - [multilabel_classify.py:3445:main]
2025-06-04 19:21:27,513 - INFO - We are registering the tokenizer deb101/mistral-7b-instruct-v0.3-mimic4-adapt in Custom Trainer - [multilabel_classify.py:1961:__init__]
2025-06-04 19:21:27,765 - INFO - 🚀 Starting Training... - [multilabel_classify.py:1615:on_train_begin]
2025-06-04 19:21:48,179 - INFO - 
🚂 Training Metrics (Step 10) 🚂
+---------------+---------+
| Metric        |   Value |
+===============+=========+
| loss          |  0.6501 |
+---------------+---------+
| grad_norm     | 7.11264 |
+---------------+---------+
| learning_rate |   2e-06 |
+---------------+---------+
| epoch         | 0.56338 |
+---------------+---------+ - [multilabel_classify.py:1809:on_log]
2025-06-04 19:22:02,156 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [multilabel_classify.py:1973:evaluate]
2025-06-04 19:22:36,988 - INFO - 
🔍 Evaluation Metrics 🔍
+-------------------------------+----------+
| Metric                        |    Value |
+===============================+==========+
| eval_f1_micro                 |        0 |
+-------------------------------+----------+
| eval_f1_macro                 |        0 |
+-------------------------------+----------+
| eval_precision_at_5           | 0.011765 |
+-------------------------------+----------+
| eval_recall_at_5              | 0.003995 |
+-------------------------------+----------+
| eval_precision_at_8           | 0.020221 |
+-------------------------------+----------+
| eval_recall_at_8              | 0.008339 |
+-------------------------------+----------+
| eval_precision_at_15          | 0.023039 |
+-------------------------------+----------+
| eval_recall_at_15             |  0.01855 |
+-------------------------------+----------+
| eval_rare_f1_micro            |        0 |
+-------------------------------+----------+
| eval_rare_f1_macro            |        0 |
+-------------------------------+----------+
| eval_rare_precision           |        0 |
+-------------------------------+----------+
| eval_rare_recall              |        0 |
+-------------------------------+----------+
| eval_rare_precision_at_5      | 0.014706 |
+-------------------------------+----------+
| eval_rare_recall_at_5         | 0.004619 |
+-------------------------------+----------+
| eval_rare_precision_at_8      | 0.018382 |
+-------------------------------+----------+
| eval_rare_recall_at_8         | 0.008006 |
+-------------------------------+----------+
| eval_rare_precision_at_15     | 0.020588 |
+-------------------------------+----------+
| eval_rare_recall_at_15        | 0.017777 |
+-------------------------------+----------+
| eval_not_rare_f1_micro        | 0.595588 |
+-------------------------------+----------+
| eval_not_rare_f1_macro        | 0.373272 |
+-------------------------------+----------+
| eval_not_rare_precision       | 0.595588 |
+-------------------------------+----------+
| eval_not_rare_recall          | 0.595588 |
+-------------------------------+----------+
| eval_not_rare_precision_at_5  | 0.080882 |
+-------------------------------+----------+
| eval_not_rare_recall_at_5     | 0.404412 |
+-------------------------------+----------+
| eval_not_rare_precision_at_8  | 0.050551 |
+-------------------------------+----------+
| eval_not_rare_recall_at_8     | 0.404412 |
+-------------------------------+----------+
| eval_not_rare_precision_at_15 | 0.026961 |
+-------------------------------+----------+
| eval_not_rare_recall_at_15    | 0.404412 |
+-------------------------------+----------+
| eval_loss                     | 0.219905 |
+-------------------------------+----------+ - [multilabel_classify.py:1828:on_evaluate]
2025-06-04 19:22:38,343 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-18 - [multilabel_classify.py:2066:_save]
2025-06-04 19:22:38,344 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-18 - [multilabel_classify.py:2071:_save]
2025-06-04 19:22:38,346 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-18:
+---------+-------------------+------------+
|   Index | Saved File        | Size       |
+=========+===================+============+
|       1 | training_args.bin | 0.01 MB    |
+---------+-------------------+------------+
|       2 | model.safetensors | 4267.74 MB |
+---------+-------------------+------------+
|       3 | config.json       | 0.00 MB    |
+---------+-------------------+------------+ - [multilabel_classify.py:2088:_save]
2025-06-04 19:22:44,363 - INFO - 
🚂 Training Metrics (Step 20) 🚂
+---------------+---------+
| Metric        |   Value |
+===============+=========+
| loss          |  0.3431 |
+---------------+---------+
| grad_norm     | 2.48011 |
+---------------+---------+
| learning_rate |   4e-06 |
+---------------+---------+
| epoch         | 1.11268 |
+---------------+---------+ - [multilabel_classify.py:1809:on_log]
2025-06-04 19:23:02,442 - INFO - 
🚂 Training Metrics (Step 30) 🚂
+---------------+----------+
| Metric        |    Value |
+===============+==========+
| loss          |    0.124 |
+---------------+----------+
| grad_norm     | 0.291574 |
+---------------+----------+
| learning_rate |    6e-06 |
+---------------+----------+
| epoch         |  1.67606 |
+---------------+----------+ - [multilabel_classify.py:1809:on_log]
2025-06-04 19:23:12,766 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [multilabel_classify.py:1973:evaluate]
2025-06-04 19:23:48,300 - INFO - 
🔍 Evaluation Metrics 🔍
+-------------------------------+----------+
| Metric                        |    Value |
+===============================+==========+
| eval_f1_micro                 |        0 |
+-------------------------------+----------+
| eval_f1_macro                 |        0 |
+-------------------------------+----------+
| eval_precision_at_5           | 0.020588 |
+-------------------------------+----------+
| eval_recall_at_5              | 0.006539 |
+-------------------------------+----------+
| eval_precision_at_8           | 0.020221 |
+-------------------------------+----------+
| eval_recall_at_8              | 0.010792 |
+-------------------------------+----------+
| eval_precision_at_15          | 0.018627 |
+-------------------------------+----------+
| eval_recall_at_15             | 0.018112 |
+-------------------------------+----------+
| eval_rare_f1_micro            |        0 |
+-------------------------------+----------+
| eval_rare_f1_macro            |        0 |
+-------------------------------+----------+
| eval_rare_precision           |        0 |
+-------------------------------+----------+
| eval_rare_recall              |        0 |
+-------------------------------+----------+
| eval_rare_precision_at_5      | 0.016176 |
+-------------------------------+----------+
| eval_rare_recall_at_5         | 0.006962 |
+-------------------------------+----------+
| eval_rare_precision_at_8      | 0.020221 |
+-------------------------------+----------+
| eval_rare_recall_at_8         | 0.010903 |
+-------------------------------+----------+
| eval_rare_precision_at_15     | 0.021569 |
+-------------------------------+----------+
| eval_rare_recall_at_15        | 0.019736 |
+-------------------------------+----------+
| eval_not_rare_f1_micro        | 0.595588 |
+-------------------------------+----------+
| eval_not_rare_f1_macro        | 0.373272 |
+-------------------------------+----------+
| eval_not_rare_precision       | 0.595588 |
+-------------------------------+----------+
| eval_not_rare_recall          | 0.595588 |
+-------------------------------+----------+
| eval_not_rare_precision_at_5  | 0.080882 |
+-------------------------------+----------+
| eval_not_rare_recall_at_5     | 0.404412 |
+-------------------------------+----------+
| eval_not_rare_precision_at_8  | 0.050551 |
+-------------------------------+----------+
| eval_not_rare_recall_at_8     | 0.404412 |
+-------------------------------+----------+
| eval_not_rare_precision_at_15 | 0.026961 |
+-------------------------------+----------+
| eval_not_rare_recall_at_15    | 0.404412 |
+-------------------------------+----------+
| eval_loss                     | 0.122365 |
+-------------------------------+----------+ - [multilabel_classify.py:1828:on_evaluate]
2025-06-04 19:23:49,563 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-36 - [multilabel_classify.py:2066:_save]
2025-06-04 19:23:49,564 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-36 - [multilabel_classify.py:2071:_save]
2025-06-04 19:23:49,565 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-36:
+---------+-------------------+------------+
|   Index | Saved File        | Size       |
+=========+===================+============+
|       1 | training_args.bin | 0.01 MB    |
+---------+-------------------+------------+
|       2 | model.safetensors | 4267.74 MB |
+---------+-------------------+------------+
|       3 | config.json       | 0.00 MB    |
+---------+-------------------+------------+ - [multilabel_classify.py:2088:_save]
2025-06-04 19:23:59,247 - INFO - 
🚂 Training Metrics (Step 40) 🚂
+---------------+----------+
| Metric        |    Value |
+===============+==========+
| loss          |   0.1106 |
+---------------+----------+
| grad_norm     | 0.465793 |
+---------------+----------+
| learning_rate |    8e-06 |
+---------------+----------+
| epoch         |  2.22535 |
+---------------+----------+ - [multilabel_classify.py:1809:on_log]
2025-06-04 19:24:17,296 - INFO - 
🚂 Training Metrics (Step 50) 🚂
+---------------+----------+
| Metric        |    Value |
+===============+==========+
| loss          |   0.1083 |
+---------------+----------+
| grad_norm     | 0.045582 |
+---------------+----------+
| learning_rate |    1e-05 |
+---------------+----------+
| epoch         |  2.78873 |
+---------------+----------+ - [multilabel_classify.py:1809:on_log]
2025-06-04 19:24:24,041 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [multilabel_classify.py:1973:evaluate]
2025-06-04 19:24:58,992 - INFO - 
🔍 Evaluation Metrics 🔍
+-------------------------------+----------+
| Metric                        |    Value |
+===============================+==========+
| eval_f1_micro                 |        0 |
+-------------------------------+----------+
| eval_f1_macro                 |        0 |
+-------------------------------+----------+
| eval_precision_at_5           | 0.038235 |
+-------------------------------+----------+
| eval_recall_at_5              | 0.015452 |
+-------------------------------+----------+
| eval_precision_at_8           | 0.036765 |
+-------------------------------+----------+
| eval_recall_at_8              | 0.023271 |
+-------------------------------+----------+
| eval_precision_at_15          | 0.033824 |
+-------------------------------+----------+
| eval_recall_at_15             | 0.036379 |
+-------------------------------+----------+
| eval_rare_f1_micro            |        0 |
+-------------------------------+----------+
| eval_rare_f1_macro            |        0 |
+-------------------------------+----------+
| eval_rare_precision           |        0 |
+-------------------------------+----------+
| eval_rare_recall              |        0 |
+-------------------------------+----------+
| eval_rare_precision_at_5      | 0.038235 |
+-------------------------------+----------+
| eval_rare_recall_at_5         | 0.015345 |
+-------------------------------+----------+
| eval_rare_precision_at_8      | 0.034007 |
+-------------------------------+----------+
| eval_rare_recall_at_8         | 0.020342 |
+-------------------------------+----------+
| eval_rare_precision_at_15     | 0.027941 |
+-------------------------------+----------+
| eval_rare_recall_at_15        | 0.028912 |
+-------------------------------+----------+
| eval_not_rare_f1_micro        | 0.595588 |
+-------------------------------+----------+
| eval_not_rare_f1_macro        | 0.373272 |
+-------------------------------+----------+
| eval_not_rare_precision       | 0.595588 |
+-------------------------------+----------+
| eval_not_rare_recall          | 0.595588 |
+-------------------------------+----------+
| eval_not_rare_precision_at_5  | 0.080882 |
+-------------------------------+----------+
| eval_not_rare_recall_at_5     | 0.404412 |
+-------------------------------+----------+
| eval_not_rare_precision_at_8  | 0.050551 |
+-------------------------------+----------+
| eval_not_rare_recall_at_8     | 0.404412 |
+-------------------------------+----------+
| eval_not_rare_precision_at_15 | 0.026961 |
+-------------------------------+----------+
| eval_not_rare_recall_at_15    | 0.404412 |
+-------------------------------+----------+
| eval_loss                     | 0.107356 |
+-------------------------------+----------+ - [multilabel_classify.py:1828:on_evaluate]
2025-06-04 19:25:00,219 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-54 - [multilabel_classify.py:2066:_save]
2025-06-04 19:25:00,220 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-54 - [multilabel_classify.py:2071:_save]
2025-06-04 19:25:00,221 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-54:
+---------+-------------------+------------+
|   Index | Saved File        | Size       |
+=========+===================+============+
|       1 | training_args.bin | 0.01 MB    |
+---------+-------------------+------------+
|       2 | model.safetensors | 4267.74 MB |
+---------+-------------------+------------+
|       3 | config.json       | 0.00 MB    |
+---------+-------------------+------------+ - [multilabel_classify.py:2088:_save]
2025-06-04 19:25:13,465 - INFO - 
🚂 Training Metrics (Step 60) 🚂
+---------------+----------+
| Metric        |    Value |
+===============+==========+
| loss          |   0.1035 |
+---------------+----------+
| grad_norm     | 0.185712 |
+---------------+----------+
| learning_rate |  1.2e-05 |
+---------------+----------+
| epoch         |  3.33803 |
+---------------+----------+ - [multilabel_classify.py:1809:on_log]
2025-06-04 19:25:29,148 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-68 - [multilabel_classify.py:2066:_save]
2025-06-04 19:25:29,149 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-68 - [multilabel_classify.py:2071:_save]
2025-06-04 19:25:29,150 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-68:
+---------+-------------------+------------+
|   Index | Saved File        | Size       |
+=========+===================+============+
|       1 | training_args.bin | 0.01 MB    |
+---------+-------------------+------------+
|       2 | model.safetensors | 4267.74 MB |
+---------+-------------------+------------+
|       3 | config.json       | 0.00 MB    |
+---------+-------------------+------------+ - [multilabel_classify.py:2088:_save]
2025-06-04 19:25:29,466 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [multilabel_classify.py:1973:evaluate]
2025-06-04 19:26:04,418 - INFO - 
🔍 Evaluation Metrics 🔍
+-------------------------------+----------+
| Metric                        |    Value |
+===============================+==========+
| eval_f1_micro                 |        0 |
+-------------------------------+----------+
| eval_f1_macro                 |        0 |
+-------------------------------+----------+
| eval_precision_at_5           | 0.132353 |
+-------------------------------+----------+
| eval_recall_at_5              | 0.050205 |
+-------------------------------+----------+
| eval_precision_at_8           | 0.106618 |
+-------------------------------+----------+
| eval_recall_at_8              | 0.067604 |
+-------------------------------+----------+
| eval_precision_at_15          | 0.078922 |
+-------------------------------+----------+
| eval_recall_at_15             | 0.088833 |
+-------------------------------+----------+
| eval_rare_f1_micro            |        0 |
+-------------------------------+----------+
| eval_rare_f1_macro            |        0 |
+-------------------------------+----------+
| eval_rare_precision           |        0 |
+-------------------------------+----------+
| eval_rare_recall              |        0 |
+-------------------------------+----------+
| eval_rare_precision_at_5      | 0.069118 |
+-------------------------------+----------+
| eval_rare_recall_at_5         | 0.030581 |
+-------------------------------+----------+
| eval_rare_precision_at_8      | 0.057904 |
+-------------------------------+----------+
| eval_rare_recall_at_8         |  0.03551 |
+-------------------------------+----------+
| eval_rare_precision_at_15     | 0.053922 |
+-------------------------------+----------+
| eval_rare_recall_at_15        | 0.058368 |
+-------------------------------+----------+
| eval_not_rare_f1_micro        | 0.595588 |
+-------------------------------+----------+
| eval_not_rare_f1_macro        | 0.373272 |
+-------------------------------+----------+
| eval_not_rare_precision       | 0.595588 |
+-------------------------------+----------+
| eval_not_rare_recall          | 0.595588 |
+-------------------------------+----------+
| eval_not_rare_precision_at_5  | 0.080882 |
+-------------------------------+----------+
| eval_not_rare_recall_at_5     | 0.404412 |
+-------------------------------+----------+
| eval_not_rare_precision_at_8  | 0.050551 |
+-------------------------------+----------+
| eval_not_rare_recall_at_8     | 0.404412 |
+-------------------------------+----------+
| eval_not_rare_precision_at_15 | 0.026961 |
+-------------------------------+----------+
| eval_not_rare_recall_at_15    | 0.404412 |
+-------------------------------+----------+
| eval_loss                     | 0.104864 |
+-------------------------------+----------+ - [multilabel_classify.py:1828:on_evaluate]
2025-06-04 19:26:08,196 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-68 - [multilabel_classify.py:2066:_save]
2025-06-04 19:26:08,198 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-68 - [multilabel_classify.py:2071:_save]
2025-06-04 19:26:08,199 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-68:
+---------+--------------------+------------+
|   Index | Saved File         | Size       |
+=========+====================+============+
|       1 | training_args.bin  | 0.01 MB    |
+---------+--------------------+------------+
|       2 | optimizer.pt       | 642.30 MB  |
+---------+--------------------+------------+
|       3 | model.safetensors  | 4267.74 MB |
+---------+--------------------+------------+
|       4 | scaler.pt          | 0.00 MB    |
+---------+--------------------+------------+
|       5 | config.json        | 0.00 MB    |
+---------+--------------------+------------+
|       6 | scheduler.pt       | 0.00 MB    |
+---------+--------------------+------------+
|       7 | trainer_state.json | 0.01 MB    |
+---------+--------------------+------------+
|       8 | rng_state.pth      | 0.01 MB    |
+---------+--------------------+------------+ - [multilabel_classify.py:2088:_save]
2025-06-04 19:26:08,600 - INFO - 📂 Loading best model from ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-68 - [multilabel_classify.py:2140:_load_best_model]
2025-06-04 19:26:08,600 - INFO - 🖥️ Model is on device: cuda:0 - [multilabel_classify.py:2150:_load_best_model]
2025-06-04 19:26:08,663 - INFO - 🔑 Key order comparison:
+---------+--------------------------------------------+--------------------------------------------------------------------------------------+
|   Index | Saved state_dict Keys                      | Model state_dict Keys                                                                |
+=========+============================================+======================================================================================+
|       1 | attention.in_proj_bias                     | boost_mul                                                                            |
+---------+--------------------------------------------+--------------------------------------------------------------------------------------+
|       2 | attention.in_proj_weight                   | boost_add                                                                            |
+---------+--------------------------------------------+--------------------------------------------------------------------------------------+
|       3 | attention.out_proj.bias                    | base_model.base_model.model.model.embed_tokens.weight                                |
+---------+--------------------------------------------+--------------------------------------------------------------------------------------+
|       4 | attention.out_proj.weight                  | base_model.base_model.model.model.layers.0.self_attn.q_proj.base_layer.weight        |
+---------+--------------------------------------------+--------------------------------------------------------------------------------------+
|       5 | base_model.base_model.model.lm_head.weight | base_model.base_model.model.model.layers.0.self_attn.q_proj.base_layer.weight.absmax |
+---------+--------------------------------------------+--------------------------------------------------------------------------------------+ - [multilabel_classify.py:2174:_load_best_model]
2025-06-04 19:26:09,667 - INFO - ✅ Loaded best model weights from ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-68/model.safetensors - [multilabel_classify.py:2191:_load_best_model]
2025-06-04 19:26:09,692 - INFO - ✔️ Weight for boost_mul matches between saved and loaded state_dict - [multilabel_classify.py:2203:_load_best_model]
2025-06-04 19:26:09,714 - INFO - ✔️ Weight for boost_add matches between saved and loaded state_dict - [multilabel_classify.py:2203:_load_best_model]
2025-06-04 19:26:09,728 - INFO - 
🚂 Training Metrics (Step 68) 🚂
+--------------------------+----------+
| Metric                   |    Value |
+==========================+==========+
| train_runtime            |  281.964 |
+--------------------------+----------+
| train_samples_per_second |    8.044 |
+--------------------------+----------+
| train_steps_per_second   |    0.241 |
+--------------------------+----------+
| total_flos               |        0 |
+--------------------------+----------+
| train_loss               | 0.223955 |
+--------------------------+----------+
| epoch                    |  3.78873 |
+--------------------------+----------+ - [multilabel_classify.py:1809:on_log]
2025-06-04 19:26:09,728 - INFO - ✨ Training Completed! ✨ - [multilabel_classify.py:1682:on_train_end]
2025-06-04 19:26:09,795 - INFO - 📊 Training loss plot saved as '../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/train_loss_plot.png' - [multilabel_classify.py:1878:on_train_end]
2025-06-04 19:26:09,853 - INFO - 📊 Evaluation loss plot saved as '../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/eval_loss_plot.png' - [multilabel_classify.py:1892:on_train_end]
2025-06-04 19:26:09,912 - INFO - 📊 Evaluation metric plot saved as '../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/eval_precision_at_15_plot.png' - [multilabel_classify.py:1913:on_train_end]
2025-06-04 19:26:09,912 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:97:log_section]
2025-06-04 19:26:09,912 - INFO - +                                 ✨ MODEL SAVING                                 + - [multilabel_classify.py:98:log_section]
2025-06-04 19:26:09,912 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:101:log_section]
2025-06-04 19:26:09,912 - INFO - 💾 Saving trained model and pushing to Hugging Face Hub... - [multilabel_classify.py:3459:main]
2025-06-04 19:26:09,912 - INFO - 📁 Creating/using output directory: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2666:save_and_push]
2025-06-04 19:26:11,119 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2066:_save]
2025-06-04 19:26:11,121 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2071:_save]
2025-06-04 19:26:11,122 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b:
+---------+-------------------------------+------------+
|   Index | Saved File                    | Size       |
+=========+===============================+============+
|       1 | eval_loss_plot.png            | 0.03 MB    |
+---------+-------------------------------+------------+
|       2 | training_args.bin             | 0.01 MB    |
+---------+-------------------------------+------------+
|       3 | model.safetensors             | 4267.74 MB |
+---------+-------------------------------+------------+
|       4 | config.json                   | 0.00 MB    |
+---------+-------------------------------+------------+
|       5 | train_loss_plot.png           | 0.02 MB    |
+---------+-------------------------------+------------+
|       6 | eval_precision_at_15_plot.png | 0.03 MB    |
+---------+-------------------------------+------------+ - [multilabel_classify.py:2088:_save]
2025-06-04 19:26:14,931 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2066:_save]
2025-06-04 19:26:14,932 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2071:_save]
2025-06-04 19:26:14,933 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b:
+---------+-------------------------------+------------+
|   Index | Saved File                    | Size       |
+=========+===============================+============+
|       1 | eval_loss_plot.png            | 0.03 MB    |
+---------+-------------------------------+------------+
|       2 | training_args.bin             | 0.01 MB    |
+---------+-------------------------------+------------+
|       3 | model.safetensors             | 4267.74 MB |
+---------+-------------------------------+------------+
|       4 | config.json                   | 0.00 MB    |
+---------+-------------------------------+------------+
|       5 | train_loss_plot.png           | 0.02 MB    |
+---------+-------------------------------+------------+
|       6 | eval_precision_at_15_plot.png | 0.03 MB    |
+---------+-------------------------------+------------+ - [multilabel_classify.py:2088:_save]
2025-06-04 19:27:37,188 - INFO - 💾 Model saved to: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2670:save_and_push]
2025-06-04 19:27:37,217 - INFO - 🖌️ Tokenizer saved to: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2674:save_and_push]