2025-06-05 15:02:25,280 - INFO - ================================================================================ - [multilabel_classify.py:100:log_section] 2025-06-05 15:02:25,281 - INFO - = ๐Ÿ“Œ INITIALIZING TRAINING ENVIRONMENT = - [multilabel_classify.py:101:log_section] 2025-06-05 15:02:25,281 - INFO - ================================================================================ - [multilabel_classify.py:104:log_section] 2025-06-05 15:02:25,281 - INFO - ๐Ÿš€ Setting up data paths and environment variables... - [multilabel_classify.py:3560:main] 2025-06-05 15:02:25,281 - INFO - ๐Ÿ“‚ Using output directory: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:3566:main] 2025-06-05 15:02:25,281 - INFO - ๐Ÿ› ๏ธ Command-line Arguments: - [multilabel_classify.py:368:print_args] 2025-06-05 15:02:25,281 - 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: False ๐Ÿ”น task: multilabel-classify ๐Ÿ”น num_train_epochs: 4 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: 500 ๐Ÿ”น logfile_path: ../tmp/logs/classification_log_2025-06-05_15-02-25.log ๐Ÿ”น source: /home/ubuntu/.xcube/data/mimic4_demo - [multilabel_classify.py:369:print_args] 2025-06-05 15:02:25,281 - 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 15:02:25,281 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:100:log_section] 2025-06-05 15:02:25,281 - INFO - + โœจ LOADING DATASETS + - [multilabel_classify.py:101:log_section] 2025-06-05 15:02:25,281 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:104:log_section] 2025-06-05 15:02:25,282 - INFO - ๐Ÿ“Š Loading main datasets.... - [multilabel_classify.py:3572:main] 2025-06-05 15:02:33,869 - INFO - ๐Ÿ” Total unique labels in dataset: 7942 - [multilabel_classify.py:3353:sample_df_with_full_label_coverage] 2025-06-05 15:02:33,882 - INFO - ๐Ÿงช Attempt 1: Sampled 122 rows covering 863 labels. - [multilabel_classify.py:3367:sample_df_with_full_label_coverage] 2025-06-05 15:02:33,892 - INFO - ๐Ÿงช Attempt 2: Sampled 122 rows covering 816 labels. - [multilabel_classify.py:3367:sample_df_with_full_label_coverage] 2025-06-05 15:02:33,901 - INFO - ๐Ÿงช Attempt 3: Sampled 122 rows covering 885 labels. - [multilabel_classify.py:3367:sample_df_with_full_label_coverage] 2025-06-05 15:02:33,910 - INFO - ๐Ÿงช Attempt 4: Sampled 122 rows covering 828 labels. - [multilabel_classify.py:3367:sample_df_with_full_label_coverage] 2025-06-05 15:02:33,920 - INFO - ๐Ÿงช Attempt 5: Sampled 122 rows covering 879 labels. - [multilabel_classify.py:3367:sample_df_with_full_label_coverage] 2025-06-05 15:02:33,928 - INFO - ๐Ÿงช Attempt 6: Sampled 122 rows covering 852 labels. - [multilabel_classify.py:3367:sample_df_with_full_label_coverage] 2025-06-05 15:02:33,937 - INFO - ๐Ÿงช Attempt 7: Sampled 122 rows covering 838 labels. - [multilabel_classify.py:3367:sample_df_with_full_label_coverage] 2025-06-05 15:02:33,946 - INFO - ๐Ÿงช Attempt 8: Sampled 122 rows covering 851 labels. - [multilabel_classify.py:3367:sample_df_with_full_label_coverage] 2025-06-05 15:02:33,955 - INFO - ๐Ÿงช Attempt 9: Sampled 122 rows covering 825 labels. - [multilabel_classify.py:3367:sample_df_with_full_label_coverage] 2025-06-05 15:02:33,964 - INFO - ๐Ÿงช Attempt 10: Sampled 122 rows covering 833 labels. - [multilabel_classify.py:3367:sample_df_with_full_label_coverage] 2025-06-05 15:02:33,964 - INFO - โš ๏ธ Skipping label coverage fix. 7109 labels are missing. - [multilabel_classify.py:3385:sample_df_with_full_label_coverage] 2025-06-05 15:02:33,964 - INFO - โœ… Final row count: 122 (Valid: 20, Not-valid: 102) - [multilabel_classify.py:3390:sample_df_with_full_label_coverage] 2025-06-05 15:02:33,983 - INFO - ******************************************************************************** - [multilabel_classify.py:100:log_section] 2025-06-05 15:02:33,983 - INFO - * ๐ŸŒŸ STARTING MULTI_LABEL CLASSIFICATION MODEL TRAINING * - [multilabel_classify.py:101:log_section] 2025-06-05 15:02:33,983 - INFO - ******************************************************************************** - [multilabel_classify.py:104:log_section] 2025-06-05 15:02:33,983 - INFO - ๐Ÿ” Loaded authentication token from environment - [multilabel_classify.py:3599:main] 2025-06-05 15:02:33,983 - 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 15:02:33,984 - INFO - -------------------------------------------------------------------------------- - [multilabel_classify.py:100:log_section] 2025-06-05 15:02:33,984 - INFO - - ๐Ÿ“‹ MODEL EXISTENCE CHECK - - [multilabel_classify.py:101:log_section] 2025-06-05 15:02:33,984 - INFO - -------------------------------------------------------------------------------- - [multilabel_classify.py:104:log_section] 2025-06-05 15:02:33,984 - INFO - ๐Ÿ” Checking model existence locally and on Hugging Face Hub... - [multilabel_classify.py:3468:check_model_existence] 2025-06-05 15:02:33,984 - INFO - โœ… Model exists locally at: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:3473:check_model_existence] 2025-06-05 15:02:34,066 - 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 15:02:34,066 - INFO - ๐Ÿ“ Model exists either locally or on Hub - [multilabel_classify.py:3513:check_model_existence] 2025-06-05 15:02:34,067 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:100:log_section] 2025-06-05 15:02:34,067 - INFO - + โœจ STARTING FRESH TRAINING + - [multilabel_classify.py:101:log_section] 2025-06-05 15:02:34,067 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:104:log_section] 2025-06-05 15:02:34,067 - INFO - ๐Ÿ”„ Starting fresh training (either forced or model not found)... - [multilabel_classify.py:3616:main] 2025-06-05 15:02:34,081 - 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 15:02:34,081 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:100:log_section] 2025-06-05 15:02:34,081 - INFO - + โœจ LOADING BASE MODEL + - [multilabel_classify.py:101:log_section] 2025-06-05 15:02:34,081 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:104:log_section] 2025-06-05 15:02:34,081 - INFO - ๐Ÿ“ฅ Loading pretrained model and tokenizer... - [multilabel_classify.py:3646:main] 2025-06-05 15:02:34,081 - INFO - ๐Ÿš€ Starting model and tokenizer loading process... - [multilabel_classify.py:1243:load_base_model_and_tokenizer] 2025-06-05 15:02:34,082 - 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 15:02:34,082 - 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 15:02:34,439 - 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 15:02:34,464 - 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 15:02:34,464 - INFO - ๐Ÿ” Loading model configuration for mistralai/Mistral-7B-Instruct-v0.3... - [multilabel_classify.py:1282:load_base_model_and_tokenizer] 2025-06-05 15:02:34,496 - INFO - Model type: mistral, Architectures: ['MistralForCausalLM'] - [multilabel_classify.py:1288:load_base_model_and_tokenizer] 2025-06-05 15:02:34,496 - INFO - ๐Ÿง  Loading base model: mistralai/Mistral-7B-Instruct-v0.3... - [multilabel_classify.py:1351:load_base_model_and_tokenizer] 2025-06-05 15:02:35,026 - 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 15:02:40,290 - 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 15:02:40,733 - INFO - ๐Ÿ”ง Before enabling PEFT adapters for training - [multilabel_classify.py:1368:load_base_model_and_tokenizer] 2025-06-05 15:02:40,735 - 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 15:02:40,738 - INFO - ๐Ÿ”ง After Enabling PEFT adapters for training - [multilabel_classify.py:1375:load_base_model_and_tokenizer] 2025-06-05 15:02:40,740 - 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 15:02:40,741 - INFO - โœ… Model and tokenizer successfully loaded! - [multilabel_classify.py:1416:load_base_model_and_tokenizer] 2025-06-05 15:02:40,741 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:100:log_section] 2025-06-05 15:02:40,741 - INFO - + โœจ DATA PREPROCESSING + - [multilabel_classify.py:101:log_section] 2025-06-05 15:02:40,741 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:104:log_section] 2025-06-05 15:02:40,742 - INFO - ๐Ÿ”„ Loading and preprocessing training data... - [multilabel_classify.py:3654:main] 2025-06-05 15:02:40,746 - INFO - Total number of labels: 833 - [multilabel_classify.py:1044:preprocess_data] 2025-06-05 15:02:40,746 - INFO - Rare labels (freq < 50): 832 - [multilabel_classify.py:1045:preprocess_data] 2025-06-05 15:02:40,746 - INFO - Not rare labels (freq >= 50): 1 - [multilabel_classify.py:1046:preprocess_data] 2025-06-05 15:02:40,746 - INFO - Label partitions and classes saved to ../tmp/MIMIC4_DEMO/labels_partition.json - [multilabel_classify.py:1047:preprocess_data] 2025-06-05 15:02:42,069 - INFO - The size of training set: 567 - [multilabel_classify.py:1143:preprocess_data] 2025-06-05 15:02:42,069 - INFO - The size of Evaluation set: 136 - [multilabel_classify.py:1144:preprocess_data] 2025-06-05 15:02:42,074 - INFO - Number of unique ICD-10 codes: 833 - [multilabel_classify.py:3660:main] 2025-06-05 15:02:42,074 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:100:log_section] 2025-06-05 15:02:42,074 - INFO - + โœจ MODEL INITIALIZATION + - [multilabel_classify.py:101:log_section] 2025-06-05 15:02:42,074 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:104:log_section] 2025-06-05 15:02:42,075 - INFO - ๐Ÿง  Initializing custom L2R model for outputting per-token relevance scores per ICD-10 codes. - [multilabel_classify.py:3663:main] 2025-06-05 15:02:42,075 - INFO - Will now start to create Multilabel-Classification Model from the base model - [multilabel_classify.py:560:__init__] 2025-06-05 15:02:42,078 - 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 15:02:42,416 - 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 15:02:42,419 - 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 15:02:42,419 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:100:log_section] 2025-06-05 15:02:42,419 - INFO - + โœจ TRAINING PREPARATION + - [multilabel_classify.py:101:log_section] 2025-06-05 15:02:42,419 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:104:log_section] 2025-06-05 15:02:42,419 - INFO - โš™๏ธ Preparing training components and optimizers... - [multilabel_classify.py:3670:main] 2025-06-05 15:02:42,476 - INFO - ๐Ÿ–ฅ๏ธ Device: NVIDIA GH200 480GB - [multilabel_classify.py:891:log_training_configuration] 2025-06-05 15:02:42,476 - INFO - ๐Ÿ”‹ CUDA Available: True - [multilabel_classify.py:894:log_training_configuration] 2025-06-05 15:02:42,476 - INFO - ๐Ÿ’พ CUDA Device Count: 1 - [multilabel_classify.py:895:log_training_configuration] 2025-06-05 15:02:42,478 - 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 | 4 | | 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 | 500 | | 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 | 68 | | 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 15:02:42,478 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:100:log_section] 2025-06-05 15:02:42,478 - INFO - + โœจ MODEL TRAINING + - [multilabel_classify.py:101:log_section] 2025-06-05 15:02:42,478 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:104:log_section] 2025-06-05 15:02:42,479 - INFO - ๐Ÿ‹๏ธ Starting model training process... - [multilabel_classify.py:3692:main] 2025-06-05 15:02:42,520 - INFO - We are registering the tokenizer deb101/mistral-7b-instruct-v0.3-mimic4-adapt in Custom Trainer - [multilabel_classify.py:1988:__init__] 2025-06-05 15:02:42,770 - INFO - ๐Ÿš€ Starting Training... - [multilabel_classify.py:1642:on_train_begin] 2025-06-05 15:03:03,122 - INFO - ๐Ÿš‚ Training Metrics (Step 10) ๐Ÿš‚ +---------------+---------+ | Metric | Value | +===============+=========+ | loss | 0.6384 | +---------------+---------+ | grad_norm | 6.84453 | +---------------+---------+ | learning_rate | 2e-06 | +---------------+---------+ | epoch | 0.56338 | +---------------+---------+ - [multilabel_classify.py:1836:on_log] 2025-06-05 15:03:17,100 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [multilabel_classify.py:2000:evaluate] 2025-06-05 15:03:52,220 - INFO - ๐Ÿ” Evaluation Metrics ๐Ÿ” +-------------------------------+----------+ | Metric | Value | +===============================+==========+ | eval_f1_micro | 0 | +-------------------------------+----------+ | eval_f1_macro | 0 | +-------------------------------+----------+ | eval_precision_at_5 | 0.036765 | +-------------------------------+----------+ | eval_recall_at_5 | 0.008744 | +-------------------------------+----------+ | eval_precision_at_8 | 0.037684 | +-------------------------------+----------+ | eval_recall_at_8 | 0.017401 | +-------------------------------+----------+ | eval_precision_at_15 | 0.037745 | +-------------------------------+----------+ | eval_recall_at_15 | 0.032384 | +-------------------------------+----------+ | eval_rare_f1_micro | 0 | +-------------------------------+----------+ | eval_rare_f1_macro | 0 | +-------------------------------+----------+ | eval_rare_precision | 0 | +-------------------------------+----------+ | eval_rare_recall | 0 | +-------------------------------+----------+ | eval_rare_precision_at_5 | 0.029412 | +-------------------------------+----------+ | eval_rare_recall_at_5 | 0.00805 | +-------------------------------+----------+ | eval_rare_precision_at_8 | 0.026654 | +-------------------------------+----------+ | eval_rare_recall_at_8 | 0.010721 | +-------------------------------+----------+ | eval_rare_precision_at_15 | 0.027451 | +-------------------------------+----------+ | eval_rare_recall_at_15 | 0.021147 | +-------------------------------+----------+ | 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 | 0.229106 | +-------------------------------+----------+ - [multilabel_classify.py:1855:on_evaluate] 2025-06-05 15:03:55,736 - 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 15:03:55,737 - INFO - โš™๏ธ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-18 - [multilabel_classify.py:2098:_save] 2025-06-05 15:03:55,738 - 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 | 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 | 0.00 MB | +---------+--------------------+------------+ | 8 | rng_state.pth | 0.01 MB | +---------+--------------------+------------+ - [multilabel_classify.py:2115:_save] 2025-06-05 15:04:01,845 - INFO - ๐Ÿš‚ Training Metrics (Step 20) ๐Ÿš‚ +---------------+---------+ | Metric | Value | +===============+=========+ | loss | 0.345 | +---------------+---------+ | grad_norm | 2.53065 | +---------------+---------+ | learning_rate | 4e-06 | +---------------+---------+ | epoch | 1.11268 | +---------------+---------+ - [multilabel_classify.py:1836:on_log] 2025-06-05 15:04:19,966 - INFO - ๐Ÿš‚ Training Metrics (Step 30) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.1265 | +---------------+----------+ | grad_norm | 0.237818 | +---------------+----------+ | learning_rate | 6e-06 | +---------------+----------+ | epoch | 1.67606 | +---------------+----------+ - [multilabel_classify.py:1836:on_log] 2025-06-05 15:04:30,351 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [multilabel_classify.py:2000:evaluate] 2025-06-05 15:05:05,550 - INFO - ๐Ÿ” Evaluation Metrics ๐Ÿ” +-------------------------------+----------+ | Metric | Value | +===============================+==========+ | eval_f1_micro | 0 | +-------------------------------+----------+ | eval_f1_macro | 0 | +-------------------------------+----------+ | eval_precision_at_5 | 0.041176 | +-------------------------------+----------+ | eval_recall_at_5 | 0.009645 | +-------------------------------+----------+ | eval_precision_at_8 | 0.039522 | +-------------------------------+----------+ | eval_recall_at_8 | 0.016571 | +-------------------------------+----------+ | eval_precision_at_15 | 0.037255 | +-------------------------------+----------+ | eval_recall_at_15 | 0.030333 | +-------------------------------+----------+ | eval_rare_f1_micro | 0 | +-------------------------------+----------+ | eval_rare_f1_macro | 0 | +-------------------------------+----------+ | eval_rare_precision | 0 | +-------------------------------+----------+ | eval_rare_recall | 0 | +-------------------------------+----------+ | eval_rare_precision_at_5 | 0.025 | +-------------------------------+----------+ | eval_rare_recall_at_5 | 0.004753 | +-------------------------------+----------+ | eval_rare_precision_at_8 | 0.027574 | +-------------------------------+----------+ | eval_rare_recall_at_8 | 0.010902 | +-------------------------------+----------+ | eval_rare_precision_at_15 | 0.028431 | +-------------------------------+----------+ | eval_rare_recall_at_15 | 0.02441 | +-------------------------------+----------+ | 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 | 0.12156 | +-------------------------------+----------+ - [multilabel_classify.py:1855:on_evaluate] 2025-06-05 15:05:09,029 - 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 15:05:09,030 - INFO - โš™๏ธ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-36 - [multilabel_classify.py:2098:_save] 2025-06-05 15:05:09,031 - 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 | 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 | 0.00 MB | +---------+--------------------+------------+ | 8 | rng_state.pth | 0.01 MB | +---------+--------------------+------------+ - [multilabel_classify.py:2115:_save] 2025-06-05 15:05:19,082 - INFO - ๐Ÿš‚ Training Metrics (Step 40) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.1096 | +---------------+----------+ | grad_norm | 0.465592 | +---------------+----------+ | learning_rate | 8e-06 | +---------------+----------+ | epoch | 2.22535 | +---------------+----------+ - [multilabel_classify.py:1836:on_log] 2025-06-05 15:05:37,209 - INFO - ๐Ÿš‚ Training Metrics (Step 50) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.1092 | +---------------+----------+ | grad_norm | 0.099644 | +---------------+----------+ | learning_rate | 1e-05 | +---------------+----------+ | epoch | 2.78873 | +---------------+----------+ - [multilabel_classify.py:1836:on_log] 2025-06-05 15:05:43,993 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [multilabel_classify.py:2000:evaluate] 2025-06-05 15:06:19,081 - INFO - ๐Ÿ” Evaluation Metrics ๐Ÿ” +-------------------------------+----------+ | Metric | Value | +===============================+==========+ | eval_f1_micro | 0 | +-------------------------------+----------+ | eval_f1_macro | 0 | +-------------------------------+----------+ | eval_precision_at_5 | 0.116176 | +-------------------------------+----------+ | eval_recall_at_5 | 0.039057 | +-------------------------------+----------+ | eval_precision_at_8 | 0.100184 | +-------------------------------+----------+ | eval_recall_at_8 | 0.059546 | +-------------------------------+----------+ | eval_precision_at_15 | 0.081373 | +-------------------------------+----------+ | eval_recall_at_15 | 0.089004 | +-------------------------------+----------+ | eval_rare_f1_micro | 0 | +-------------------------------+----------+ | eval_rare_f1_macro | 0 | +-------------------------------+----------+ | eval_rare_precision | 0 | +-------------------------------+----------+ | eval_rare_recall | 0 | +-------------------------------+----------+ | eval_rare_precision_at_5 | 0.060294 | +-------------------------------+----------+ | eval_rare_recall_at_5 | 0.020816 | +-------------------------------+----------+ | eval_rare_precision_at_8 | 0.057904 | +-------------------------------+----------+ | eval_rare_recall_at_8 | 0.033152 | +-------------------------------+----------+ | eval_rare_precision_at_15 | 0.056373 | +-------------------------------+----------+ | eval_rare_recall_at_15 | 0.059526 | +-------------------------------+----------+ | 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 | 0.106887 | +-------------------------------+----------+ - [multilabel_classify.py:1855:on_evaluate] 2025-06-05 15:06:22,738 - 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 15:06:22,739 - INFO - โš™๏ธ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-54 - [multilabel_classify.py:2098:_save] 2025-06-05 15:06:22,740 - 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 | 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 15:06:36,356 - INFO - ๐Ÿš‚ Training Metrics (Step 60) ๐Ÿš‚ +---------------+----------+ | Metric | Value | +===============+==========+ | loss | 0.1033 | +---------------+----------+ | grad_norm | 0.216208 | +---------------+----------+ | learning_rate | 1.2e-05 | +---------------+----------+ | epoch | 3.33803 | +---------------+----------+ - [multilabel_classify.py:1836:on_log] 2025-06-05 15:06:54,505 - INFO - ๐Ÿ’พ Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-68 - [multilabel_classify.py:2093:_save] 2025-06-05 15:06:54,507 - INFO - โš™๏ธ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-68 - [multilabel_classify.py:2098:_save] 2025-06-05 15:06:54,508 - INFO - ๐Ÿ“‹ 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:2115:_save] 2025-06-05 15:06:54,897 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [multilabel_classify.py:2000:evaluate] 2025-06-05 15:07:30,167 - INFO - ๐Ÿ” Evaluation Metrics ๐Ÿ” +-------------------------------+----------+ | Metric | Value | +===============================+==========+ | eval_f1_micro | 0 | +-------------------------------+----------+ | eval_f1_macro | 0 | +-------------------------------+----------+ | eval_precision_at_5 | 0.227941 | +-------------------------------+----------+ | eval_recall_at_5 | 0.094901 | +-------------------------------+----------+ | eval_precision_at_8 | 0.16636 | +-------------------------------+----------+ | eval_recall_at_8 | 0.103783 | +-------------------------------+----------+ | eval_precision_at_15 | 0.113725 | +-------------------------------+----------+ | eval_recall_at_15 | 0.128501 | +-------------------------------+----------+ | eval_rare_f1_micro | 0 | +-------------------------------+----------+ | eval_rare_f1_macro | 0 | +-------------------------------+----------+ | eval_rare_precision | 0 | +-------------------------------+----------+ | eval_rare_recall | 0 | +-------------------------------+----------+ | eval_rare_precision_at_5 | 0.15 | +-------------------------------+----------+ | eval_rare_recall_at_5 | 0.06448 | +-------------------------------+----------+ | eval_rare_precision_at_8 | 0.120404 | +-------------------------------+----------+ | eval_rare_recall_at_8 | 0.078831 | +-------------------------------+----------+ | eval_rare_precision_at_15 | 0.087255 | +-------------------------------+----------+ | eval_rare_recall_at_15 | 0.099736 | +-------------------------------+----------+ | 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 | 0.104832 | +-------------------------------+----------+ - [multilabel_classify.py:1855:on_evaluate] 2025-06-05 15:07:33,859 - INFO - ๐Ÿ’พ Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-68 - [multilabel_classify.py:2093:_save] 2025-06-05 15:07:33,860 - INFO - โš™๏ธ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-68 - [multilabel_classify.py:2098:_save] 2025-06-05 15:07:33,862 - INFO - ๐Ÿ“‹ 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:2115:_save] 2025-06-05 15:07:34,327 - INFO - ๐Ÿ“‚ Loading best model from ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-68 - [multilabel_classify.py:2167:_load_best_model] 2025-06-05 15:07:34,327 - INFO - ๐Ÿ–ฅ๏ธ Model is on device: cuda:0 - [multilabel_classify.py:2177:_load_best_model] 2025-06-05 15:07:34,399 - 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 15:07:35,427 - INFO - โœ… Loaded best model weights from ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-68/model.safetensors - [multilabel_classify.py:2218:_load_best_model] 2025-06-05 15:07:35,452 - INFO - โœ”๏ธ Weight for boost_mul matches between saved and loaded state_dict - [multilabel_classify.py:2230:_load_best_model] 2025-06-05 15:07:35,475 - INFO - โœ”๏ธ Weight for boost_add matches between saved and loaded state_dict - [multilabel_classify.py:2230:_load_best_model] 2025-06-05 15:07:35,490 - INFO - ๐Ÿš‚ Training Metrics (Step 68) ๐Ÿš‚ +--------------------------+----------+ | Metric | Value | +==========================+==========+ | train_runtime | 292.721 | +--------------------------+----------+ | train_samples_per_second | 7.748 | +--------------------------+----------+ | train_steps_per_second | 0.232 | +--------------------------+----------+ | total_flos | 0 | +--------------------------+----------+ | train_loss | 0.222837 | +--------------------------+----------+ | epoch | 3.78873 | +--------------------------+----------+ - [multilabel_classify.py:1836:on_log] 2025-06-05 15:07:35,490 - INFO - โœจ Training Completed! โœจ - [multilabel_classify.py:1709:on_train_end] 2025-06-05 15:07:35,559 - 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 15:07:35,619 - 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 15:07:35,680 - 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 15:07:35,680 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:100:log_section] 2025-06-05 15:07:35,680 - INFO - + โœจ MODEL SAVING + - [multilabel_classify.py:101:log_section] 2025-06-05 15:07:35,680 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:104:log_section] 2025-06-05 15:07:35,680 - INFO - ๐Ÿ’พ Saving trained model and pushing to Hugging Face Hub... - [multilabel_classify.py:3706:main] 2025-06-05 15:07:35,680 - INFO - ๐Ÿ“ Creating/using output directory: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2693:save_and_push] 2025-06-05 15:07:39,183 - INFO - ๐Ÿ’พ Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2093:_save] 2025-06-05 15:07:39,184 - INFO - โš™๏ธ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2098:_save] 2025-06-05 15:07:39,186 - INFO - ๐Ÿ“‹ 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 | tokenizer.model | 0.56 MB | +---------+--------------------------------------------+------------+ | 4 | tokenizer.json | 3.50 MB | +---------+--------------------------------------------+------------+ | 5 | model.safetensors | 4267.74 MB | +---------+--------------------------------------------+------------+ | 6 | config.json | 0.00 MB | +---------+--------------------------------------------+------------+ | 7 | special_tokens_map.json | 0.00 MB | +---------+--------------------------------------------+------------+ | 8 | tokenizer_config.json | 0.13 MB | +---------+--------------------------------------------+------------+ | 9 | train_loss_plot.png | 0.02 MB | +---------+--------------------------------------------+------------+ | 10 | eval_precision_at_15_plot.png | 0.03 MB | +---------+--------------------------------------------+------------+ | 11 | README.md | 0.01 MB | +---------+--------------------------------------------+------------+ | 12 | classification_log_2025-06-05_14-33-04.log | 0.04 MB | +---------+--------------------------------------------+------------+ - [multilabel_classify.py:2115:_save] 2025-06-05 15:07:42,412 - INFO - ๐Ÿ’พ Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2093:_save] 2025-06-05 15:07:42,413 - INFO - โš™๏ธ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2098:_save] 2025-06-05 15:07:42,415 - INFO - ๐Ÿ“‹ 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 | tokenizer.model | 0.56 MB | +---------+--------------------------------------------+------------+ | 4 | tokenizer.json | 3.50 MB | +---------+--------------------------------------------+------------+ | 5 | model.safetensors | 4267.74 MB | +---------+--------------------------------------------+------------+ | 6 | config.json | 0.00 MB | +---------+--------------------------------------------+------------+ | 7 | special_tokens_map.json | 0.00 MB | +---------+--------------------------------------------+------------+ | 8 | tokenizer_config.json | 0.13 MB | +---------+--------------------------------------------+------------+ | 9 | train_loss_plot.png | 0.02 MB | +---------+--------------------------------------------+------------+ | 10 | eval_precision_at_15_plot.png | 0.03 MB | +---------+--------------------------------------------+------------+ | 11 | README.md | 0.01 MB | +---------+--------------------------------------------+------------+ | 12 | classification_log_2025-06-05_14-33-04.log | 0.04 MB | +---------+--------------------------------------------+------------+ - [multilabel_classify.py:2115:_save] 2025-06-05 15:09:03,581 - INFO - ๐Ÿ’พ Model saved to: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2697:save_and_push] 2025-06-05 15:09:03,611 - INFO - ๐Ÿ–Œ๏ธ Tokenizer saved to: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2701:save_and_push]