diff --git "a/classification_log_2025-06-16_18-00-57.log" "b/classification_log_2025-06-16_18-00-57.log" new file mode 100644--- /dev/null +++ "b/classification_log_2025-06-16_18-00-57.log" @@ -0,0 +1,1905 @@ +2025-06-16 18:00:57,977 - INFO - ================================================================================ - [multilabel_classify.py:101:log_section] +2025-06-16 18:00:57,978 - INFO - = ๐Ÿ“Œ INITIALIZING TRAINING ENVIRONMENT = - [multilabel_classify.py:102:log_section] +2025-06-16 18:00:57,978 - INFO - ================================================================================ - [multilabel_classify.py:105:log_section] +2025-06-16 18:00:57,978 - INFO - ๐Ÿš€ Setting up data paths and environment variables... - [multilabel_classify.py:3920:main] +2025-06-16 18:00:57,978 - INFO - ๐Ÿ“‚ Using output directory: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:3926:main] +2025-06-16 18:00:57,978 - INFO - ๐Ÿ› ๏ธ Command-line Arguments: - [multilabel_classify.py:369:print_args] +2025-06-16 18:00:57,978 - 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_2025-06-16_18-00-57.log + ๐Ÿ”น source: /home/ubuntu/.xcube/data/mimic4_demo - [multilabel_classify.py:370:print_args] +2025-06-16 18:00:57,978 - 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:371:print_args] +2025-06-16 18:00:57,990 - INFO - +๐Ÿš€ Quick Git Info: ๐Ÿ“ xcube | ๐ŸŒฟ plant | ๐Ÿ” cf8d41a | ๐Ÿ‘ค Debjyoti Saha Roy | โšก MIXED (1 staged, 3 unstaged) | ๐Ÿ”ฌ git show cf8d41a - [multilabel_classify.py:3932:main] +2025-06-16 18:00:57,990 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:101:log_section] +2025-06-16 18:00:57,990 - INFO - + โœจ LOADING DATASETS + - [multilabel_classify.py:102:log_section] +2025-06-16 18:00:57,990 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:105:log_section] +2025-06-16 18:00:57,990 - INFO - ๐Ÿ“Š Loading main datasets.... - [multilabel_classify.py:3935:main] +2025-06-16 18:01:06,560 - INFO - ๐Ÿ” Total unique labels in dataset: 7942 - [multilabel_classify.py:3711:sample_df_with_full_label_coverage] +2025-06-16 18:01:06,573 - INFO - ๐Ÿงช Attempt 1: Sampled 122 rows covering 863 labels. - [multilabel_classify.py:3725:sample_df_with_full_label_coverage] +2025-06-16 18:01:06,583 - INFO - ๐Ÿงช Attempt 2: Sampled 122 rows covering 816 labels. - [multilabel_classify.py:3725:sample_df_with_full_label_coverage] +2025-06-16 18:01:06,593 - INFO - ๐Ÿงช Attempt 3: Sampled 122 rows covering 885 labels. - [multilabel_classify.py:3725:sample_df_with_full_label_coverage] +2025-06-16 18:01:06,602 - INFO - ๐Ÿงช Attempt 4: Sampled 122 rows covering 828 labels. - [multilabel_classify.py:3725:sample_df_with_full_label_coverage] +2025-06-16 18:01:06,611 - INFO - ๐Ÿงช Attempt 5: Sampled 122 rows covering 879 labels. - [multilabel_classify.py:3725:sample_df_with_full_label_coverage] +2025-06-16 18:01:06,620 - INFO - ๐Ÿงช Attempt 6: Sampled 122 rows covering 852 labels. - [multilabel_classify.py:3725:sample_df_with_full_label_coverage] +2025-06-16 18:01:06,629 - INFO - ๐Ÿงช Attempt 7: Sampled 122 rows covering 838 labels. - [multilabel_classify.py:3725:sample_df_with_full_label_coverage] +2025-06-16 18:01:06,637 - INFO - ๐Ÿงช Attempt 8: Sampled 122 rows covering 851 labels. - [multilabel_classify.py:3725:sample_df_with_full_label_coverage] +2025-06-16 18:01:06,646 - INFO - ๐Ÿงช Attempt 9: Sampled 122 rows covering 825 labels. - [multilabel_classify.py:3725:sample_df_with_full_label_coverage] +2025-06-16 18:01:06,655 - INFO - ๐Ÿงช Attempt 10: Sampled 122 rows covering 833 labels. - [multilabel_classify.py:3725:sample_df_with_full_label_coverage] +2025-06-16 18:01:06,659 - INFO - ๐Ÿ› ๏ธ Fixing missing labels: 7109 remaining... - [multilabel_classify.py:3758:sample_df_with_full_label_coverage] +2025-06-16 18:04:43,351 - INFO - โœ… Added 1648 rows to achieve full label coverage. - [multilabel_classify.py:3790:sample_df_with_full_label_coverage] +2025-06-16 18:04:43,353 - INFO - ๐Ÿ“Š Final total labels: 7942 - [multilabel_classify.py:3793:sample_df_with_full_label_coverage] +2025-06-16 18:04:43,354 - INFO - โœ… Final row count: 1770 (Valid: 420, Not-valid: 1350) - [multilabel_classify.py:3801:sample_df_with_full_label_coverage] +2025-06-16 18:04:44,124 - INFO - ******************************************************************************** - [multilabel_classify.py:101:log_section] +2025-06-16 18:04:44,125 - INFO - * ๐ŸŒŸ STARTING MULTI_LABEL CLASSIFICATION MODEL TRAINING * - [multilabel_classify.py:102:log_section] +2025-06-16 18:04:44,125 - INFO - ******************************************************************************** - [multilabel_classify.py:105:log_section] +2025-06-16 18:04:44,125 - INFO - ๐Ÿ” Loaded authentication token from environment - [multilabel_classify.py:3962:main] +2025-06-16 18:04:44,125 - INFO - ๐Ÿท๏ธ Hub Model ID for this Classification task: deb101/mistral-7b-instruct-v0.3-mimic4-adapt-multilabel-classify - [multilabel_classify.py:3966:main] +2025-06-16 18:04:44,125 - INFO - -------------------------------------------------------------------------------- - [multilabel_classify.py:101:log_section] +2025-06-16 18:04:44,125 - INFO - - ๐Ÿ“‹ MODEL EXISTENCE CHECK - - [multilabel_classify.py:102:log_section] +2025-06-16 18:04:44,125 - INFO - -------------------------------------------------------------------------------- - [multilabel_classify.py:105:log_section] +2025-06-16 18:04:44,125 - INFO - ๐Ÿ” Checking model existence locally and on Hugging Face Hub... - [multilabel_classify.py:3826:check_model_existence] +2025-06-16 18:04:44,125 - INFO - โŒ Model not found locally at: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:3833:check_model_existence] +2025-06-16 18:05:03,454 - INFO - โœ… Model exists on Hugging Face Hub with ID: deb101/mistral-7b-instruct-v0.3-mimic4-adapt-multilabel-classify - [multilabel_classify.py:3845:check_model_existence] +2025-06-16 18:05:03,455 - INFO - ๐Ÿ“ Model exists either locally or on Hub - [multilabel_classify.py:3871:check_model_existence] +2025-06-16 18:05:03,455 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:101:log_section] +2025-06-16 18:05:03,455 - INFO - + โœจ STARTING FRESH TRAINING + - [multilabel_classify.py:102:log_section] +2025-06-16 18:05:03,455 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:105:log_section] +2025-06-16 18:05:03,455 - INFO - ๐Ÿ”„ Starting fresh training (either forced or model not found)... - [multilabel_classify.py:3979:main] +2025-06-16 18:05:10,923 - 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] +2025-06-16 18:05:10,924 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:101:log_section] +2025-06-16 18:05:10,924 - INFO - + โœจ LOADING BASE MODEL + - [multilabel_classify.py:102:log_section] +2025-06-16 18:05:10,924 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:105:log_section] +2025-06-16 18:05:10,924 - INFO - ๐Ÿ“ฅ Loading pretrained model and tokenizer... - [multilabel_classify.py:4011:main] +2025-06-16 18:05:10,924 - INFO - ๐Ÿš€ Starting model and tokenizer loading process... - [multilabel_classify.py:1583:load_base_model_and_tokenizer] +2025-06-16 18:05:10,925 - INFO - ๐Ÿ“Š Quantization config: 4-bit, nf4, double_quant, bfloat16 - [multilabel_classify.py:1592:load_base_model_and_tokenizer] +2025-06-16 18:05:10,925 - INFO - ๐Ÿ”ค Loading tokenizer for model: deb101/mistral-7b-instruct-v0.3-mimic4-adapt... - [multilabel_classify.py:1596:load_base_model_and_tokenizer] +2025-06-16 18:05:21,210 - INFO - ๐Ÿ” Checking if deb101/mistral-7b-instruct-v0.3-mimic4-adapt is a PEFT model... - [multilabel_classify.py:1607:load_base_model_and_tokenizer] +2025-06-16 18:05:31,236 - INFO - โœ… Detected PEFT model. Base model: mistralai/Mistral-7B-Instruct-v0.3 - [multilabel_classify.py:1611:load_base_model_and_tokenizer] +2025-06-16 18:05:31,236 - INFO - ๐Ÿ” Loading model configuration for mistralai/Mistral-7B-Instruct-v0.3... - [multilabel_classify.py:1619:load_base_model_and_tokenizer] +2025-06-16 18:05:41,258 - INFO - Model type: mistral, Architectures: ['MistralForCausalLM'] - [multilabel_classify.py:1634:load_base_model_and_tokenizer] +2025-06-16 18:05:41,259 - INFO - ๐Ÿง  Loading base model: mistralai/Mistral-7B-Instruct-v0.3... - [multilabel_classify.py:1702:load_base_model_and_tokenizer] +2025-06-16 18:05:51,805 - 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] +2025-06-16 18:06:07,166 - INFO - ๐Ÿงฉ Loading PEFT adapters for deb101/mistral-7b-instruct-v0.3-mimic4-adapt... - [multilabel_classify.py:1722:load_base_model_and_tokenizer] +2025-06-16 18:06:46,612 - INFO - ๐Ÿ”ง Before enabling PEFT adapters - [multilabel_classify.py:1724:load_base_model_and_tokenizer] +2025-06-16 18:06:46,614 - INFO - ๐Ÿ“Š trainable params: 0 || all params: 7,254,839,296 || trainable%: 0.0000 - [multilabel_classify.py:160:log_print_output] +2025-06-16 18:06:46,617 - INFO - Enabled gradients for parameters: ['base_model.model.model.layers.0.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.0.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.0.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.0.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.1.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.1.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.1.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.1.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.2.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.2.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.2.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.2.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.3.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.3.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.3.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.3.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.4.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.4.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.4.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.4.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.5.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.5.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.5.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.5.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.6.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.6.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.6.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.6.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.7.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.7.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.7.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.7.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.8.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.8.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.8.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.8.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.9.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.9.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.9.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.9.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.10.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.10.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.10.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.10.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.11.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.11.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.11.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.11.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.12.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.12.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.12.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.12.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.13.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.13.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.13.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.13.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.14.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.14.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.14.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.14.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.15.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.15.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.15.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.15.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.16.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.16.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.16.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.16.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.17.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.17.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.17.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.17.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.18.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.18.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.18.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.18.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.19.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.19.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.19.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.19.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.20.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.20.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.20.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.20.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.21.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.21.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.21.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.21.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.22.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.22.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.22.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.22.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.23.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.23.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.23.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.23.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.24.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.24.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.24.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.24.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.25.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.25.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.25.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.25.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.26.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.26.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.26.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.26.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.27.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.27.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.27.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.27.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.28.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.28.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.28.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.28.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.29.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.29.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.29.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.29.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.30.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.30.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.30.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.30.self_attn.v_proj.lora_B.default.weight', 'base_model.model.model.layers.31.self_attn.q_proj.lora_A.default.weight', 'base_model.model.model.layers.31.self_attn.q_proj.lora_B.default.weight', 'base_model.model.model.layers.31.self_attn.v_proj.lora_A.default.weight', 'base_model.model.model.layers.31.self_attn.v_proj.lora_B.default.weight'] - [multilabel_classify.py:1734:load_base_model_and_tokenizer] +2025-06-16 18:06:46,617 - INFO - ๐Ÿ”ง After enabling PEFT adapters - [multilabel_classify.py:1735:load_base_model_and_tokenizer] +2025-06-16 18:06:46,619 - INFO - ๐Ÿ“Š trainable params: 6,815,744 || all params: 7,254,839,296 || trainable%: 0.0939 - [multilabel_classify.py:160:log_print_output] +2025-06-16 18:06:46,620 - INFO - โœ… Model and tokenizer successfully loaded! - [multilabel_classify.py:1773:load_base_model_and_tokenizer] +2025-06-16 18:06:46,620 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:101:log_section] +2025-06-16 18:06:46,621 - INFO - + โœจ DATA PREPROCESSING + - [multilabel_classify.py:102:log_section] +2025-06-16 18:06:46,621 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:105:log_section] +2025-06-16 18:06:46,621 - INFO - ๐Ÿ”„ Loading and preprocessing training data... - [multilabel_classify.py:4021:main] +2025-06-16 18:06:46,799 - INFO - Total number of labels: 7942 - [multilabel_classify.py:1176:preprocess_data] +2025-06-16 18:06:46,800 - INFO - Rare labels (freq < 50): 7817 - [multilabel_classify.py:1177:preprocess_data] +2025-06-16 18:06:46,800 - INFO - Not rare labels (freq >= 50): 125 - [multilabel_classify.py:1178:preprocess_data] +2025-06-16 18:06:46,800 - INFO - Label partitions and classes saved to ../tmp/MIMIC4_DEMO/labels_partition.json - [multilabel_classify.py:1179:preprocess_data] +2025-06-16 18:07:43,902 - INFO - The size of training set: 8393 - [multilabel_classify.py:1275:preprocess_data] +2025-06-16 18:07:43,902 - INFO - The size of Evaluation set: 2528 - [multilabel_classify.py:1276:preprocess_data] +2025-06-16 18:07:44,309 - INFO - Number of unique ICD-10 codes: 7942 - [multilabel_classify.py:4027:main] +2025-06-16 18:07:44,311 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:101:log_section] +2025-06-16 18:07:44,311 - INFO - + โœจ MODEL INITIALIZATION + - [multilabel_classify.py:102:log_section] +2025-06-16 18:07:44,311 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:105:log_section] +2025-06-16 18:07:44,311 - INFO - ๐Ÿง  Initializing custom L2R model for outputting per-token relevance scores per ICD-10 codes. - [multilabel_classify.py:4030:main] +2025-06-16 18:07:44,312 - INFO - ๐Ÿฅ๐Ÿ“Š Creating MultilabelICDClassifier - Standard multilabel medical classifier! ๐Ÿ”ฌ๐Ÿ’ซ - [multilabel_classify.py:864:define_model] +2025-06-16 18:07:44,312 - INFO - Will now start to create Multilabel-Classification Model from the base model - [multilabel_classify.py:565:__init__] +2025-06-16 18:07:44,316 - INFO - ๐Ÿ“Š trainable params: 6,815,744 || all params: 3,765,178,368 || trainable%: 0.1810 - [utils.py:474:compute_trainable_params] +2025-06-16 18:07:46,041 - INFO - Creating the Multi-Label Classification Model from base model mistralai/Mistral-7B-Instruct-v0.3 completed!!! - [multilabel_classify.py:607:__init__] +2025-06-16 18:07:46,045 - INFO - ๐Ÿ“Š trainable params: 171,532,417 || all params: 3,929,895,041 || trainable%: 4.3648 - [utils.py:474:compute_trainable_params] +2025-06-16 18:07:46,045 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:101:log_section] +2025-06-16 18:07:46,045 - INFO - + โœจ TRAINING PREPARATION + - [multilabel_classify.py:102:log_section] +2025-06-16 18:07:46,045 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:105:log_section] +2025-06-16 18:07:46,045 - INFO - โš™๏ธ Preparing training components and optimizers... - [multilabel_classify.py:4037:main] +2025-06-16 18:07:46,130 - INFO - ๐Ÿ–ฅ๏ธ Device: NVIDIA GH200 480GB - [multilabel_classify.py:1023:log_training_configuration] +2025-06-16 18:07:46,130 - INFO - ๐Ÿ”‹ CUDA Available: True - [multilabel_classify.py:1026:log_training_configuration] +2025-06-16 18:07:46,130 - INFO - ๐Ÿ’พ CUDA Device Count: 1 - [multilabel_classify.py:1027:log_training_configuration] +2025-06-16 18:07:46,132 - 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 | 262 | +| ๐Ÿ”ข | Total Training Steps | 1048 | +| ๐Ÿ”ข | Evaluation Steps | 316 | +| ๐Ÿ“Š | Training Dataset Size | 8393 samples ๐Ÿ‹๏ธ | +| ๐Ÿ“Š | Evaluation Dataset Size | 2528 samples ๐Ÿ” | ++----------+-----------------------------+------------------------------------------------------------------+ - [multilabel_classify.py:1015:log_training_args] +2025-06-16 18:07:46,132 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:101:log_section] +2025-06-16 18:07:46,132 - INFO - + โœจ MODEL TRAINING + - [multilabel_classify.py:102:log_section] +2025-06-16 18:07:46,132 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:105:log_section] +2025-06-16 18:07:46,133 - INFO - ๐Ÿ‹๏ธ Starting model training process... - [multilabel_classify.py:4059:main] +2025-06-16 18:08:46,629 - INFO - We are registering the tokenizer deb101/mistral-7b-instruct-v0.3-mimic4-adapt in Custom Trainer - [multilabel_classify.py:2344:__init__] +2025-06-16 18:08:46,892 - INFO - ๐Ÿš€ Starting Training... - [multilabel_classify.py:1998:on_train_begin] +2025-06-16 18:09:10,541 - INFO - +๐Ÿš‚ Training Metrics (Step 10) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.5786 | ++---------------+----------+ +| grad_norm | 6.61274 | ++---------------+----------+ +| learning_rate | 2e-06 | ++---------------+----------+ +| epoch | 0.038095 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:09:30,123 - INFO - +๐Ÿš‚ Training Metrics (Step 20) ๐Ÿš‚ ++---------------+---------+ +| Metric | Value | ++===============+=========+ +| loss | 0.2979 | ++---------------+---------+ +| grad_norm | 2.50729 | ++---------------+---------+ +| learning_rate | 4e-06 | ++---------------+---------+ +| epoch | 0.07619 | ++---------------+---------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:09:49,704 - INFO - +๐Ÿš‚ Training Metrics (Step 30) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0651 | ++---------------+----------+ +| grad_norm | 0.2233 | ++---------------+----------+ +| learning_rate | 6e-06 | ++---------------+----------+ +| epoch | 0.114286 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:10:09,181 - INFO - +๐Ÿš‚ Training Metrics (Step 40) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0231 | ++---------------+----------+ +| grad_norm | 0.09893 | ++---------------+----------+ +| learning_rate | 8e-06 | ++---------------+----------+ +| epoch | 0.152381 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:10:28,675 - INFO - +๐Ÿš‚ Training Metrics (Step 50) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0278 | ++---------------+----------+ +| grad_norm | 0.147324 | ++---------------+----------+ +| learning_rate | 1e-05 | ++---------------+----------+ +| epoch | 0.190476 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:10:48,153 - INFO - +๐Ÿš‚ Training Metrics (Step 60) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0268 | ++---------------+----------+ +| grad_norm | 0.129953 | ++---------------+----------+ +| learning_rate | 1.2e-05 | ++---------------+----------+ +| epoch | 0.228571 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:11:07,647 - INFO - +๐Ÿš‚ Training Metrics (Step 70) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0243 | ++---------------+----------+ +| grad_norm | 0.030411 | ++---------------+----------+ +| learning_rate | 1.4e-05 | ++---------------+----------+ +| epoch | 0.266667 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:11:27,127 - INFO - +๐Ÿš‚ Training Metrics (Step 80) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0233 | ++---------------+----------+ +| grad_norm | 0.03486 | ++---------------+----------+ +| learning_rate | 1.6e-05 | ++---------------+----------+ +| epoch | 0.304762 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:11:46,621 - INFO - +๐Ÿš‚ Training Metrics (Step 90) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0235 | ++---------------+----------+ +| grad_norm | 0.036425 | ++---------------+----------+ +| learning_rate | 1.8e-05 | ++---------------+----------+ +| epoch | 0.342857 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:12:06,120 - INFO - +๐Ÿš‚ Training Metrics (Step 100) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0241 | ++---------------+----------+ +| grad_norm | 0.159289 | ++---------------+----------+ +| learning_rate | 2e-05 | ++---------------+----------+ +| epoch | 0.380952 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:12:25,607 - INFO - +๐Ÿš‚ Training Metrics (Step 110) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0229 | ++---------------+----------+ +| grad_norm | 0.01171 | ++---------------+----------+ +| learning_rate | 2.2e-05 | ++---------------+----------+ +| epoch | 0.419048 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:12:45,093 - INFO - +๐Ÿš‚ Training Metrics (Step 120) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0223 | ++---------------+----------+ +| grad_norm | 0.011407 | ++---------------+----------+ +| learning_rate | 2.4e-05 | ++---------------+----------+ +| epoch | 0.457143 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:13:04,597 - INFO - +๐Ÿš‚ Training Metrics (Step 130) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0234 | ++---------------+----------+ +| grad_norm | 0.008729 | ++---------------+----------+ +| learning_rate | 2.6e-05 | ++---------------+----------+ +| epoch | 0.495238 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:13:24,089 - INFO - +๐Ÿš‚ Training Metrics (Step 140) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0233 | ++---------------+----------+ +| grad_norm | 0.007958 | ++---------------+----------+ +| learning_rate | 2.8e-05 | ++---------------+----------+ +| epoch | 0.533333 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:13:43,573 - INFO - +๐Ÿš‚ Training Metrics (Step 150) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0227 | ++---------------+----------+ +| grad_norm | 0.027206 | ++---------------+----------+ +| learning_rate | 3e-05 | ++---------------+----------+ +| epoch | 0.571429 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:14:03,062 - INFO - +๐Ÿš‚ Training Metrics (Step 160) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0218 | ++---------------+----------+ +| grad_norm | 0.015988 | ++---------------+----------+ +| learning_rate | 3.2e-05 | ++---------------+----------+ +| epoch | 0.609524 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:14:22,517 - INFO - +๐Ÿš‚ Training Metrics (Step 170) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0216 | ++---------------+----------+ +| grad_norm | 0.010847 | ++---------------+----------+ +| learning_rate | 3.4e-05 | ++---------------+----------+ +| epoch | 0.647619 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:14:41,988 - INFO - +๐Ÿš‚ Training Metrics (Step 180) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0231 | ++---------------+----------+ +| grad_norm | 0.020155 | ++---------------+----------+ +| learning_rate | 3.6e-05 | ++---------------+----------+ +| epoch | 0.685714 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:15:01,468 - INFO - +๐Ÿš‚ Training Metrics (Step 190) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0236 | ++---------------+----------+ +| grad_norm | 0.004788 | ++---------------+----------+ +| learning_rate | 3.8e-05 | ++---------------+----------+ +| epoch | 0.72381 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:15:20,960 - INFO - +๐Ÿš‚ Training Metrics (Step 200) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0231 | ++---------------+----------+ +| grad_norm | 0.022587 | ++---------------+----------+ +| learning_rate | 4e-05 | ++---------------+----------+ +| epoch | 0.761905 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:15:40,446 - INFO - +๐Ÿš‚ Training Metrics (Step 210) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0222 | ++---------------+----------+ +| grad_norm | 0.007002 | ++---------------+----------+ +| learning_rate | 4.2e-05 | ++---------------+----------+ +| epoch | 0.8 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:15:59,940 - INFO - +๐Ÿš‚ Training Metrics (Step 220) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0225 | ++---------------+----------+ +| grad_norm | 0.011847 | ++---------------+----------+ +| learning_rate | 4.4e-05 | ++---------------+----------+ +| epoch | 0.838095 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:16:19,427 - INFO - +๐Ÿš‚ Training Metrics (Step 230) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0238 | ++---------------+----------+ +| grad_norm | 0.007445 | ++---------------+----------+ +| learning_rate | 4.6e-05 | ++---------------+----------+ +| epoch | 0.87619 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:16:38,917 - INFO - +๐Ÿš‚ Training Metrics (Step 240) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0222 | ++---------------+----------+ +| grad_norm | 0.005909 | ++---------------+----------+ +| learning_rate | 4.8e-05 | ++---------------+----------+ +| epoch | 0.914286 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:16:58,403 - INFO - +๐Ÿš‚ Training Metrics (Step 250) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0232 | ++---------------+----------+ +| grad_norm | 0.01134 | ++---------------+----------+ +| learning_rate | 5e-05 | ++---------------+----------+ +| epoch | 0.952381 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:17:17,886 - INFO - +๐Ÿš‚ Training Metrics (Step 260) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0229 | ++---------------+----------+ +| grad_norm | 0.010347 | ++---------------+----------+ +| learning_rate | 5.2e-05 | ++---------------+----------+ +| epoch | 0.990476 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:17:22,267 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [multilabel_classify.py:2356:evaluate] +2025-06-16 18:30:57,773 - INFO - +๐Ÿ” Evaluation Metrics ๐Ÿ” ++-------------------------------+----------+ +| Metric | Value | ++===============================+==========+ +| eval_f1_micro | 0 | ++-------------------------------+----------+ +| eval_f1_macro | 0 | ++-------------------------------+----------+ +| eval_precision_at_5 | 0.276899 | ++-------------------------------+----------+ +| eval_recall_at_5 | 0.064377 | ++-------------------------------+----------+ +| eval_precision_at_8 | 0.247231 | ++-------------------------------+----------+ +| eval_recall_at_8 | 0.088033 | ++-------------------------------+----------+ +| eval_precision_at_15 | 0.188265 | ++-------------------------------+----------+ +| eval_recall_at_15 | 0.12263 | ++-------------------------------+----------+ +| eval_rare_f1_micro | 0 | ++-------------------------------+----------+ +| eval_rare_f1_macro | 0 | ++-------------------------------+----------+ +| eval_rare_precision | 0 | ++-------------------------------+----------+ +| eval_rare_recall | 0 | ++-------------------------------+----------+ +| eval_rare_precision_at_5 | 0.007832 | ++-------------------------------+----------+ +| eval_rare_recall_at_5 | 0.002522 | ++-------------------------------+----------+ +| eval_rare_precision_at_8 | 0.007466 | ++-------------------------------+----------+ +| eval_rare_recall_at_8 | 0.003996 | ++-------------------------------+----------+ +| eval_rare_precision_at_15 | 0.006962 | ++-------------------------------+----------+ +| eval_rare_recall_at_15 | 0.006522 | ++-------------------------------+----------+ +| eval_not_rare_f1_micro | 0 | ++-------------------------------+----------+ +| eval_not_rare_f1_macro | 0 | ++-------------------------------+----------+ +| eval_not_rare_precision | 0 | ++-------------------------------+----------+ +| eval_not_rare_recall | 0 | ++-------------------------------+----------+ +| eval_not_rare_precision_at_5 | 0.277136 | ++-------------------------------+----------+ +| eval_not_rare_recall_at_5 | 0.170671 | ++-------------------------------+----------+ +| eval_not_rare_precision_at_8 | 0.24733 | ++-------------------------------+----------+ +| eval_not_rare_recall_at_8 | 0.234122 | ++-------------------------------+----------+ +| eval_not_rare_precision_at_15 | 0.188792 | ++-------------------------------+----------+ +| eval_not_rare_recall_at_15 | 0.324266 | ++-------------------------------+----------+ +| eval_loss | 0.02093 | ++-------------------------------+----------+ - [multilabel_classify.py:2211:on_evaluate] +2025-06-16 18:30:59,092 - INFO - ๐Ÿ’พ Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-262 - [multilabel_classify.py:2449:_save] +2025-06-16 18:30:59,094 - INFO - โš™๏ธ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-262 - [multilabel_classify.py:2454:_save] +2025-06-16 18:30:59,095 - INFO - ๐Ÿ“‹ Saved files in ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-262: ++---------+-------------------+------------+ +| Index | Saved File | Size | ++=========+===================+============+ +| 1 | training_args.bin | 0.01 MB | ++---------+-------------------+------------+ +| 2 | model.safetensors | 4600.97 MB | ++---------+-------------------+------------+ +| 3 | config.json | 0.00 MB | ++---------+-------------------+------------+ - [multilabel_classify.py:2471:_save] +2025-06-16 18:31:17,991 - INFO - +๐Ÿš‚ Training Metrics (Step 270) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.023 | ++---------------+----------+ +| grad_norm | 0.016343 | ++---------------+----------+ +| learning_rate | 5.4e-05 | ++---------------+----------+ +| epoch | 1.03048 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:31:37,431 - INFO - +๐Ÿš‚ Training Metrics (Step 280) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0217 | ++---------------+----------+ +| grad_norm | 0.005856 | ++---------------+----------+ +| learning_rate | 5.6e-05 | ++---------------+----------+ +| epoch | 1.06857 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:31:56,913 - INFO - +๐Ÿš‚ Training Metrics (Step 290) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0229 | ++---------------+----------+ +| grad_norm | 0.009098 | ++---------------+----------+ +| learning_rate | 5.8e-05 | ++---------------+----------+ +| epoch | 1.10667 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:32:16,404 - INFO - +๐Ÿš‚ Training Metrics (Step 300) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0236 | ++---------------+----------+ +| grad_norm | 0.022614 | ++---------------+----------+ +| learning_rate | 6e-05 | ++---------------+----------+ +| epoch | 1.14476 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:32:35,906 - INFO - +๐Ÿš‚ Training Metrics (Step 310) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0226 | ++---------------+----------+ +| grad_norm | 0.013578 | ++---------------+----------+ +| learning_rate | 6.2e-05 | ++---------------+----------+ +| epoch | 1.18286 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:32:55,390 - INFO - +๐Ÿš‚ Training Metrics (Step 320) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0223 | ++---------------+----------+ +| grad_norm | 0.003184 | ++---------------+----------+ +| learning_rate | 6.4e-05 | ++---------------+----------+ +| epoch | 1.22095 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:33:15,069 - INFO - +๐Ÿš‚ Training Metrics (Step 330) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.023 | ++---------------+----------+ +| grad_norm | 0.019315 | ++---------------+----------+ +| learning_rate | 6.6e-05 | ++---------------+----------+ +| epoch | 1.25905 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:33:34,555 - INFO - +๐Ÿš‚ Training Metrics (Step 340) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0225 | ++---------------+----------+ +| grad_norm | 0.018046 | ++---------------+----------+ +| learning_rate | 6.8e-05 | ++---------------+----------+ +| epoch | 1.29714 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:33:54,043 - INFO - +๐Ÿš‚ Training Metrics (Step 350) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0231 | ++---------------+----------+ +| grad_norm | 0.015778 | ++---------------+----------+ +| learning_rate | 7e-05 | ++---------------+----------+ +| epoch | 1.33524 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:34:13,538 - INFO - +๐Ÿš‚ Training Metrics (Step 360) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0228 | ++---------------+----------+ +| grad_norm | 0.007371 | ++---------------+----------+ +| learning_rate | 7.2e-05 | ++---------------+----------+ +| epoch | 1.37333 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:34:33,040 - INFO - +๐Ÿš‚ Training Metrics (Step 370) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0223 | ++---------------+----------+ +| grad_norm | 0.012295 | ++---------------+----------+ +| learning_rate | 7.4e-05 | ++---------------+----------+ +| epoch | 1.41143 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:34:52,552 - INFO - +๐Ÿš‚ Training Metrics (Step 380) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0217 | ++---------------+----------+ +| grad_norm | 0.028032 | ++---------------+----------+ +| learning_rate | 7.6e-05 | ++---------------+----------+ +| epoch | 1.44952 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:35:12,089 - INFO - +๐Ÿš‚ Training Metrics (Step 390) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0197 | ++---------------+----------+ +| grad_norm | 0.013432 | ++---------------+----------+ +| learning_rate | 7.8e-05 | ++---------------+----------+ +| epoch | 1.48762 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:35:31,624 - INFO - +๐Ÿš‚ Training Metrics (Step 400) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0198 | ++---------------+----------+ +| grad_norm | 0.027268 | ++---------------+----------+ +| learning_rate | 8e-05 | ++---------------+----------+ +| epoch | 1.52571 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:35:51,161 - INFO - +๐Ÿš‚ Training Metrics (Step 410) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0193 | ++---------------+----------+ +| grad_norm | 0.017981 | ++---------------+----------+ +| learning_rate | 8.2e-05 | ++---------------+----------+ +| epoch | 1.56381 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:36:10,684 - INFO - +๐Ÿš‚ Training Metrics (Step 420) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0182 | ++---------------+----------+ +| grad_norm | 0.020879 | ++---------------+----------+ +| learning_rate | 8.4e-05 | ++---------------+----------+ +| epoch | 1.6019 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:36:30,217 - INFO - +๐Ÿš‚ Training Metrics (Step 430) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0185 | ++---------------+----------+ +| grad_norm | 0.015975 | ++---------------+----------+ +| learning_rate | 8.6e-05 | ++---------------+----------+ +| epoch | 1.64 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:36:49,726 - INFO - +๐Ÿš‚ Training Metrics (Step 440) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0177 | ++---------------+----------+ +| grad_norm | 0.006284 | ++---------------+----------+ +| learning_rate | 8.8e-05 | ++---------------+----------+ +| epoch | 1.67809 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:37:09,223 - INFO - +๐Ÿš‚ Training Metrics (Step 450) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0182 | ++---------------+----------+ +| grad_norm | 0.010877 | ++---------------+----------+ +| learning_rate | 9e-05 | ++---------------+----------+ +| epoch | 1.71619 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:37:28,750 - INFO - +๐Ÿš‚ Training Metrics (Step 460) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0181 | ++---------------+----------+ +| grad_norm | 0.010465 | ++---------------+----------+ +| learning_rate | 9.2e-05 | ++---------------+----------+ +| epoch | 1.75429 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:37:48,279 - INFO - +๐Ÿš‚ Training Metrics (Step 470) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0188 | ++---------------+----------+ +| grad_norm | 0.023603 | ++---------------+----------+ +| learning_rate | 9.4e-05 | ++---------------+----------+ +| epoch | 1.79238 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:38:07,816 - INFO - +๐Ÿš‚ Training Metrics (Step 480) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0187 | ++---------------+----------+ +| grad_norm | 0.029903 | ++---------------+----------+ +| learning_rate | 9.6e-05 | ++---------------+----------+ +| epoch | 1.83048 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:38:27,360 - INFO - +๐Ÿš‚ Training Metrics (Step 490) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0187 | ++---------------+----------+ +| grad_norm | 0.024319 | ++---------------+----------+ +| learning_rate | 9.8e-05 | ++---------------+----------+ +| epoch | 1.86857 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:38:46,901 - INFO - +๐Ÿš‚ Training Metrics (Step 500) ๐Ÿš‚ ++---------------+---------+ +| Metric | Value | ++===============+=========+ +| loss | 0.0181 | ++---------------+---------+ +| grad_norm | 0.02574 | ++---------------+---------+ +| learning_rate | 0.0001 | ++---------------+---------+ +| epoch | 1.90667 | ++---------------+---------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:39:06,405 - INFO - +๐Ÿš‚ Training Metrics (Step 510) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0174 | ++---------------+----------+ +| grad_norm | 0.016141 | ++---------------+----------+ +| learning_rate | 0.0001 | ++---------------+----------+ +| epoch | 1.94476 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:39:25,924 - INFO - +๐Ÿš‚ Training Metrics (Step 520) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0181 | ++---------------+----------+ +| grad_norm | 0.007738 | ++---------------+----------+ +| learning_rate | 0.0001 | ++---------------+----------+ +| epoch | 1.98286 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:39:34,215 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [multilabel_classify.py:2356:evaluate] +2025-06-16 18:52:58,617 - INFO - +๐Ÿ” Evaluation Metrics ๐Ÿ” ++-------------------------------+----------+ +| Metric | Value | ++===============================+==========+ +| eval_f1_micro | 0 | ++-------------------------------+----------+ +| eval_f1_macro | 0 | ++-------------------------------+----------+ +| eval_precision_at_5 | 0.277532 | ++-------------------------------+----------+ +| eval_recall_at_5 | 0.065113 | ++-------------------------------+----------+ +| eval_precision_at_8 | 0.254203 | ++-------------------------------+----------+ +| eval_recall_at_8 | 0.091028 | ++-------------------------------+----------+ +| eval_precision_at_15 | 0.193434 | ++-------------------------------+----------+ +| eval_recall_at_15 | 0.127009 | ++-------------------------------+----------+ +| eval_rare_f1_micro | 0 | ++-------------------------------+----------+ +| eval_rare_f1_macro | 0 | ++-------------------------------+----------+ +| eval_rare_precision | 0 | ++-------------------------------+----------+ +| eval_rare_recall | 0 | ++-------------------------------+----------+ +| eval_rare_precision_at_5 | 0.029509 | ++-------------------------------+----------+ +| eval_rare_recall_at_5 | 0.009105 | ++-------------------------------+----------+ +| eval_rare_precision_at_8 | 0.025069 | ++-------------------------------+----------+ +| eval_rare_recall_at_8 | 0.012753 | ++-------------------------------+----------+ +| eval_rare_precision_at_15 | 0.022969 | ++-------------------------------+----------+ +| eval_rare_recall_at_15 | 0.021418 | ++-------------------------------+----------+ +| eval_not_rare_f1_micro | 0 | ++-------------------------------+----------+ +| eval_not_rare_f1_macro | 0 | ++-------------------------------+----------+ +| eval_not_rare_precision | 0 | ++-------------------------------+----------+ +| eval_not_rare_recall | 0 | ++-------------------------------+----------+ +| eval_not_rare_precision_at_5 | 0.277373 | ++-------------------------------+----------+ +| eval_not_rare_recall_at_5 | 0.171545 | ++-------------------------------+----------+ +| eval_not_rare_precision_at_8 | 0.254203 | ++-------------------------------+----------+ +| eval_not_rare_recall_at_8 | 0.240055 | ++-------------------------------+----------+ +| eval_not_rare_precision_at_15 | 0.193302 | ++-------------------------------+----------+ +| eval_not_rare_recall_at_15 | 0.33663 | ++-------------------------------+----------+ +| eval_loss | 0.016997 | ++-------------------------------+----------+ - [multilabel_classify.py:2211:on_evaluate] +2025-06-16 18:52:59,937 - INFO - ๐Ÿ’พ Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-524 - [multilabel_classify.py:2449:_save] +2025-06-16 18:52:59,939 - INFO - โš™๏ธ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-524 - [multilabel_classify.py:2454:_save] +2025-06-16 18:52:59,940 - INFO - ๐Ÿ“‹ Saved files in ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-524: ++---------+-------------------+------------+ +| Index | Saved File | Size | ++=========+===================+============+ +| 1 | training_args.bin | 0.01 MB | ++---------+-------------------+------------+ +| 2 | model.safetensors | 4600.97 MB | ++---------+-------------------+------------+ +| 3 | config.json | 0.00 MB | ++---------+-------------------+------------+ - [multilabel_classify.py:2471:_save] +2025-06-16 18:53:14,917 - INFO - +๐Ÿš‚ Training Metrics (Step 530) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0174 | ++---------------+----------+ +| grad_norm | 0.017119 | ++---------------+----------+ +| learning_rate | 9.9e-05 | ++---------------+----------+ +| epoch | 2.02286 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:53:34,401 - INFO - +๐Ÿš‚ Training Metrics (Step 540) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0185 | ++---------------+----------+ +| grad_norm | 0.020773 | ++---------------+----------+ +| learning_rate | 9.9e-05 | ++---------------+----------+ +| epoch | 2.06095 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:53:53,887 - INFO - +๐Ÿš‚ Training Metrics (Step 550) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0181 | ++---------------+----------+ +| grad_norm | 0.028108 | ++---------------+----------+ +| learning_rate | 9.8e-05 | ++---------------+----------+ +| epoch | 2.09905 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:54:13,389 - INFO - +๐Ÿš‚ Training Metrics (Step 560) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0179 | ++---------------+----------+ +| grad_norm | 0.010793 | ++---------------+----------+ +| learning_rate | 9.7e-05 | ++---------------+----------+ +| epoch | 2.13714 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:54:32,877 - INFO - +๐Ÿš‚ Training Metrics (Step 570) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0175 | ++---------------+----------+ +| grad_norm | 0.028471 | ++---------------+----------+ +| learning_rate | 9.6e-05 | ++---------------+----------+ +| epoch | 2.17524 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:54:52,379 - INFO - +๐Ÿš‚ Training Metrics (Step 580) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0175 | ++---------------+----------+ +| grad_norm | 0.031605 | ++---------------+----------+ +| learning_rate | 9.5e-05 | ++---------------+----------+ +| epoch | 2.21333 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:55:11,913 - INFO - +๐Ÿš‚ Training Metrics (Step 590) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0181 | ++---------------+----------+ +| grad_norm | 0.006935 | ++---------------+----------+ +| learning_rate | 9.4e-05 | ++---------------+----------+ +| epoch | 2.25143 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:55:31,420 - INFO - +๐Ÿš‚ Training Metrics (Step 600) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0183 | ++---------------+----------+ +| grad_norm | 0.026774 | ++---------------+----------+ +| learning_rate | 9.2e-05 | ++---------------+----------+ +| epoch | 2.28952 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:55:50,930 - INFO - +๐Ÿš‚ Training Metrics (Step 610) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0175 | ++---------------+----------+ +| grad_norm | 0.010172 | ++---------------+----------+ +| learning_rate | 9e-05 | ++---------------+----------+ +| epoch | 2.32762 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:56:10,447 - INFO - +๐Ÿš‚ Training Metrics (Step 620) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0173 | ++---------------+----------+ +| grad_norm | 0.007341 | ++---------------+----------+ +| learning_rate | 8.9e-05 | ++---------------+----------+ +| epoch | 2.36571 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:56:29,953 - INFO - +๐Ÿš‚ Training Metrics (Step 630) ๐Ÿš‚ ++---------------+---------+ +| Metric | Value | ++===============+=========+ +| loss | 0.0178 | ++---------------+---------+ +| grad_norm | 0.00705 | ++---------------+---------+ +| learning_rate | 8.7e-05 | ++---------------+---------+ +| epoch | 2.40381 | ++---------------+---------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:56:49,469 - INFO - +๐Ÿš‚ Training Metrics (Step 640) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0174 | ++---------------+----------+ +| grad_norm | 0.019678 | ++---------------+----------+ +| learning_rate | 8.5e-05 | ++---------------+----------+ +| epoch | 2.44191 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:57:08,999 - INFO - +๐Ÿš‚ Training Metrics (Step 650) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0173 | ++---------------+----------+ +| grad_norm | 0.013822 | ++---------------+----------+ +| learning_rate | 8.3e-05 | ++---------------+----------+ +| epoch | 2.48 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:57:28,534 - INFO - +๐Ÿš‚ Training Metrics (Step 660) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0185 | ++---------------+----------+ +| grad_norm | 0.027862 | ++---------------+----------+ +| learning_rate | 8.1e-05 | ++---------------+----------+ +| epoch | 2.5181 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:57:48,057 - INFO - +๐Ÿš‚ Training Metrics (Step 670) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.018 | ++---------------+----------+ +| grad_norm | 0.031936 | ++---------------+----------+ +| learning_rate | 7.8e-05 | ++---------------+----------+ +| epoch | 2.55619 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:58:07,596 - INFO - +๐Ÿš‚ Training Metrics (Step 680) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0176 | ++---------------+----------+ +| grad_norm | 0.017191 | ++---------------+----------+ +| learning_rate | 7.6e-05 | ++---------------+----------+ +| epoch | 2.59429 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:58:27,126 - INFO - +๐Ÿš‚ Training Metrics (Step 690) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0175 | ++---------------+----------+ +| grad_norm | 0.006769 | ++---------------+----------+ +| learning_rate | 7.3e-05 | ++---------------+----------+ +| epoch | 2.63238 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:58:46,663 - INFO - +๐Ÿš‚ Training Metrics (Step 700) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0183 | ++---------------+----------+ +| grad_norm | 0.042239 | ++---------------+----------+ +| learning_rate | 7.1e-05 | ++---------------+----------+ +| epoch | 2.67048 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:59:06,183 - INFO - +๐Ÿš‚ Training Metrics (Step 710) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0182 | ++---------------+----------+ +| grad_norm | 0.027337 | ++---------------+----------+ +| learning_rate | 6.8e-05 | ++---------------+----------+ +| epoch | 2.70857 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:59:25,691 - INFO - +๐Ÿš‚ Training Metrics (Step 720) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0178 | ++---------------+----------+ +| grad_norm | 0.009165 | ++---------------+----------+ +| learning_rate | 6.6e-05 | ++---------------+----------+ +| epoch | 2.74667 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 18:59:45,196 - INFO - +๐Ÿš‚ Training Metrics (Step 730) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0173 | ++---------------+----------+ +| grad_norm | 0.034446 | ++---------------+----------+ +| learning_rate | 6.3e-05 | ++---------------+----------+ +| epoch | 2.78476 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 19:00:04,707 - INFO - +๐Ÿš‚ Training Metrics (Step 740) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0177 | ++---------------+----------+ +| grad_norm | 0.036923 | ++---------------+----------+ +| learning_rate | 6e-05 | ++---------------+----------+ +| epoch | 2.82286 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 19:00:24,233 - INFO - +๐Ÿš‚ Training Metrics (Step 750) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0177 | ++---------------+----------+ +| grad_norm | 0.019272 | ++---------------+----------+ +| learning_rate | 5.7e-05 | ++---------------+----------+ +| epoch | 2.86095 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 19:00:43,737 - INFO - +๐Ÿš‚ Training Metrics (Step 760) ๐Ÿš‚ ++---------------+---------+ +| Metric | Value | ++===============+=========+ +| loss | 0.0172 | ++---------------+---------+ +| grad_norm | 0.00851 | ++---------------+---------+ +| learning_rate | 5.4e-05 | ++---------------+---------+ +| epoch | 2.89905 | ++---------------+---------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 19:01:03,258 - INFO - +๐Ÿš‚ Training Metrics (Step 770) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0182 | ++---------------+----------+ +| grad_norm | 0.011208 | ++---------------+----------+ +| learning_rate | 5.2e-05 | ++---------------+----------+ +| epoch | 2.93714 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 19:01:22,759 - INFO - +๐Ÿš‚ Training Metrics (Step 780) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0176 | ++---------------+----------+ +| grad_norm | 0.018971 | ++---------------+----------+ +| learning_rate | 4.9e-05 | ++---------------+----------+ +| epoch | 2.97524 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 19:01:34,955 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [multilabel_classify.py:2356:evaluate] +2025-06-16 19:15:07,900 - INFO - +๐Ÿ” Evaluation Metrics ๐Ÿ” ++-------------------------------+----------+ +| Metric | Value | ++===============================+==========+ +| eval_f1_micro | 0.00048 | ++-------------------------------+----------+ +| eval_f1_macro | 4e-06 | ++-------------------------------+----------+ +| eval_precision_at_5 | 0.284415 | ++-------------------------------+----------+ +| eval_recall_at_5 | 0.066494 | ++-------------------------------+----------+ +| eval_precision_at_8 | 0.254203 | ++-------------------------------+----------+ +| eval_recall_at_8 | 0.091028 | ++-------------------------------+----------+ +| eval_precision_at_15 | 0.190796 | ++-------------------------------+----------+ +| eval_recall_at_15 | 0.122706 | ++-------------------------------+----------+ +| eval_rare_f1_micro | 0 | ++-------------------------------+----------+ +| eval_rare_f1_macro | 0 | ++-------------------------------+----------+ +| eval_rare_precision | 0 | ++-------------------------------+----------+ +| eval_rare_recall | 0 | ++-------------------------------+----------+ +| eval_rare_precision_at_5 | 0.028244 | ++-------------------------------+----------+ +| eval_rare_recall_at_5 | 0.008353 | ++-------------------------------+----------+ +| eval_rare_precision_at_8 | 0.024624 | ++-------------------------------+----------+ +| eval_rare_recall_at_8 | 0.011806 | ++-------------------------------+----------+ +| eval_rare_precision_at_15 | 0.027321 | ++-------------------------------+----------+ +| eval_rare_recall_at_15 | 0.023346 | ++-------------------------------+----------+ +| eval_not_rare_f1_micro | 0.001304 | ++-------------------------------+----------+ +| eval_not_rare_f1_macro | 0.000269 | ++-------------------------------+----------+ +| eval_not_rare_precision | 0.283019 | ++-------------------------------+----------+ +| eval_not_rare_recall | 0.000653 | ++-------------------------------+----------+ +| eval_not_rare_precision_at_5 | 0.284415 | ++-------------------------------+----------+ +| eval_not_rare_recall_at_5 | 0.175523 | ++-------------------------------+----------+ +| eval_not_rare_precision_at_8 | 0.254203 | ++-------------------------------+----------+ +| eval_not_rare_recall_at_8 | 0.240055 | ++-------------------------------+----------+ +| eval_not_rare_precision_at_15 | 0.19077 | ++-------------------------------+----------+ +| eval_not_rare_recall_at_15 | 0.323003 | ++-------------------------------+----------+ +| eval_loss | 0.017024 | ++-------------------------------+----------+ - [multilabel_classify.py:2211:on_evaluate] +2025-06-16 19:15:09,208 - INFO - ๐Ÿ’พ Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-786 - [multilabel_classify.py:2449:_save] +2025-06-16 19:15:09,210 - INFO - โš™๏ธ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-786 - [multilabel_classify.py:2454:_save] +2025-06-16 19:15:09,211 - INFO - ๐Ÿ“‹ Saved files in ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-786: ++---------+-------------------+------------+ +| Index | Saved File | Size | ++=========+===================+============+ +| 1 | training_args.bin | 0.01 MB | ++---------+-------------------+------------+ +| 2 | model.safetensors | 4600.97 MB | ++---------+-------------------+------------+ +| 3 | config.json | 0.00 MB | ++---------+-------------------+------------+ - [multilabel_classify.py:2471:_save] +2025-06-16 19:15:20,302 - INFO - +๐Ÿš‚ Training Metrics (Step 790) ๐Ÿš‚ ++---------------+---------+ +| Metric | Value | ++===============+=========+ +| loss | 0.0179 | ++---------------+---------+ +| grad_norm | 0.02621 | ++---------------+---------+ +| learning_rate | 4.6e-05 | ++---------------+---------+ +| epoch | 3.01524 | ++---------------+---------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 19:15:39,961 - INFO - +๐Ÿš‚ Training Metrics (Step 800) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0175 | ++---------------+----------+ +| grad_norm | 0.008445 | ++---------------+----------+ +| learning_rate | 4.3e-05 | ++---------------+----------+ +| epoch | 3.05333 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 19:15:59,433 - INFO - +๐Ÿš‚ Training Metrics (Step 810) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0175 | ++---------------+----------+ +| grad_norm | 0.008988 | ++---------------+----------+ +| learning_rate | 4e-05 | ++---------------+----------+ +| epoch | 3.09143 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 19:16:18,942 - INFO - +๐Ÿš‚ Training Metrics (Step 820) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0176 | ++---------------+----------+ +| grad_norm | 0.008902 | ++---------------+----------+ +| learning_rate | 3.8e-05 | ++---------------+----------+ +| epoch | 3.12952 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 19:16:38,433 - INFO - +๐Ÿš‚ Training Metrics (Step 830) ๐Ÿš‚ ++---------------+---------+ +| Metric | Value | ++===============+=========+ +| loss | 0.0172 | ++---------------+---------+ +| grad_norm | 0.01081 | ++---------------+---------+ +| learning_rate | 3.5e-05 | ++---------------+---------+ +| epoch | 3.16762 | ++---------------+---------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 19:16:57,922 - INFO - +๐Ÿš‚ Training Metrics (Step 840) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0168 | ++---------------+----------+ +| grad_norm | 0.014023 | ++---------------+----------+ +| learning_rate | 3.2e-05 | ++---------------+----------+ +| epoch | 3.20571 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 19:17:17,420 - INFO - +๐Ÿš‚ Training Metrics (Step 850) ๐Ÿš‚ ++---------------+---------+ +| Metric | Value | ++===============+=========+ +| loss | 0.017 | ++---------------+---------+ +| grad_norm | 0.00913 | ++---------------+---------+ +| learning_rate | 3e-05 | ++---------------+---------+ +| epoch | 3.24381 | ++---------------+---------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 19:17:36,939 - INFO - +๐Ÿš‚ Training Metrics (Step 860) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0172 | ++---------------+----------+ +| grad_norm | 0.012359 | ++---------------+----------+ +| learning_rate | 2.7e-05 | ++---------------+----------+ +| epoch | 3.28191 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 19:17:56,446 - INFO - +๐Ÿš‚ Training Metrics (Step 870) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0178 | ++---------------+----------+ +| grad_norm | 0.011665 | ++---------------+----------+ +| learning_rate | 2.5e-05 | ++---------------+----------+ +| epoch | 3.32 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 19:18:15,972 - INFO - +๐Ÿš‚ Training Metrics (Step 880) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0173 | ++---------------+----------+ +| grad_norm | 0.010671 | ++---------------+----------+ +| learning_rate | 2.2e-05 | ++---------------+----------+ +| epoch | 3.3581 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 19:18:35,489 - INFO - +๐Ÿš‚ Training Metrics (Step 890) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0181 | ++---------------+----------+ +| grad_norm | 0.007859 | ++---------------+----------+ +| learning_rate | 2e-05 | ++---------------+----------+ +| epoch | 3.39619 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 19:18:55,024 - INFO - +๐Ÿš‚ Training Metrics (Step 900) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0179 | ++---------------+----------+ +| grad_norm | 0.025227 | ++---------------+----------+ +| learning_rate | 1.8e-05 | ++---------------+----------+ +| epoch | 3.43429 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 19:19:14,537 - INFO - +๐Ÿš‚ Training Metrics (Step 910) ๐Ÿš‚ ++---------------+---------+ +| Metric | Value | ++===============+=========+ +| loss | 0.0178 | ++---------------+---------+ +| grad_norm | 0.00911 | ++---------------+---------+ +| learning_rate | 1.6e-05 | ++---------------+---------+ +| epoch | 3.47238 | ++---------------+---------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 19:19:34,051 - INFO - +๐Ÿš‚ Training Metrics (Step 920) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0181 | ++---------------+----------+ +| grad_norm | 0.011931 | ++---------------+----------+ +| learning_rate | 1.4e-05 | ++---------------+----------+ +| epoch | 3.51048 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 19:19:53,570 - INFO - +๐Ÿš‚ Training Metrics (Step 930) ๐Ÿš‚ ++---------------+---------+ +| Metric | Value | ++===============+=========+ +| loss | 0.0181 | ++---------------+---------+ +| grad_norm | 0.03169 | ++---------------+---------+ +| learning_rate | 1.2e-05 | ++---------------+---------+ +| epoch | 3.54857 | ++---------------+---------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 19:20:13,096 - INFO - +๐Ÿš‚ Training Metrics (Step 940) ๐Ÿš‚ ++---------------+---------+ +| Metric | Value | ++===============+=========+ +| loss | 0.0182 | ++---------------+---------+ +| grad_norm | 0.02254 | ++---------------+---------+ +| learning_rate | 1e-05 | ++---------------+---------+ +| epoch | 3.58667 | ++---------------+---------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 19:20:32,607 - INFO - +๐Ÿš‚ Training Metrics (Step 950) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0173 | ++---------------+----------+ +| grad_norm | 0.009264 | ++---------------+----------+ +| learning_rate | 9e-06 | ++---------------+----------+ +| epoch | 3.62476 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 19:20:52,157 - INFO - +๐Ÿš‚ Training Metrics (Step 960) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0176 | ++---------------+----------+ +| grad_norm | 0.008533 | ++---------------+----------+ +| learning_rate | 7e-06 | ++---------------+----------+ +| epoch | 3.66286 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 19:21:11,673 - INFO - +๐Ÿš‚ Training Metrics (Step 970) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0182 | ++---------------+----------+ +| grad_norm | 0.008758 | ++---------------+----------+ +| learning_rate | 6e-06 | ++---------------+----------+ +| epoch | 3.70095 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 19:21:31,199 - INFO - +๐Ÿš‚ Training Metrics (Step 980) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0176 | ++---------------+----------+ +| grad_norm | 0.015255 | ++---------------+----------+ +| learning_rate | 5e-06 | ++---------------+----------+ +| epoch | 3.73905 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 19:21:50,724 - INFO - +๐Ÿš‚ Training Metrics (Step 990) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0171 | ++---------------+----------+ +| grad_norm | 0.010326 | ++---------------+----------+ +| learning_rate | 4e-06 | ++---------------+----------+ +| epoch | 3.77714 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 19:22:10,247 - INFO - +๐Ÿš‚ Training Metrics (Step 1000) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0176 | ++---------------+----------+ +| grad_norm | 0.009529 | ++---------------+----------+ +| learning_rate | 3e-06 | ++---------------+----------+ +| epoch | 3.81524 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 19:22:29,759 - INFO - +๐Ÿš‚ Training Metrics (Step 1010) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0175 | ++---------------+----------+ +| grad_norm | 0.007658 | ++---------------+----------+ +| learning_rate | 2e-06 | ++---------------+----------+ +| epoch | 3.85333 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 19:22:49,262 - INFO - +๐Ÿš‚ Training Metrics (Step 1020) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0173 | ++---------------+----------+ +| grad_norm | 0.012725 | ++---------------+----------+ +| learning_rate | 2e-06 | ++---------------+----------+ +| epoch | 3.89143 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 19:23:08,795 - INFO - +๐Ÿš‚ Training Metrics (Step 1030) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0181 | ++---------------+----------+ +| grad_norm | 0.025473 | ++---------------+----------+ +| learning_rate | 1e-06 | ++---------------+----------+ +| epoch | 3.92952 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 19:23:28,303 - INFO - +๐Ÿš‚ Training Metrics (Step 1040) ๐Ÿš‚ ++---------------+----------+ +| Metric | Value | ++===============+==========+ +| loss | 0.0167 | ++---------------+----------+ +| grad_norm | 0.008335 | ++---------------+----------+ +| learning_rate | 1e-06 | ++---------------+----------+ +| epoch | 3.96762 | ++---------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 19:23:45,277 - INFO - ๐Ÿ’พ Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-1048 - [multilabel_classify.py:2449:_save] +2025-06-16 19:23:45,279 - INFO - โš™๏ธ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-1048 - [multilabel_classify.py:2454:_save] +2025-06-16 19:23:45,280 - INFO - ๐Ÿ“‹ Saved files in ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-1048: ++---------+-------------------+------------+ +| Index | Saved File | Size | ++=========+===================+============+ +| 1 | training_args.bin | 0.01 MB | ++---------+-------------------+------------+ +| 2 | model.safetensors | 4600.97 MB | ++---------+-------------------+------------+ +| 3 | config.json | 0.00 MB | ++---------+-------------------+------------+ - [multilabel_classify.py:2471:_save] +2025-06-16 19:23:45,928 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [multilabel_classify.py:2356:evaluate] +2025-06-16 19:37:11,613 - INFO - +๐Ÿ” Evaluation Metrics ๐Ÿ” ++-------------------------------+----------+ +| Metric | Value | ++===============================+==========+ +| eval_f1_micro | 0.000544 | ++-------------------------------+----------+ +| eval_f1_macro | 5e-06 | ++-------------------------------+----------+ +| eval_precision_at_5 | 0.284652 | ++-------------------------------+----------+ +| eval_recall_at_5 | 0.066423 | ++-------------------------------+----------+ +| eval_precision_at_8 | 0.254203 | ++-------------------------------+----------+ +| eval_recall_at_8 | 0.091031 | ++-------------------------------+----------+ +| eval_precision_at_15 | 0.192563 | ++-------------------------------+----------+ +| eval_recall_at_15 | 0.125212 | ++-------------------------------+----------+ +| eval_rare_f1_micro | 0 | ++-------------------------------+----------+ +| eval_rare_f1_macro | 0 | ++-------------------------------+----------+ +| eval_rare_precision | 0 | ++-------------------------------+----------+ +| eval_rare_recall | 0 | ++-------------------------------+----------+ +| eval_rare_precision_at_5 | 0.026345 | ++-------------------------------+----------+ +| eval_rare_recall_at_5 | 0.006949 | ++-------------------------------+----------+ +| eval_rare_precision_at_8 | 0.026701 | ++-------------------------------+----------+ +| eval_rare_recall_at_8 | 0.011773 | ++-------------------------------+----------+ +| eval_rare_precision_at_15 | 0.025738 | ++-------------------------------+----------+ +| eval_rare_recall_at_15 | 0.021891 | ++-------------------------------+----------+ +| eval_not_rare_f1_micro | 0.001477 | ++-------------------------------+----------+ +| eval_not_rare_f1_macro | 0.000307 | ++-------------------------------+----------+ +| eval_not_rare_precision | 0.257576 | ++-------------------------------+----------+ +| eval_not_rare_recall | 0.000741 | ++-------------------------------+----------+ +| eval_not_rare_precision_at_5 | 0.284731 | ++-------------------------------+----------+ +| eval_not_rare_recall_at_5 | 0.175564 | ++-------------------------------+----------+ +| eval_not_rare_precision_at_8 | 0.254203 | ++-------------------------------+----------+ +| eval_not_rare_recall_at_8 | 0.240067 | ++-------------------------------+----------+ +| eval_not_rare_precision_at_15 | 0.192563 | ++-------------------------------+----------+ +| eval_not_rare_recall_at_15 | 0.33241 | ++-------------------------------+----------+ +| eval_loss | 0.017044 | ++-------------------------------+----------+ - [multilabel_classify.py:2211:on_evaluate] +2025-06-16 19:37:15,436 - INFO - ๐Ÿ’พ Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-1048 - [multilabel_classify.py:2449:_save] +2025-06-16 19:37:15,438 - INFO - โš™๏ธ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-1048 - [multilabel_classify.py:2454:_save] +2025-06-16 19:37:15,439 - INFO - ๐Ÿ“‹ Saved files in ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-1048: ++---------+--------------------+------------+ +| Index | Saved File | Size | ++=========+====================+============+ +| 1 | training_args.bin | 0.01 MB | ++---------+--------------------+------------+ +| 2 | optimizer.pt | 1308.77 MB | ++---------+--------------------+------------+ +| 3 | model.safetensors | 4600.97 MB | ++---------+--------------------+------------+ +| 4 | scaler.pt | 0.00 MB | ++---------+--------------------+------------+ +| 5 | config.json | 0.00 MB | ++---------+--------------------+------------+ +| 6 | scheduler.pt | 0.00 MB | ++---------+--------------------+------------+ +| 7 | trainer_state.json | 0.02 MB | ++---------+--------------------+------------+ +| 8 | rng_state.pth | 0.01 MB | ++---------+--------------------+------------+ - [multilabel_classify.py:2471:_save] +2025-06-16 19:37:16,939 - INFO - ๐Ÿ“‚ Loading best model from ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-524 - [multilabel_classify.py:2523:_load_best_model] +2025-06-16 19:37:16,939 - INFO - ๐Ÿ–ฅ๏ธ Model is on device: cuda:0 - [multilabel_classify.py:2533:_load_best_model] +2025-06-16 19:37:17,000 - 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:2557:_load_best_model] +2025-06-16 19:37:18,002 - INFO - โœ… Loaded best model weights from ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-524/model.safetensors - [multilabel_classify.py:2574:_load_best_model] +2025-06-16 19:37:18,041 - INFO - โœ”๏ธ Weight for boost_mul matches between saved and loaded state_dict - [multilabel_classify.py:2586:_load_best_model] +2025-06-16 19:37:18,075 - INFO - โœ”๏ธ Weight for boost_add matches between saved and loaded state_dict - [multilabel_classify.py:2586:_load_best_model] +2025-06-16 19:37:18,090 - INFO - +๐Ÿš‚ Training Metrics (Step 1048) ๐Ÿš‚ ++--------------------------+----------+ +| Metric | Value | ++==========================+==========+ +| train_runtime | 5311.2 | ++--------------------------+----------+ +| train_samples_per_second | 6.321 | ++--------------------------+----------+ +| train_steps_per_second | 0.197 | ++--------------------------+----------+ +| total_flos | 0 | ++--------------------------+----------+ +| train_loss | 0.028082 | ++--------------------------+----------+ +| epoch | 3.9981 | ++--------------------------+----------+ - [multilabel_classify.py:2192:on_log] +2025-06-16 19:37:18,091 - INFO - โœจ Training Completed! โœจ - [multilabel_classify.py:2065:on_train_end] +2025-06-16 19:37:18,162 - INFO - ๐Ÿ“Š Training loss plot saved as '../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/train_loss_plot.png' - [multilabel_classify.py:2261:on_train_end] +2025-06-16 19:37:18,229 - INFO - ๐Ÿ“Š Evaluation loss plot saved as '../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/eval_loss_plot.png' - [multilabel_classify.py:2275:on_train_end] +2025-06-16 19:37:18,291 - INFO - ๐Ÿ“Š Evaluation metric plot saved as '../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/eval_precision_at_15_plot.png' - [multilabel_classify.py:2296:on_train_end] +2025-06-16 19:37:18,291 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:101:log_section] +2025-06-16 19:37:18,291 - INFO - + โœจ MODEL SAVING + - [multilabel_classify.py:102:log_section] +2025-06-16 19:37:18,291 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:105:log_section] +2025-06-16 19:37:18,291 - INFO - ๐Ÿ’พ Saving trained model and pushing to Hugging Face Hub... - [multilabel_classify.py:4073:main] +2025-06-16 19:37:18,292 - INFO - ๐Ÿ“ Creating/using output directory: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:3049:save_and_push] +2025-06-16 19:37:19,588 - INFO - ๐Ÿ’พ Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2449:_save] +2025-06-16 19:37:19,590 - INFO - โš™๏ธ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2454:_save] +2025-06-16 19:37:19,591 - 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 | model.safetensors | 4600.97 MB | ++---------+-------------------------------+------------+ +| 4 | config.json | 0.00 MB | ++---------+-------------------------------+------------+ +| 5 | train_loss_plot.png | 0.02 MB | ++---------+-------------------------------+------------+ +| 6 | eval_precision_at_15_plot.png | 0.04 MB | ++---------+-------------------------------+------------+ - [multilabel_classify.py:2471:_save] +2025-06-16 19:37:23,306 - INFO - ๐Ÿ’พ Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2449:_save] +2025-06-16 19:37:23,308 - INFO - โš™๏ธ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2454:_save] +2025-06-16 19:37:23,309 - 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 | model.safetensors | 4600.97 MB | ++---------+-------------------------------+------------+ +| 4 | config.json | 0.00 MB | ++---------+-------------------------------+------------+ +| 5 | train_loss_plot.png | 0.02 MB | ++---------+-------------------------------+------------+ +| 6 | eval_precision_at_15_plot.png | 0.04 MB | ++---------+-------------------------------+------------+ - [multilabel_classify.py:2471:_save] +2025-06-16 19:38:59,928 - INFO - ๐Ÿ’พ Model saved to: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:3053:save_and_push] +2025-06-16 19:38:59,958 - INFO - ๐Ÿ–Œ๏ธ Tokenizer saved to: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:3057:save_and_push]