2025-06-05 15:38:15,054 - INFO - ================================================================================ - [multilabel_classify.py:100:log_section] 2025-06-05 15:38:15,054 - INFO - = ๐Ÿ“Œ INITIALIZING TRAINING ENVIRONMENT = - [multilabel_classify.py:101:log_section] 2025-06-05 15:38:15,054 - INFO - ================================================================================ - [multilabel_classify.py:104:log_section] 2025-06-05 15:38:15,055 - INFO - ๐Ÿš€ Setting up data paths and environment variables... - [multilabel_classify.py:3560:main] 2025-06-05 15:38:15,055 - INFO - ๐Ÿ“‚ Using output directory: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:3566:main] 2025-06-05 15:38:15,055 - INFO - ๐Ÿ› ๏ธ Command-line Arguments: - [multilabel_classify.py:368:print_args] 2025-06-05 15:38:15,055 - INFO - ๐Ÿ”น output_dir: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b ๐Ÿ”น source_url: XURLs.MIMIC4_DEMO ๐Ÿ”น data: mimic4_icd10_full ๐Ÿ”น logfile: classification_log ๐Ÿ”น base_dir: ../tmp/MIMIC4_DEMO ๐Ÿ”น hub_model_id: deb101/mistral-7b-instruct-v0.3-mimic4-adapt ๐Ÿ”น model_name: mistralai/Mistral-7B-Instruct-v0.3 ๐Ÿ”น max_length: 512 ๐Ÿ”น do_fresh_training: True ๐Ÿ”น load_from_checkpoint: True ๐Ÿ”น task: multilabel-classify ๐Ÿ”น num_train_epochs: 7 ๐Ÿ”น per_device_train_batch_size: 8 ๐Ÿ”น per_device_eval_batch_size: 8 ๐Ÿ”น metric_for_best_model: precision_at_15 ๐Ÿ”น learning_rate: 0.0001 ๐Ÿ”น final_lr_scheduling: 1e-06 ๐Ÿ”น warmup_steps: 50 ๐Ÿ”น logfile_path: ../tmp/logs/classification_log_2025-06-05_15-38-15.log ๐Ÿ”น source: /home/ubuntu/.xcube/data/mimic4_demo - [multilabel_classify.py:369:print_args] 2025-06-05 15:38:15,055 - INFO - โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž–โž– - [multilabel_classify.py:370:print_args] 2025-06-05 15:38:15,055 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:100:log_section] 2025-06-05 15:38:15,055 - INFO - + โœจ LOADING DATASETS + - [multilabel_classify.py:101:log_section] 2025-06-05 15:38:15,055 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:104:log_section] 2025-06-05 15:38:15,055 - INFO - ๐Ÿ“Š Loading main datasets.... - [multilabel_classify.py:3572:main] 2025-06-05 15:38:23,640 - INFO - ๐Ÿ” Total unique labels in dataset: 7942 - [multilabel_classify.py:3353:sample_df_with_full_label_coverage] 2025-06-05 15:38:23,653 - INFO - ๐Ÿงช Attempt 1: Sampled 122 rows covering 863 labels. - [multilabel_classify.py:3367:sample_df_with_full_label_coverage] 2025-06-05 15:38:23,663 - INFO - ๐Ÿงช Attempt 2: Sampled 122 rows covering 816 labels. - [multilabel_classify.py:3367:sample_df_with_full_label_coverage] 2025-06-05 15:38:23,672 - INFO - ๐Ÿงช Attempt 3: Sampled 122 rows covering 885 labels. - [multilabel_classify.py:3367:sample_df_with_full_label_coverage] 2025-06-05 15:38:23,682 - INFO - ๐Ÿงช Attempt 4: Sampled 122 rows covering 828 labels. - [multilabel_classify.py:3367:sample_df_with_full_label_coverage] 2025-06-05 15:38:23,690 - INFO - ๐Ÿงช Attempt 5: Sampled 122 rows covering 879 labels. - [multilabel_classify.py:3367:sample_df_with_full_label_coverage] 2025-06-05 15:38:23,699 - INFO - ๐Ÿงช Attempt 6: Sampled 122 rows covering 852 labels. - [multilabel_classify.py:3367:sample_df_with_full_label_coverage] 2025-06-05 15:38:23,708 - INFO - ๐Ÿงช Attempt 7: Sampled 122 rows covering 838 labels. - [multilabel_classify.py:3367:sample_df_with_full_label_coverage] 2025-06-05 15:38:23,716 - INFO - ๐Ÿงช Attempt 8: Sampled 122 rows covering 851 labels. - [multilabel_classify.py:3367:sample_df_with_full_label_coverage] 2025-06-05 15:38:23,725 - INFO - ๐Ÿงช Attempt 9: Sampled 122 rows covering 825 labels. - [multilabel_classify.py:3367:sample_df_with_full_label_coverage] 2025-06-05 15:38:23,733 - INFO - ๐Ÿงช Attempt 10: Sampled 122 rows covering 833 labels. - [multilabel_classify.py:3367:sample_df_with_full_label_coverage] 2025-06-05 15:38:23,733 - INFO - โš ๏ธ Skipping label coverage fix. 7109 labels are missing. - [multilabel_classify.py:3385:sample_df_with_full_label_coverage] 2025-06-05 15:38:23,734 - INFO - โœ… Final row count: 122 (Valid: 20, Not-valid: 102) - [multilabel_classify.py:3390:sample_df_with_full_label_coverage] 2025-06-05 15:38:23,752 - INFO - ******************************************************************************** - [multilabel_classify.py:100:log_section] 2025-06-05 15:38:23,752 - INFO - * ๐ŸŒŸ STARTING MULTI_LABEL CLASSIFICATION MODEL TRAINING * - [multilabel_classify.py:101:log_section] 2025-06-05 15:38:23,752 - INFO - ******************************************************************************** - [multilabel_classify.py:104:log_section] 2025-06-05 15:38:23,752 - INFO - ๐Ÿ” Loaded authentication token from environment - [multilabel_classify.py:3599:main] 2025-06-05 15:38:23,753 - INFO - ๐Ÿท๏ธ Hub Model ID for this Classification task: deb101/mistral-7b-instruct-v0.3-mimic4-adapt-multilabel-classify - [multilabel_classify.py:3603:main] 2025-06-05 15:38:23,753 - INFO - -------------------------------------------------------------------------------- - [multilabel_classify.py:100:log_section] 2025-06-05 15:38:23,753 - INFO - - ๐Ÿ“‹ MODEL EXISTENCE CHECK - - [multilabel_classify.py:101:log_section] 2025-06-05 15:38:23,753 - INFO - -------------------------------------------------------------------------------- - [multilabel_classify.py:104:log_section] 2025-06-05 15:38:23,753 - INFO - ๐Ÿ” Checking model existence locally and on Hugging Face Hub... - [multilabel_classify.py:3468:check_model_existence] 2025-06-05 15:38:23,753 - INFO - โŒ Model not found locally at: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:3475:check_model_existence] 2025-06-05 15:38:23,805 - INFO - โœ… Model exists on Hugging Face Hub with ID: deb101/mistral-7b-instruct-v0.3-mimic4-adapt-multilabel-classify - [multilabel_classify.py:3487:check_model_existence] 2025-06-05 15:38:23,805 - INFO - ๐Ÿ“ Model exists either locally or on Hub - [multilabel_classify.py:3513:check_model_existence] 2025-06-05 15:38:23,805 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:100:log_section] 2025-06-05 15:38:23,805 - INFO - + โœจ STARTING FRESH TRAINING + - [multilabel_classify.py:101:log_section] 2025-06-05 15:38:23,805 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:104:log_section] 2025-06-05 15:38:23,805 - INFO - ๐Ÿ”„ Starting fresh training (either forced or model not found)... - [multilabel_classify.py:3616:main] 2025-06-05 15:38:23,817 - 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] 2025-06-05 15:38:23,817 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:100:log_section] 2025-06-05 15:38:23,817 - INFO - + โœจ LOADING FROM CHECKPOINT + - [multilabel_classify.py:101:log_section] 2025-06-05 15:38:23,818 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:104:log_section] 2025-06-05 15:38:23,818 - INFO - ๐Ÿ“ฅ Loading existing model from checkpoint... - [multilabel_classify.py:3623:main] 2025-06-05 15:38:23,818 - INFO - ๐Ÿ” Model exists locally: False - [multilabel_classify.py:2972:load_custom_task_model_and_tokenizer] 2025-06-05 15:38:23,835 - INFO - โœ… Validated Hugging Face model: deb101/mistral-7b-instruct-v0.3-mimic4-adapt-multilabel-classify - [multilabel_classify.py:3523:is_valid_hf_model] 2025-06-05 15:38:23,835 - INFO - ๐ŸŒ Loading model from Hub: deb101/mistral-7b-instruct-v0.3-mimic4-adapt-multilabel-classify - [multilabel_classify.py:2983:load_custom_task_model_and_tokenizer] 2025-06-05 15:38:23,899 - INFO - ๐ŸŒ Loaded config from Hub: deb101/mistral-7b-instruct-v0.3-mimic4-adapt-multilabel-classify - [multilabel_classify.py:3001:load_custom_task_model_and_tokenizer] 2025-06-05 15:38:23,899 - INFO - ๐Ÿ”ข Num labels: 833, Base model path: deb101/mistral-7b-instruct-v0.3-mimic4-adapt - [multilabel_classify.py:3013:load_custom_task_model_and_tokenizer] 2025-06-05 15:38:23,899 - INFO - ๐Ÿš€ Starting model and tokenizer loading process... - [multilabel_classify.py:1243:load_base_model_and_tokenizer] 2025-06-05 15:38:23,900 - INFO - ๐Ÿ“Š 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:1252:load_base_model_and_tokenizer] 2025-06-05 15:38:23,900 - INFO - ๐Ÿ”ค Loading tokenizer for model: deb101/mistral-7b-instruct-v0.3-mimic4-adapt... - [multilabel_classify.py:1256:load_base_model_and_tokenizer] 2025-06-05 15:38:24,208 - INFO - ๐Ÿ” Checking if deb101/mistral-7b-instruct-v0.3-mimic4-adapt is a PEFT model... - [multilabel_classify.py:1268:load_base_model_and_tokenizer] 2025-06-05 15:38:24,232 - INFO - โœ… Detected PEFT model. Base model: mistralai/Mistral-7B-Instruct-v0.3 - [multilabel_classify.py:1272:load_base_model_and_tokenizer] 2025-06-05 15:38:24,232 - INFO - ๐Ÿ” Loading model configuration for mistralai/Mistral-7B-Instruct-v0.3... - [multilabel_classify.py:1282:load_base_model_and_tokenizer] 2025-06-05 15:38:24,253 - INFO - Model type: mistral, Architectures: ['MistralForCausalLM'] - [multilabel_classify.py:1288:load_base_model_and_tokenizer] 2025-06-05 15:38:24,253 - INFO - ๐Ÿง  Loading base model: mistralai/Mistral-7B-Instruct-v0.3... - [multilabel_classify.py:1351:load_base_model_and_tokenizer] 2025-06-05 15:38:24,771 - 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] 2025-06-05 15:38:30,024 - INFO - ๐Ÿงฉ Loading PEFT adapters for deb101/mistral-7b-instruct-v0.3-mimic4-adapt... - [multilabel_classify.py:1366:load_base_model_and_tokenizer] 2025-06-05 15:38:30,887 - INFO - ๐Ÿ”ง Before enabling PEFT adapters for training - [multilabel_classify.py:1368:load_base_model_and_tokenizer] 2025-06-05 15:38:30,890 - INFO - ๐Ÿ“Š trainable params: 0 || all params: 7,254,839,296 || trainable%: 0.0000 - [multilabel_classify.py:159:log_print_output] 2025-06-05 15:38:30,893 - INFO - ๐Ÿ”ง After Enabling PEFT adapters for training - [multilabel_classify.py:1375:load_base_model_and_tokenizer] 2025-06-05 15:38:30,895 - INFO - ๐Ÿ“Š trainable params: 6,815,744 || all params: 7,254,839,296 || trainable%: 0.0939 - [multilabel_classify.py:159:log_print_output] 2025-06-05 15:38:30,896 - INFO - โœ… Model and tokenizer successfully loaded! - [multilabel_classify.py:1416:load_base_model_and_tokenizer] 2025-06-05 15:38:30,896 - INFO - ๐Ÿค– Loaded base model from: deb101/mistral-7b-instruct-v0.3-mimic4-adapt - [multilabel_classify.py:3017:load_custom_task_model_and_tokenizer] 2025-06-05 15:38:30,896 - INFO - Will now start to create Multilabel-Classification Model from the base model - [multilabel_classify.py:560:__init__] 2025-06-05 15:38:30,899 - INFO - ๐Ÿ“Š trainable params: 6,815,744 || all params: 3,765,178,368 || trainable%: 0.1810 - [multilabel_classify.py:614:compute_trainable_params] 2025-06-05 15:38:31,236 - INFO - Creating the Multi-Label Classification Model from base model mistralai/Mistral-7B-Instruct-v0.3 completed!!! - [multilabel_classify.py:602:__init__] 2025-06-05 15:38:31,239 - INFO - ๐Ÿ“Š trainable params: 84,177,025 || all params: 3,842,539,649 || trainable%: 2.1907 - [multilabel_classify.py:614:compute_trainable_params] 2025-06-05 15:38:31,239 - INFO - ๐Ÿ—๏ธ Initialized L2R model with 833 labels - [multilabel_classify.py:3025:load_custom_task_model_and_tokenizer] 2025-06-05 15:38:31,277 - INFO - ๐Ÿ–ฅ๏ธ Model moved to device: cuda - [multilabel_classify.py:3029:load_custom_task_model_and_tokenizer] 2025-06-05 15:39:32,232 - INFO - ๐Ÿ’พ Loaded custom weights from Hub: /home/ubuntu/.cache/huggingface/hub/models--deb101--mistral-7b-instruct-v0.3-mimic4-adapt-multilabel-classify/snapshots/fe1ea1ffc7211d1daaa3b0b6eb81b21bed5096a4/model.safetensors - [multilabel_classify.py:3052:load_custom_task_model_and_tokenizer] 2025-06-05 15:39:33,290 - INFO - โœ… Custom weights loaded into model - [multilabel_classify.py:3071:load_custom_task_model_and_tokenizer] 2025-06-05 15:39:33,298 - INFO - โœ”๏ธ Loaded weights match model's state_dict - [multilabel_classify.py:3082:load_custom_task_model_and_tokenizer] 2025-06-05 15:39:33,300 - INFO - ๐Ÿ“‹ Loaded files from Hub (directory: /home/ubuntu/.cache/huggingface/hub/models--deb101--mistral-7b-instruct-v0.3-mimic4-adapt-multilabel-classify/snapshots/fe1ea1ffc7211d1daaa3b0b6eb81b21bed5096a4): +---------+-------------------+------------+ | Index | Loaded File | Size | +=========+===================+============+ | 1 | model.safetensors | 4267.74 MB | +---------+-------------------+------------+ | 2 | config.json | 0.00 MB | +---------+-------------------+------------+ - [multilabel_classify.py:3122:load_custom_task_model_and_tokenizer] 2025-06-05 15:39:35,109 - INFO - ๐Ÿ–Œ๏ธ Loaded tokenizer from: deb101/mistral-7b-instruct-v0.3-mimic4-adapt-multilabel-classify - [multilabel_classify.py:3137:load_custom_task_model_and_tokenizer] 2025-06-05 15:39:35,118 - INFO - ๐Ÿ–ฅ๏ธ Model moved to device: cuda - [multilabel_classify.py:3144:load_custom_task_model_and_tokenizer] 2025-06-05 15:39:35,125 - INFO - โœ… Successfully loaded from checkpoint, will now continue training for 7 epochs. - [multilabel_classify.py:3634:main] 2025-06-05 15:39:35,127 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:100:log_section] 2025-06-05 15:39:35,127 - INFO - + โœจ PREPARING EVALUATION DATA + - [multilabel_classify.py:101:log_section] 2025-06-05 15:39:35,127 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:104:log_section] 2025-06-05 15:39:35,127 - INFO - ๐Ÿ”„ Loading and preprocessing evaluation data... - [multilabel_classify.py:3641:main] 2025-06-05 15:39:35,131 - INFO - Total number of labels: 833 - [multilabel_classify.py:1044:preprocess_data] 2025-06-05 15:39:35,131 - INFO - Rare labels (freq < 50): 832 - [multilabel_classify.py:1045:preprocess_data] 2025-06-05 15:39:35,131 - INFO - Not rare labels (freq >= 50): 1 - [multilabel_classify.py:1046:preprocess_data] 2025-06-05 15:39:35,131 - INFO - Label partitions and classes saved to ../tmp/MIMIC4_DEMO/labels_partition.json - [multilabel_classify.py:1047:preprocess_data] 2025-06-05 15:39:36,494 - INFO - The size of training set: 567 - [multilabel_classify.py:1143:preprocess_data] 2025-06-05 15:39:36,494 - INFO - The size of Evaluation set: 136 - [multilabel_classify.py:1144:preprocess_data] 2025-06-05 15:39:36,500 - INFO - ๐Ÿท๏ธ Number of unique ICD-10 codes: 833 - [multilabel_classify.py:3645:main] 2025-06-05 15:39:36,500 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:100:log_section] 2025-06-05 15:39:36,500 - INFO - + โœจ TRAINING PREPARATION + - [multilabel_classify.py:101:log_section] 2025-06-05 15:39:36,500 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:104:log_section] 2025-06-05 15:39:36,500 - INFO - โš™๏ธ Preparing training components and optimizers... - [multilabel_classify.py:3672:main] 2025-06-05 15:39:36,527 - INFO - ๐Ÿ–ฅ๏ธ Device: NVIDIA GH200 480GB - [multilabel_classify.py:891:log_training_configuration] 2025-06-05 15:39:36,528 - INFO - ๐Ÿ”‹ CUDA Available: True - [multilabel_classify.py:894:log_training_configuration] 2025-06-05 15:39:36,528 - INFO - ๐Ÿ’พ CUDA Device Count: 1 - [multilabel_classify.py:895:log_training_configuration] 2025-06-05 15:39:36,528 - INFO - ๐Ÿ“‹ Training Configuration ๐Ÿ“‹ +----------+-----------------------------+------------------------------------------------------------------+ | ๐ŸŒŸ Emoji | ๐Ÿท๏ธ Parameter | ๐Ÿ“Š Value | +----------+-----------------------------+------------------------------------------------------------------+ | ๐Ÿ“ | Output Directory | ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b | | ๐Ÿ” | Training Epochs | 7 | | ๐Ÿ‹๏ธ | Train Batch Size | 8 | | ๐Ÿ” | Eval Batch Size | 8 | | ๐Ÿ“Š | Gradient Accumulation Steps | 4 | | ๐Ÿš€ | Learning Rate | 0.0001 | | ๐ŸŒ… | Warmup Steps | 50 | | ๐Ÿ’พ | Save Strategy | epoch | | ๐Ÿ’พ | Save Total Limit | 10 | | ๐Ÿ“Š | Evaluation Strategy | epoch | | ๐ŸŽฏ | Best Model Metric | precision_at_15 | | ๐Ÿ“ | Logging Strategy | steps (every 10 steps) | | ๐ŸŒ | Push to Hub | True | | ๐ŸŒ | Hub Model ID | deb101/mistral-7b-instruct-v0.3-mimic4-adapt-multilabel-classify | | ๐Ÿ”ข | Steps per Epoch | 17 | | ๐Ÿ”ข | Total Training Steps | 119 | | ๐Ÿ”ข | Evaluation Steps | 17 | | ๐Ÿ“Š | Training Dataset Size | 567 samples ๐Ÿ‹๏ธ | | ๐Ÿ“Š | Evaluation Dataset Size | 136 samples ๐Ÿ” | +----------+-----------------------------+------------------------------------------------------------------+ - [multilabel_classify.py:883:log_training_args] 2025-06-05 15:39:36,529 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:100:log_section] 2025-06-05 15:39:36,529 - INFO - + โœจ MODEL TRAINING + - [multilabel_classify.py:101:log_section] 2025-06-05 15:39:36,529 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:104:log_section] 2025-06-05 15:39:36,529 - INFO - ๐Ÿ‹๏ธ Starting model training process... - [multilabel_classify.py:3694:main] 2025-06-05 15:39:36,572 - INFO - We are registering the tokenizer deb101/mistral-7b-instruct-v0.3-mimic4-adapt-multilabel-classify in Custom Trainer - [multilabel_classify.py:1988:__init__] 2025-06-05 15:39:36,834 - INFO - ๐Ÿš€ Starting Training... - [multilabel_classify.py:1642:on_train_begin] 2025-06-05 15:39:57,096 - INFO - ๐Ÿš‚ Training Metrics (Step 10) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.0989 | +---------------+----------+ | grad_norm | 0.063781 | +---------------+----------+ | learning_rate | 2e-05 | +---------------+----------+ | epoch | 0.56338 | +---------------+----------+ - [multilabel_classify.py:1836:on_log] 2025-06-05 15:40:11,014 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [multilabel_classify.py:2000:evaluate] 2025-06-05 15:40:45,983 - INFO - ๐Ÿ” Evaluation Metrics ๐Ÿ” +-------------------------------+----------+ | Metric | Value | +===============================+==========+ | eval_f1_micro | 0 | +-------------------------------+----------+ | eval_f1_macro | 0 | +-------------------------------+----------+ | eval_precision_at_5 | 0.272059 | +-------------------------------+----------+ | eval_recall_at_5 | 0.108443 | +-------------------------------+----------+ | eval_precision_at_8 | 0.195772 | +-------------------------------+----------+ | eval_recall_at_8 | 0.124597 | +-------------------------------+----------+ | eval_precision_at_15 | 0.126961 | +-------------------------------+----------+ | eval_recall_at_15 | 0.146996 | +-------------------------------+----------+ | eval_rare_f1_micro | 0 | +-------------------------------+----------+ | eval_rare_f1_macro | 0 | +-------------------------------+----------+ | eval_rare_precision | 0 | +-------------------------------+----------+ | eval_rare_recall | 0 | +-------------------------------+----------+ | eval_rare_precision_at_5 | 0.208824 | +-------------------------------+----------+ | eval_rare_recall_at_5 | 0.088475 | +-------------------------------+----------+ | eval_rare_precision_at_8 | 0.150735 | +-------------------------------+----------+ | eval_rare_recall_at_8 | 0.101507 | +-------------------------------+----------+ | eval_rare_precision_at_15 | 0.098529 | +-------------------------------+----------+ | eval_rare_recall_at_15 | 0.120102 | +-------------------------------+----------+ | 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 | 0.103884 | +-------------------------------+----------+ - [multilabel_classify.py:1855:on_evaluate] 2025-06-05 15:40:47,180 - INFO - ๐Ÿ’พ Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-18 - [multilabel_classify.py:2093:_save] 2025-06-05 15:40:47,181 - INFO - โš™๏ธ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-18 - [multilabel_classify.py:2098:_save] 2025-06-05 15:40:47,182 - INFO - ๐Ÿ“‹ 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:2115:_save] 2025-06-05 15:40:53,184 - INFO - ๐Ÿš‚ Training Metrics (Step 20) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.1039 | +---------------+----------+ | grad_norm | 0.113664 | +---------------+----------+ | learning_rate | 4e-05 | +---------------+----------+ | epoch | 1.11268 | +---------------+----------+ - [multilabel_classify.py:1836:on_log] 2025-06-05 15:41:11,244 - INFO - ๐Ÿš‚ Training Metrics (Step 30) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.1013 | +---------------+----------+ | grad_norm | 0.198499 | +---------------+----------+ | learning_rate | 6e-05 | +---------------+----------+ | epoch | 1.67606 | +---------------+----------+ - [multilabel_classify.py:1836:on_log] 2025-06-05 15:41:21,600 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [multilabel_classify.py:2000:evaluate] 2025-06-05 15:41:56,730 - INFO - ๐Ÿ” Evaluation Metrics ๐Ÿ” +-------------------------------+----------+ | Metric | Value | +===============================+==========+ | eval_f1_micro | 0 | +-------------------------------+----------+ | eval_f1_macro | 0 | +-------------------------------+----------+ | eval_precision_at_5 | 0.270588 | +-------------------------------+----------+ | eval_recall_at_5 | 0.111741 | +-------------------------------+----------+ | eval_precision_at_8 | 0.230699 | +-------------------------------+----------+ | eval_recall_at_8 | 0.153039 | +-------------------------------+----------+ | eval_precision_at_15 | 0.148529 | +-------------------------------+----------+ | eval_recall_at_15 | 0.172471 | +-------------------------------+----------+ | eval_rare_f1_micro | 0 | +-------------------------------+----------+ | eval_rare_f1_macro | 0 | +-------------------------------+----------+ | eval_rare_precision | 0 | +-------------------------------+----------+ | eval_rare_recall | 0 | +-------------------------------+----------+ | eval_rare_precision_at_5 | 0.227941 | +-------------------------------+----------+ | eval_rare_recall_at_5 | 0.091875 | +-------------------------------+----------+ | eval_rare_precision_at_8 | 0.191176 | +-------------------------------+----------+ | eval_rare_recall_at_8 | 0.134186 | +-------------------------------+----------+ | eval_rare_precision_at_15 | 0.126961 | +-------------------------------+----------+ | eval_rare_recall_at_15 | 0.150628 | +-------------------------------+----------+ | 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 | 0.105386 | +-------------------------------+----------+ - [multilabel_classify.py:1855:on_evaluate] 2025-06-05 15:41:57,912 - INFO - ๐Ÿ’พ Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-36 - [multilabel_classify.py:2093:_save] 2025-06-05 15:41:57,913 - INFO - โš™๏ธ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-36 - [multilabel_classify.py:2098:_save] 2025-06-05 15:41:57,914 - INFO - ๐Ÿ“‹ 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:2115:_save] 2025-06-05 15:42:07,554 - INFO - ๐Ÿš‚ Training Metrics (Step 40) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.0971 | +---------------+----------+ | grad_norm | 0.073463 | +---------------+----------+ | learning_rate | 8e-05 | +---------------+----------+ | epoch | 2.22535 | +---------------+----------+ - [multilabel_classify.py:1836:on_log] 2025-06-05 15:42:25,650 - INFO - ๐Ÿš‚ Training Metrics (Step 50) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.1012 | +---------------+----------+ | grad_norm | 0.058595 | +---------------+----------+ | learning_rate | 0.0001 | +---------------+----------+ | epoch | 2.78873 | +---------------+----------+ - [multilabel_classify.py:1836:on_log] 2025-06-05 15:42:32,400 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [multilabel_classify.py:2000:evaluate] 2025-06-05 15:43:07,380 - INFO - ๐Ÿ” Evaluation Metrics ๐Ÿ” +-------------------------------+----------+ | Metric | Value | +===============================+==========+ | eval_f1_micro | 0 | +-------------------------------+----------+ | eval_f1_macro | 0 | +-------------------------------+----------+ | eval_precision_at_5 | 0.276471 | +-------------------------------+----------+ | eval_recall_at_5 | 0.111579 | +-------------------------------+----------+ | eval_precision_at_8 | 0.237132 | +-------------------------------+----------+ | eval_recall_at_8 | 0.15122 | +-------------------------------+----------+ | eval_precision_at_15 | 0.148039 | +-------------------------------+----------+ | eval_recall_at_15 | 0.171528 | +-------------------------------+----------+ | eval_rare_f1_micro | 0 | +-------------------------------+----------+ | eval_rare_f1_macro | 0 | +-------------------------------+----------+ | eval_rare_precision | 0 | +-------------------------------+----------+ | eval_rare_recall | 0 | +-------------------------------+----------+ | eval_rare_precision_at_5 | 0.247059 | +-------------------------------+----------+ | eval_rare_recall_at_5 | 0.105122 | +-------------------------------+----------+ | eval_rare_precision_at_8 | 0.193015 | +-------------------------------+----------+ | eval_rare_recall_at_8 | 0.135358 | +-------------------------------+----------+ | eval_rare_precision_at_15 | 0.125 | +-------------------------------+----------+ | eval_rare_recall_at_15 | 0.149296 | +-------------------------------+----------+ | 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 | 0.103298 | +-------------------------------+----------+ - [multilabel_classify.py:1855:on_evaluate] 2025-06-05 15:43:08,572 - INFO - ๐Ÿ’พ Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-54 - [multilabel_classify.py:2093:_save] 2025-06-05 15:43:08,574 - INFO - โš™๏ธ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-54 - [multilabel_classify.py:2098:_save] 2025-06-05 15:43:08,575 - INFO - ๐Ÿ“‹ 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:2115:_save] 2025-06-05 15:43:21,824 - INFO - ๐Ÿš‚ Training Metrics (Step 60) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.0995 | +---------------+----------+ | grad_norm | 0.103198 | +---------------+----------+ | learning_rate | 9.5e-05 | +---------------+----------+ | epoch | 3.33803 | +---------------+----------+ - [multilabel_classify.py:1836:on_log] 2025-06-05 15:43:39,928 - INFO - ๐Ÿš‚ Training Metrics (Step 70) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.1003 | +---------------+----------+ | grad_norm | 0.184965 | +---------------+----------+ | learning_rate | 8.1e-05 | +---------------+----------+ | epoch | 3.90141 | +---------------+----------+ - [multilabel_classify.py:1836:on_log] 2025-06-05 15:43:43,080 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [multilabel_classify.py:2000:evaluate] 2025-06-05 15:44:18,190 - INFO - ๐Ÿ” Evaluation Metrics ๐Ÿ” +-------------------------------+----------+ | Metric | Value | +===============================+==========+ | eval_f1_micro | 0 | +-------------------------------+----------+ | eval_f1_macro | 0 | +-------------------------------+----------+ | eval_precision_at_5 | 0.276471 | +-------------------------------+----------+ | eval_recall_at_5 | 0.116576 | +-------------------------------+----------+ | eval_precision_at_8 | 0.235294 | +-------------------------------+----------+ | eval_recall_at_8 | 0.144086 | +-------------------------------+----------+ | eval_precision_at_15 | 0.14951 | +-------------------------------+----------+ | eval_recall_at_15 | 0.172205 | +-------------------------------+----------+ | eval_rare_f1_micro | 0 | +-------------------------------+----------+ | eval_rare_f1_macro | 0 | +-------------------------------+----------+ | eval_rare_precision | 0 | +-------------------------------+----------+ | eval_rare_recall | 0 | +-------------------------------+----------+ | eval_rare_precision_at_5 | 0.245588 | +-------------------------------+----------+ | eval_rare_recall_at_5 | 0.107489 | +-------------------------------+----------+ | eval_rare_precision_at_8 | 0.193934 | +-------------------------------+----------+ | eval_rare_recall_at_8 | 0.136584 | +-------------------------------+----------+ | eval_rare_precision_at_15 | 0.125 | +-------------------------------+----------+ | eval_rare_recall_at_15 | 0.149146 | +-------------------------------+----------+ | 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 | 0.101713 | +-------------------------------+----------+ - [multilabel_classify.py:1855:on_evaluate] 2025-06-05 15:44:19,386 - INFO - ๐Ÿ’พ Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-72 - [multilabel_classify.py:2093:_save] 2025-06-05 15:44:19,387 - INFO - โš™๏ธ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-72 - [multilabel_classify.py:2098:_save] 2025-06-05 15:44:19,388 - INFO - ๐Ÿ“‹ Saved files in ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-72: +---------+-------------------+------------+ | 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:2115:_save] 2025-06-05 15:44:36,268 - INFO - ๐Ÿš‚ Training Metrics (Step 80) ๐Ÿš‚ +---------------+---------+ | Metric | Value | +===============+=========+ | loss | 0.0941 | +---------------+---------+ | grad_norm | 0.19297 | +---------------+---------+ | learning_rate | 6.1e-05 | +---------------+---------+ | epoch | 4.4507 | +---------------+---------+ - [multilabel_classify.py:1836:on_log] 2025-06-05 15:44:53,903 - INFO - ๐Ÿš‚ Training Metrics (Step 90) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.0872 | +---------------+----------+ | grad_norm | 0.214059 | +---------------+----------+ | learning_rate | 3.8e-05 | +---------------+----------+ | epoch | 5 | +---------------+----------+ - [multilabel_classify.py:1836:on_log] 2025-06-05 15:44:53,903 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [multilabel_classify.py:2000:evaluate] 2025-06-05 15:45:28,817 - INFO - ๐Ÿ” Evaluation Metrics ๐Ÿ” +-------------------------------+----------+ | Metric | Value | +===============================+==========+ | eval_f1_micro | 0.0238 | +-------------------------------+----------+ | eval_f1_macro | 0.00104 | +-------------------------------+----------+ | eval_precision_at_5 | 0.276471 | +-------------------------------+----------+ | eval_recall_at_5 | 0.116576 | +-------------------------------+----------+ | eval_precision_at_8 | 0.235294 | +-------------------------------+----------+ | eval_recall_at_8 | 0.144086 | +-------------------------------+----------+ | eval_precision_at_15 | 0.153431 | +-------------------------------+----------+ | eval_recall_at_15 | 0.174813 | +-------------------------------+----------+ | eval_rare_f1_micro | 0.003331 | +-------------------------------+----------+ | eval_rare_f1_macro | 0.000516 | +-------------------------------+----------+ | eval_rare_precision | 0.4 | +-------------------------------+----------+ | eval_rare_recall | 0.001672 | +-------------------------------+----------+ | eval_rare_precision_at_5 | 0.245588 | +-------------------------------+----------+ | eval_rare_recall_at_5 | 0.107489 | +-------------------------------+----------+ | eval_rare_precision_at_8 | 0.200368 | +-------------------------------+----------+ | eval_rare_recall_at_8 | 0.12225 | +-------------------------------+----------+ | eval_rare_precision_at_15 | 0.126471 | +-------------------------------+----------+ | eval_rare_recall_at_15 | 0.149956 | +-------------------------------+----------+ | eval_not_rare_f1_micro | 0.507353 | +-------------------------------+----------+ | eval_not_rare_f1_macro | 0.499533 | +-------------------------------+----------+ | eval_not_rare_precision | 0.507353 | +-------------------------------+----------+ | eval_not_rare_recall | 0.507353 | +-------------------------------+----------+ | 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 | 0.104214 | +-------------------------------+----------+ - [multilabel_classify.py:1855:on_evaluate] 2025-06-05 15:45:30,011 - INFO - ๐Ÿ’พ Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-90 - [multilabel_classify.py:2093:_save] 2025-06-05 15:45:30,012 - INFO - โš™๏ธ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-90 - [multilabel_classify.py:2098:_save] 2025-06-05 15:45:30,013 - INFO - ๐Ÿ“‹ Saved files in ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-90: +---------+-------------------+------------+ | 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:2115:_save] 2025-06-05 15:45:50,487 - INFO - ๐Ÿš‚ Training Metrics (Step 100) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.0891 | +---------------+----------+ | grad_norm | 0.162411 | +---------------+----------+ | learning_rate | 1.8e-05 | +---------------+----------+ | epoch | 5.56338 | +---------------+----------+ - [multilabel_classify.py:1836:on_log] 2025-06-05 15:46:04,470 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [multilabel_classify.py:2000:evaluate] 2025-06-05 15:46:39,381 - INFO - ๐Ÿ” Evaluation Metrics ๐Ÿ” +-------------------------------+----------+ | Metric | Value | +===============================+==========+ | eval_f1_micro | 0.041747 | +-------------------------------+----------+ | eval_f1_macro | 0.001271 | +-------------------------------+----------+ | eval_precision_at_5 | 0.276471 | +-------------------------------+----------+ | eval_recall_at_5 | 0.116576 | +-------------------------------+----------+ | eval_precision_at_8 | 0.235294 | +-------------------------------+----------+ | eval_recall_at_8 | 0.144086 | +-------------------------------+----------+ | eval_precision_at_15 | 0.153431 | +-------------------------------+----------+ | eval_recall_at_15 | 0.174813 | +-------------------------------+----------+ | eval_rare_f1_micro | 0.013093 | +-------------------------------+----------+ | eval_rare_f1_macro | 0.000634 | +-------------------------------+----------+ | eval_rare_precision | 0.307692 | +-------------------------------+----------+ | eval_rare_recall | 0.006689 | +-------------------------------+----------+ | eval_rare_precision_at_5 | 0.236765 | +-------------------------------+----------+ | eval_rare_recall_at_5 | 0.101155 | +-------------------------------+----------+ | eval_rare_precision_at_8 | 0.200368 | +-------------------------------+----------+ | eval_rare_recall_at_8 | 0.12225 | +-------------------------------+----------+ | eval_rare_precision_at_15 | 0.126471 | +-------------------------------+----------+ | eval_rare_recall_at_15 | 0.149956 | +-------------------------------+----------+ | eval_not_rare_f1_micro | 0.507353 | +-------------------------------+----------+ | eval_not_rare_f1_macro | 0.506044 | +-------------------------------+----------+ | eval_not_rare_precision | 0.507353 | +-------------------------------+----------+ | eval_not_rare_recall | 0.507353 | +-------------------------------+----------+ | 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 | 0.101633 | +-------------------------------+----------+ - [multilabel_classify.py:1855:on_evaluate] 2025-06-05 15:46:40,584 - INFO - ๐Ÿ’พ Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-108 - [multilabel_classify.py:2093:_save] 2025-06-05 15:46:40,585 - INFO - โš™๏ธ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-108 - [multilabel_classify.py:2098:_save] 2025-06-05 15:46:40,586 - INFO - ๐Ÿ“‹ Saved files in ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-108: +---------+-------------------+------------+ | 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:2115:_save] 2025-06-05 15:46:46,602 - INFO - ๐Ÿš‚ Training Metrics (Step 110) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.0844 | +---------------+----------+ | grad_norm | 0.075479 | +---------------+----------+ | learning_rate | 5e-06 | +---------------+----------+ | epoch | 6.11268 | +---------------+----------+ - [multilabel_classify.py:1836:on_log] 2025-06-05 15:47:04,125 - INFO - ๐Ÿ’พ Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-119 - [multilabel_classify.py:2093:_save] 2025-06-05 15:47:04,126 - INFO - โš™๏ธ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-119 - [multilabel_classify.py:2098:_save] 2025-06-05 15:47:04,127 - INFO - ๐Ÿ“‹ Saved files in ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-119: +---------+-------------------+------------+ | 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:2115:_save] 2025-06-05 15:47:04,430 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [multilabel_classify.py:2000:evaluate] 2025-06-05 15:47:39,440 - INFO - ๐Ÿ” Evaluation Metrics ๐Ÿ” +-------------------------------+----------+ | Metric | Value | +===============================+==========+ | eval_f1_micro | 0.037369 | +-------------------------------+----------+ | eval_f1_macro | 0.001265 | +-------------------------------+----------+ | eval_precision_at_5 | 0.276471 | +-------------------------------+----------+ | eval_recall_at_5 | 0.116576 | +-------------------------------+----------+ | eval_precision_at_8 | 0.235294 | +-------------------------------+----------+ | eval_recall_at_8 | 0.144086 | +-------------------------------+----------+ | eval_precision_at_15 | 0.153431 | +-------------------------------+----------+ | eval_recall_at_15 | 0.174813 | +-------------------------------+----------+ | eval_rare_f1_micro | 0.011508 | +-------------------------------+----------+ | eval_rare_f1_macro | 0.000666 | +-------------------------------+----------+ | eval_rare_precision | 0.341463 | +-------------------------------+----------+ | eval_rare_recall | 0.005853 | +-------------------------------+----------+ | eval_rare_precision_at_5 | 0.232353 | +-------------------------------+----------+ | eval_rare_recall_at_5 | 0.098451 | +-------------------------------+----------+ | eval_rare_precision_at_8 | 0.200368 | +-------------------------------+----------+ | eval_rare_recall_at_8 | 0.12225 | +-------------------------------+----------+ | eval_rare_precision_at_15 | 0.126471 | +-------------------------------+----------+ | eval_rare_recall_at_15 | 0.149956 | +-------------------------------+----------+ | eval_not_rare_f1_micro | 0.5 | +-------------------------------+----------+ | eval_not_rare_f1_macro | 0.5 | +-------------------------------+----------+ | eval_not_rare_precision | 0.5 | +-------------------------------+----------+ | eval_not_rare_recall | 0.5 | +-------------------------------+----------+ | 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 | 0.101503 | +-------------------------------+----------+ - [multilabel_classify.py:1855:on_evaluate] 2025-06-05 15:47:43,196 - INFO - ๐Ÿ’พ Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-119 - [multilabel_classify.py:2093:_save] 2025-06-05 15:47:43,198 - INFO - โš™๏ธ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-119 - [multilabel_classify.py:2098:_save] 2025-06-05 15:47:43,199 - INFO - ๐Ÿ“‹ Saved files in ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-119: +---------+--------------------+------------+ | 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:2115:_save] 2025-06-05 15:47:43,564 - INFO - ๐Ÿ“‚ Loading best model from ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-90 - [multilabel_classify.py:2167:_load_best_model] 2025-06-05 15:47:43,565 - INFO - ๐Ÿ–ฅ๏ธ Model is on device: cuda:0 - [multilabel_classify.py:2177:_load_best_model] 2025-06-05 15:47:43,617 - INFO - ๐Ÿ”‘ 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:2201:_load_best_model] 2025-06-05 15:47:44,629 - INFO - โœ… Loaded best model weights from ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-90/model.safetensors - [multilabel_classify.py:2218:_load_best_model] 2025-06-05 15:47:44,653 - INFO - โœ”๏ธ Weight for boost_mul matches between saved and loaded state_dict - [multilabel_classify.py:2230:_load_best_model] 2025-06-05 15:47:44,676 - INFO - โœ”๏ธ Weight for boost_add matches between saved and loaded state_dict - [multilabel_classify.py:2230:_load_best_model] 2025-06-05 15:47:44,691 - INFO - ๐Ÿš‚ Training Metrics (Step 119) ๐Ÿš‚ +--------------------------+----------+ | Metric | Value | +==========================+==========+ | train_runtime | 487.858 | +--------------------------+----------+ | train_samples_per_second | 8.136 | +--------------------------+----------+ | train_steps_per_second | 0.244 | +--------------------------+----------+ | total_flos | 0 | +--------------------------+----------+ | train_loss | 0.095432 | +--------------------------+----------+ | epoch | 6.61972 | +--------------------------+----------+ - [multilabel_classify.py:1836:on_log] 2025-06-05 15:47:44,692 - INFO - โœจ Training Completed! โœจ - [multilabel_classify.py:1709:on_train_end] 2025-06-05 15:47:44,763 - INFO - ๐Ÿ“Š Training loss plot saved as '../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/train_loss_plot.png' - [multilabel_classify.py:1905:on_train_end] 2025-06-05 15:47:44,825 - INFO - ๐Ÿ“Š Evaluation loss plot saved as '../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/eval_loss_plot.png' - [multilabel_classify.py:1919:on_train_end] 2025-06-05 15:47:44,881 - INFO - ๐Ÿ“Š Evaluation metric plot saved as '../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/eval_precision_at_15_plot.png' - [multilabel_classify.py:1940:on_train_end] 2025-06-05 15:47:44,881 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:100:log_section] 2025-06-05 15:47:44,882 - INFO - + โœจ MODEL SAVING + - [multilabel_classify.py:101:log_section] 2025-06-05 15:47:44,882 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:104:log_section] 2025-06-05 15:47:44,882 - INFO - ๐Ÿ’พ Saving trained model and pushing to Hugging Face Hub... - [multilabel_classify.py:3708:main] 2025-06-05 15:47:44,882 - INFO - ๐Ÿ“ Creating/using output directory: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2693:save_and_push] 2025-06-05 15:47:46,066 - INFO - ๐Ÿ’พ Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2093:_save] 2025-06-05 15:47:46,067 - INFO - โš™๏ธ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2098:_save] 2025-06-05 15:47:46,068 - INFO - ๐Ÿ“‹ Saved files in ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b: +---------+-------------------------------+------------+ | Index | Saved File | Size | +=========+===============================+============+ | 1 | eval_loss_plot.png | 0.04 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 | 0.04 MB | +---------+-------------------------------+------------+ | 6 | eval_precision_at_15_plot.png | 0.03 MB | +---------+-------------------------------+------------+ - [multilabel_classify.py:2115:_save] 2025-06-05 15:47:49,635 - INFO - ๐Ÿ’พ Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2093:_save] 2025-06-05 15:47:49,637 - INFO - โš™๏ธ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2098:_save] 2025-06-05 15:47:49,638 - INFO - ๐Ÿ“‹ Saved files in ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b: +---------+-------------------------------+------------+ | Index | Saved File | Size | +=========+===============================+============+ | 1 | eval_loss_plot.png | 0.04 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 | 0.04 MB | +---------+-------------------------------+------------+ | 6 | eval_precision_at_15_plot.png | 0.03 MB | +---------+-------------------------------+------------+ - [multilabel_classify.py:2115:_save] 2025-06-05 15:49:10,190 - INFO - ๐Ÿ’พ Model saved to: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2697:save_and_push] 2025-06-05 15:49:10,219 - INFO - ๐Ÿ–Œ๏ธ Tokenizer saved to: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2701:save_and_push]