Trained L2R token ranking model on MIMIC-IV
Browse files
training_l2r_log_2025-05-29_19-25-52.log
ADDED
|
@@ -0,0 +1,599 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
2025-05-29 19:25:52,028 - INFO - 📝 Logging initialized. Log file created at: ../tmp/logs/training_l2r_log_2025-05-29_19-25-52.log - [learning2rank.py:264:setup_logging]
|
| 2 |
+
2025-05-29 19:25:52,028 - INFO - ================================================================================ - [learning2rank.py:108:log_section]
|
| 3 |
+
2025-05-29 19:25:52,028 - INFO - = 📌 INITIALIZING TRAINING ENVIRONMENT = - [learning2rank.py:109:log_section]
|
| 4 |
+
2025-05-29 19:25:52,028 - INFO - ================================================================================ - [learning2rank.py:112:log_section]
|
| 5 |
+
2025-05-29 19:25:52,028 - INFO - 🚀 Setting up data paths and environment variables... - [learning2rank.py:3841:main]
|
| 6 |
+
2025-05-29 19:25:52,028 - INFO - 🛠️ Command-line Arguments: - [learning2rank.py:280:print_args]
|
| 7 |
+
2025-05-29 19:25:52,029 - INFO -
|
| 8 |
+
🔹 output_dir: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r
|
| 9 |
+
🔹 source_url: XURLs.MIMIC4_DEMO
|
| 10 |
+
🔹 data: mimic4_icd10_full
|
| 11 |
+
🔹 data_l2r_fname_prefix: mimic4_icd10
|
| 12 |
+
🔹 logfile: training_l2r_log
|
| 13 |
+
🔹 base_dir: ../tmp/MIMIC4_DEMO
|
| 14 |
+
🔹 l2r_boot_dir: ../tmp/MIMIC4_DEMO/mimic4_l2rboot_mistral7b
|
| 15 |
+
🔹 hub_model_id: deb101/mistral-7b-instruct-v0.3-mimic4-adapt
|
| 16 |
+
🔹 model_name: mistralai/Mistral-7B-Instruct-v0.3
|
| 17 |
+
🔹 max_length: 512
|
| 18 |
+
🔹 do_fresh_training: True
|
| 19 |
+
🔹 load_from_checkpoint: False
|
| 20 |
+
🔹 task: l2r
|
| 21 |
+
🔹 num_train_epochs: 4
|
| 22 |
+
🔹 metric_for_best_model: ndcg@25
|
| 23 |
+
🔹 learning_rate: 0.0001
|
| 24 |
+
🔹 warmup_steps: 0
|
| 25 |
+
🔹 generate_report: False
|
| 26 |
+
🔹 logfile_path: ../tmp/logs/training_l2r_log_2025-05-29_19-25-52.log
|
| 27 |
+
🔹 source: /home/ubuntu/.xcube/data/mimic4_demo - [learning2rank.py:281:print_args]
|
| 28 |
+
2025-05-29 19:25:52,029 - INFO - ➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖ - [learning2rank.py:282:print_args]
|
| 29 |
+
2025-05-29 19:25:52,029 - INFO - 📁 Using L2R boot directory: ../tmp/MIMIC4_DEMO/mimic4_l2rboot_mistral7b - [learning2rank.py:3855:main]
|
| 30 |
+
2025-05-29 19:25:52,029 - INFO - 📂 Using output directory: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r - [learning2rank.py:3857:main]
|
| 31 |
+
2025-05-29 19:25:52,029 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:108:log_section]
|
| 32 |
+
2025-05-29 19:25:52,029 - INFO - + ✨ LOADING DATASETS + - [learning2rank.py:109:log_section]
|
| 33 |
+
2025-05-29 19:25:52,029 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:112:log_section]
|
| 34 |
+
2025-05-29 19:25:52,029 - INFO - 📊 Loading main dataset and L2R dataset... - [learning2rank.py:3860:main]
|
| 35 |
+
2025-05-29 19:25:52,029 - INFO - 📂 Loading main data from: /home/ubuntu/.xcube/data/mimic4_demo/mimic4_icd10_full.csv - [learning2rank.py:310:get_data]
|
| 36 |
+
2025-05-29 19:26:00,147 - INFO - ✅ Successfully loaded main data: 122279 rows - [learning2rank.py:323:get_data]
|
| 37 |
+
2025-05-29 19:26:00,147 - INFO - 📂 Loading L2R data from: ../tmp/MIMIC4_DEMO/mimic4_l2rboot_mistral7b/mimic4_icd10_tok_rank_per_lbl.ft - [learning2rank.py:329:get_data]
|
| 38 |
+
2025-05-29 19:26:00,147 - INFO - 📂 Loading L2R tokens from: ../tmp/MIMIC4_DEMO/mimic4_l2rboot_mistral7b/mimic4_icd10_tok.ft - [learning2rank.py:332:get_data]
|
| 39 |
+
2025-05-29 19:26:00,147 - INFO - 📂 Loading L2R labels from: ../tmp/MIMIC4_DEMO/mimic4_l2rboot_mistral7b/mimic4_icd10_lbl.ft - [learning2rank.py:335:get_data]
|
| 40 |
+
2025-05-29 19:26:01,853 - INFO - ✅ Successfully loaded L2R data: 260243456 rows - [learning2rank.py:342:get_data]
|
| 41 |
+
2025-05-29 19:26:01,853 - INFO - ✅ Successfully loaded L2R tokens: 32768 tokens - [learning2rank.py:343:get_data]
|
| 42 |
+
2025-05-29 19:26:01,853 - INFO - ✅ Successfully loaded L2R labels: 7942 rows - [learning2rank.py:344:get_data]
|
| 43 |
+
2025-05-29 19:26:01,853 - INFO - 🔄 Total data loaded: 122279 main rows, 260243456 L2R rows - [learning2rank.py:351:get_data]
|
| 44 |
+
2025-05-29 19:26:01,853 - INFO - ✨ Successfully loaded both datasets: - [learning2rank.py:375:load_datasets]
|
| 45 |
+
2025-05-29 19:26:01,853 - INFO - - 📄 Main dataset: 122279 records - [learning2rank.py:376:load_datasets]
|
| 46 |
+
2025-05-29 19:26:01,853 - INFO - - 📄 L2R dataset: 260243456 records - [learning2rank.py:377:load_datasets]
|
| 47 |
+
2025-05-29 19:26:01,853 - INFO - - 🔤 Tokens: 32768 items - [learning2rank.py:378:load_datasets]
|
| 48 |
+
2025-05-29 19:26:01,853 - INFO - - 🏷️ Labels: 7942 items - [learning2rank.py:379:load_datasets]
|
| 49 |
+
2025-05-29 19:26:01,860 - INFO - ✅ Data loading completed successfully - [learning2rank.py:387:load_datasets]
|
| 50 |
+
2025-05-29 19:26:03,128 - INFO - ⏳ Starting quantization of ranks for DataFrame with 260243456 rows. Containing 32768 unique tokens & 7942 unique labels - [learning2rank.py:506:quantize_l2r_data]
|
| 51 |
+
2025-05-29 19:26:03,129 - INFO - 🔄 Quantizing those 32768 unique token ranks into 101 quantization levels for each label - [learning2rank.py:531:quantize_l2r_data]
|
| 52 |
+
2025-05-29 19:26:49,291 - INFO - ✅ Completed quantization: Produced tensor of shape torch.Size([7942, 32768, 4]) with 101 quantization levels per label - [learning2rank.py:585:quantize_l2r_data]
|
| 53 |
+
2025-05-29 19:26:49,320 - WARNING - Label 1295: Only 1 tokens with top relevance score (need 50) - [learning2rank.py:701:test_scored_tokens]
|
| 54 |
+
2025-05-29 19:26:49,326 - WARNING - Label 4049: Only 1 tokens with top relevance score (need 50) - [learning2rank.py:701:test_scored_tokens]
|
| 55 |
+
2025-05-29 19:26:49,330 - WARNING - Label 3517: Only 1 tokens with top relevance score (need 50) - [learning2rank.py:701:test_scored_tokens]
|
| 56 |
+
2025-05-29 19:26:49,334 - WARNING - Label 4308: Only 1 tokens with top relevance score (need 50) - [learning2rank.py:701:test_scored_tokens]
|
| 57 |
+
2025-05-29 19:26:49,337 - WARNING - Label 519: Only 1 tokens with top relevance score (need 50) - [learning2rank.py:701:test_scored_tokens]
|
| 58 |
+
2025-05-29 19:26:49,365 - INFO - ******************************************************************************** - [learning2rank.py:108:log_section]
|
| 59 |
+
2025-05-29 19:26:49,365 - INFO - * 🌟 STARTING LEARNING TO RANK MODEL TRAINING * - [learning2rank.py:109:log_section]
|
| 60 |
+
2025-05-29 19:26:49,365 - INFO - ******************************************************************************** - [learning2rank.py:112:log_section]
|
| 61 |
+
2025-05-29 19:26:49,366 - INFO - 🔐 Loaded authentication token from environment - [learning2rank.py:3889:main]
|
| 62 |
+
2025-05-29 19:26:49,366 - INFO - 🏷️ Hub Model ID for this Learning to Rank task: deb101/mistral-7b-instruct-v0.3-mimic4-adapt-l2r - [learning2rank.py:3893:main]
|
| 63 |
+
2025-05-29 19:26:49,366 - INFO - -------------------------------------------------------------------------------- - [learning2rank.py:108:log_section]
|
| 64 |
+
2025-05-29 19:26:49,366 - INFO - - 📋 MODEL EXISTENCE CHECK - - [learning2rank.py:109:log_section]
|
| 65 |
+
2025-05-29 19:26:49,366 - INFO - -------------------------------------------------------------------------------- - [learning2rank.py:112:log_section]
|
| 66 |
+
2025-05-29 19:26:49,366 - INFO - 🔍 Checking model existence locally and on Hugging Face Hub... - [learning2rank.py:407:check_model_existence]
|
| 67 |
+
2025-05-29 19:26:49,366 - INFO - ❌ Model not found locally at: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r - [learning2rank.py:414:check_model_existence]
|
| 68 |
+
2025-05-29 19:26:49,481 - INFO - ✅ Model exists on Hugging Face Hub with ID: deb101/mistral-7b-instruct-v0.3-mimic4-adapt-l2r - [learning2rank.py:426:check_model_existence]
|
| 69 |
+
2025-05-29 19:26:49,481 - INFO - 📁 Model exists either locally or on Hub - [learning2rank.py:452:check_model_existence]
|
| 70 |
+
2025-05-29 19:26:49,481 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:108:log_section]
|
| 71 |
+
2025-05-29 19:26:49,481 - INFO - + ✨ STARTING FRESH TRAINING + - [learning2rank.py:109:log_section]
|
| 72 |
+
2025-05-29 19:26:49,481 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:112:log_section]
|
| 73 |
+
2025-05-29 19:26:49,481 - INFO - 🔄 Starting fresh training (either forced or model not found)... - [learning2rank.py:3906:main]
|
| 74 |
+
2025-05-29 19:26:49,496 - 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]
|
| 75 |
+
2025-05-29 19:26:49,496 - INFO - 🔑 Successfully authenticated with Hugging Face Hub - [learning2rank.py:288:authenticate_hf]
|
| 76 |
+
2025-05-29 19:26:49,496 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:108:log_section]
|
| 77 |
+
2025-05-29 19:26:49,496 - INFO - + ✨ LOADING BASE MODEL + - [learning2rank.py:109:log_section]
|
| 78 |
+
2025-05-29 19:26:49,496 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:112:log_section]
|
| 79 |
+
2025-05-29 19:26:49,496 - INFO - 📥 Loading pretrained model and tokenizer... - [learning2rank.py:3948:main]
|
| 80 |
+
2025-05-29 19:26:49,496 - INFO - 🚀 Starting model and tokenizer loading process... - [learning2rank.py:916:load_base_model_and_tokenizer]
|
| 81 |
+
2025-05-29 19:26:49,497 - INFO - 📊 Quantization config: BitsAndBytesConfig {
|
| 82 |
+
"_load_in_4bit": true,
|
| 83 |
+
"_load_in_8bit": false,
|
| 84 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 85 |
+
"bnb_4bit_quant_storage": "uint8",
|
| 86 |
+
"bnb_4bit_quant_type": "nf4",
|
| 87 |
+
"bnb_4bit_use_double_quant": true,
|
| 88 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
| 89 |
+
"llm_int8_has_fp16_weight": false,
|
| 90 |
+
"llm_int8_skip_modules": null,
|
| 91 |
+
"llm_int8_threshold": 6.0,
|
| 92 |
+
"load_in_4bit": true,
|
| 93 |
+
"load_in_8bit": false,
|
| 94 |
+
"quant_method": "bitsandbytes"
|
| 95 |
+
}
|
| 96 |
+
- [learning2rank.py:925:load_base_model_and_tokenizer]
|
| 97 |
+
2025-05-29 19:26:49,497 - INFO - 🔤 Loading tokenizer for model: mistralai/Mistral-7B-Instruct-v0.3... - [learning2rank.py:929:load_base_model_and_tokenizer]
|
| 98 |
+
2025-05-29 19:26:50,177 - INFO - 📝 Setting pad token to eos token... - [learning2rank.py:933:load_base_model_and_tokenizer]
|
| 99 |
+
2025-05-29 19:26:50,177 - INFO - 🧠 Loading base model with quantization... - [learning2rank.py:941:load_base_model_and_tokenizer]
|
| 100 |
+
2025-05-29 19:26:50,740 - 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]
|
| 101 |
+
2025-05-29 19:26:56,190 - INFO - 🔧 Setting up default LoRA configuration... - [learning2rank.py:964:load_base_model_and_tokenizer]
|
| 102 |
+
2025-05-29 19:26:56,190 - INFO - 🔍 LoRA config: r=16, alpha=32, targets={'o_proj', 'q_proj', 'k_proj', 'v_proj'}, dropout=0.05 - [learning2rank.py:987:load_base_model_and_tokenizer]
|
| 103 |
+
2025-05-29 19:26:56,190 - INFO - 🧩 Applying LoRA adapters to model... - [learning2rank.py:994:load_base_model_and_tokenizer]
|
| 104 |
+
2025-05-29 19:26:56,374 - INFO - ✅ Model and tokenizer successfully loaded! - [learning2rank.py:1001:load_base_model_and_tokenizer]
|
| 105 |
+
2025-05-29 19:26:56,374 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:108:log_section]
|
| 106 |
+
2025-05-29 19:26:56,374 - INFO - + ✨ DATA PREPROCESSING + - [learning2rank.py:109:log_section]
|
| 107 |
+
2025-05-29 19:26:56,374 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:112:log_section]
|
| 108 |
+
2025-05-29 19:26:56,374 - INFO - 🔄 Loading and preprocessing training data... - [learning2rank.py:3956:main]
|
| 109 |
+
2025-05-29 19:26:57,442 - INFO - 🔍 Verifying uniqueness of token IDs per label in scored_tokens... - [learning2rank.py:1279:preprocess_data]
|
| 110 |
+
2025-05-29 19:26:58,264 - INFO - ✅ All labels have unique token IDs in scored_tokens. - [learning2rank.py:1291:preprocess_data]
|
| 111 |
+
2025-05-29 19:26:58,264 - INFO - 🚀 Building a 2D lookup table for efficient token-to-relevance mapping across all labels! 🚀 - [learning2rank.py:1294:preprocess_data]
|
| 112 |
+
2025-05-29 19:26:58,264 - INFO - 🔢 Total labels = 7942 - [learning2rank.py:1297:preprocess_data]
|
| 113 |
+
2025-05-29 19:26:58,264 - INFO - 🔍 Precomputing token indices and corresponding relevance_values for each label... - [learning2rank.py:1298:preprocess_data]
|
| 114 |
+
2025-05-29 19:26:58,492 - INFO - 📊 Lookup table dimensions: 32768 vocabulary size × 7942 labels - [learning2rank.py:1305:preprocess_data]
|
| 115 |
+
2025-05-29 19:26:58,492 - INFO - ⚡ This approach eliminates token comparison broadcasting and provides O(1) lookup time for relevance scores! - [learning2rank.py:1308:preprocess_data]
|
| 116 |
+
2025-05-29 19:26:58,492 - INFO - 🧮 Processing relevance calculations vectorized for maximum speed 🔥 - [learning2rank.py:1311:preprocess_data]
|
| 117 |
+
2025-05-29 19:26:58,657 - INFO - 🔍 Verifying token mappings with 10 samples... - [learning2rank.py:1344:verify_token_mappings]
|
| 118 |
+
2025-05-29 19:26:58,838 - INFO - ✅ Token mappings verification completed successfully! 🎉 - [learning2rank.py:1435:verify_token_mappings]
|
| 119 |
+
2025-05-29 19:26:58,842 - INFO - 🔄 Processing dataset with map... - [learning2rank.py:1499:preprocess_data]
|
| 120 |
+
2025-05-29 19:26:59,159 - INFO - ✅ Dataset built in 0h 0m 0.32s - [learning2rank.py:1522:preprocess_data]
|
| 121 |
+
2025-05-29 19:26:59,171 - INFO - The size of Training set: 173 🏋️ (Training Data) - [learning2rank.py:1553:preprocess_data]
|
| 122 |
+
2025-05-29 19:26:59,172 - INFO - The size of Evaluation set: 35 🔍 (Test Data) - [learning2rank.py:1554:preprocess_data]
|
| 123 |
+
2025-05-29 19:26:59,172 - INFO - 🚀 Created HuggingFace Dataset with 208 samples, 7942 labels - [learning2rank.py:1562:preprocess_data]
|
| 124 |
+
2025-05-29 19:26:59,172 - INFO - 🏷️ Number of unique ICD-10 codes: 7942 - [learning2rank.py:3969:main]
|
| 125 |
+
2025-05-29 19:26:59,173 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:108:log_section]
|
| 126 |
+
2025-05-29 19:26:59,173 - INFO - + ✨ MODEL INITIALIZATION + - [learning2rank.py:109:log_section]
|
| 127 |
+
2025-05-29 19:26:59,173 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:112:log_section]
|
| 128 |
+
2025-05-29 19:26:59,173 - INFO - 🧠 Initializing custom L2R model for outputting per-token relevance scores per ICD-10 codes. - [learning2rank.py:3972:main]
|
| 129 |
+
2025-05-29 19:27:00,707 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:108:log_section]
|
| 130 |
+
2025-05-29 19:27:00,707 - INFO - + ✨ TRAINING PREPARATION + - [learning2rank.py:109:log_section]
|
| 131 |
+
2025-05-29 19:27:00,707 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:112:log_section]
|
| 132 |
+
2025-05-29 19:27:00,707 - INFO - ⚙️ Preparing training components and optimizers... - [learning2rank.py:3979:main]
|
| 133 |
+
2025-05-29 19:27:00,739 - INFO - 🖥️ Device: NVIDIA GH200 480GB - [learning2rank.py:2007:log_training_configuration]
|
| 134 |
+
2025-05-29 19:27:00,739 - INFO - 🔋 CUDA Available: True - [learning2rank.py:2010:log_training_configuration]
|
| 135 |
+
2025-05-29 19:27:00,739 - INFO - 💾 CUDA Device Count: 1 - [learning2rank.py:2011:log_training_configuration]
|
| 136 |
+
2025-05-29 19:27:00,740 - INFO -
|
| 137 |
+
📋 Training Configuration 📋
|
| 138 |
+
+----------+-----------------------------+--------------------------------------------------+
|
| 139 |
+
| 🌟 Emoji | 🏷️ Parameter | 📊 Value |
|
| 140 |
+
+----------+-----------------------------+--------------------------------------------------+
|
| 141 |
+
| 📁 | Output Directory | ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r |
|
| 142 |
+
| 🔁 | Training Epochs | 4 |
|
| 143 |
+
| 🏋️ | Train Batch Size | 1 |
|
| 144 |
+
| 🔍 | Eval Batch Size | 1 |
|
| 145 |
+
| 📊 | Gradient Accumulation Steps | 4 |
|
| 146 |
+
| 🚀 | Learning Rate | 0.0001 |
|
| 147 |
+
| 🌅 | Warmup Steps | 0 |
|
| 148 |
+
| 💾 | Save Strategy | epoch |
|
| 149 |
+
| 💾 | Save Total Limit | 10 |
|
| 150 |
+
| 📊 | Evaluation Strategy | epoch |
|
| 151 |
+
| 🎯 | Best Model Metric | ndcg@25 |
|
| 152 |
+
| 📝 | Logging Strategy | steps (every 10 steps) |
|
| 153 |
+
| 🌐 | Push to Hub | True |
|
| 154 |
+
| 🌐 | Hub Model ID | deb101/mistral-7b-instruct-v0.3-mimic4-adapt-l2r |
|
| 155 |
+
| 🔢 | Steps per Epoch | 43 |
|
| 156 |
+
| 🔢 | Total Training Steps | 172 |
|
| 157 |
+
| 🔢 | Evaluation Steps | 35 |
|
| 158 |
+
| 📊 | Training Dataset Size | 173 samples 🏋️ |
|
| 159 |
+
| 📊 | Evaluation Dataset Size | 35 samples 🔍 |
|
| 160 |
+
+----------+-----------------------------+--------------------------------------------------+ - [learning2rank.py:1999:log_training_args]
|
| 161 |
+
2025-05-29 19:27:00,740 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:108:log_section]
|
| 162 |
+
2025-05-29 19:27:00,740 - INFO - + ✨ MODEL TRAINING + - [learning2rank.py:109:log_section]
|
| 163 |
+
2025-05-29 19:27:00,740 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:112:log_section]
|
| 164 |
+
2025-05-29 19:27:00,740 - INFO - 🏋️ Starting model training process... - [learning2rank.py:3999:main]
|
| 165 |
+
2025-05-29 19:27:00,740 - INFO - 🏁 Preparing Custom Trainer 🛠️ - [learning2rank.py:3200:train_model]
|
| 166 |
+
2025-05-29 19:27:00,784 - INFO - We are registering the tokenizer mistralai/Mistral-7B-Instruct-v0.3 in Custom Trainer - [learning2rank.py:2639:__init__]
|
| 167 |
+
2025-05-29 19:27:00,784 - INFO - 🏋️ Commencing Model Training 💪 - [learning2rank.py:3241:train_model]
|
| 168 |
+
2025-05-29 19:27:01,050 - INFO - 🚀 Starting Training... - [learning2rank.py:2389:on_train_begin]
|
| 169 |
+
2025-05-29 19:27:20,294 - INFO -
|
| 170 |
+
[36m🚂 Training Metrics (Step 10) 🚂
|
| 171 |
+
+---------------+--------------+
|
| 172 |
+
| Metric | Value |
|
| 173 |
+
+===============+==============+
|
| 174 |
+
| loss | -4.58268e+16 |
|
| 175 |
+
+---------------+--------------+
|
| 176 |
+
| grad_norm | nan |
|
| 177 |
+
+---------------+--------------+
|
| 178 |
+
| learning_rate | 0.0001 |
|
| 179 |
+
+---------------+--------------+
|
| 180 |
+
| epoch | 0.231214 |
|
| 181 |
+
+---------------+--------------+[0m - [learning2rank.py:2307:on_log]
|
| 182 |
+
2025-05-29 19:27:34,347 - INFO -
|
| 183 |
+
[36m🚂 Training Metrics (Step 20) 🚂
|
| 184 |
+
+---------------+--------------+
|
| 185 |
+
| Metric | Value |
|
| 186 |
+
+===============+==============+
|
| 187 |
+
| loss | -4.34403e+17 |
|
| 188 |
+
+---------------+--------------+
|
| 189 |
+
| grad_norm | nan |
|
| 190 |
+
+---------------+--------------+
|
| 191 |
+
| learning_rate | 0.0001 |
|
| 192 |
+
+---------------+--------------+
|
| 193 |
+
| epoch | 0.462428 |
|
| 194 |
+
+---------------+--------------+[0m - [learning2rank.py:2307:on_log]
|
| 195 |
+
2025-05-29 19:27:48,535 - INFO -
|
| 196 |
+
[36m🚂 Training Metrics (Step 30) 🚂
|
| 197 |
+
+---------------+--------------+
|
| 198 |
+
| Metric | Value |
|
| 199 |
+
+===============+==============+
|
| 200 |
+
| loss | -6.33341e+16 |
|
| 201 |
+
+---------------+--------------+
|
| 202 |
+
| grad_norm | nan |
|
| 203 |
+
+---------------+--------------+
|
| 204 |
+
| learning_rate | 0.0001 |
|
| 205 |
+
+---------------+--------------+
|
| 206 |
+
| epoch | 0.693642 |
|
| 207 |
+
+---------------+--------------+[0m - [learning2rank.py:2307:on_log]
|
| 208 |
+
2025-05-29 19:28:02,663 - INFO -
|
| 209 |
+
[36m🚂 Training Metrics (Step 40) ���
|
| 210 |
+
+---------------+--------------+
|
| 211 |
+
| Metric | Value |
|
| 212 |
+
+===============+==============+
|
| 213 |
+
| loss | -6.34723e+18 |
|
| 214 |
+
+---------------+--------------+
|
| 215 |
+
| grad_norm | nan |
|
| 216 |
+
+---------------+--------------+
|
| 217 |
+
| learning_rate | 0.0001 |
|
| 218 |
+
+---------------+--------------+
|
| 219 |
+
| epoch | 0.924855 |
|
| 220 |
+
+---------------+--------------+[0m - [learning2rank.py:2307:on_log]
|
| 221 |
+
2025-05-29 19:28:07,197 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [learning2rank.py:2755:evaluate]
|
| 222 |
+
2025-05-29 19:31:21,756 - WARNING - No valid samples found for metric 'precision@25'. - [learning2rank.py:2859:evaluate]
|
| 223 |
+
2025-05-29 19:31:21,757 - INFO -
|
| 224 |
+
[33m🔍 Evaluation Metrics 🔍
|
| 225 |
+
+-------------------+--------------+
|
| 226 |
+
| Metric | Value |
|
| 227 |
+
+===================+==============+
|
| 228 |
+
| eval_loss | -1.17021e+17 |
|
| 229 |
+
+-------------------+--------------+
|
| 230 |
+
| eval_ndcg | 0.955488 |
|
| 231 |
+
+-------------------+--------------+
|
| 232 |
+
| eval_ndcg@25 | 0.18984 |
|
| 233 |
+
+-------------------+--------------+
|
| 234 |
+
| eval_precision@25 | 0 |
|
| 235 |
+
+-------------------+--------------+[0m - [learning2rank.py:2326:on_evaluate]
|
| 236 |
+
2025-05-29 19:31:23,021 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/checkpoint-44 - [learning2rank.py:2879:_save]
|
| 237 |
+
2025-05-29 19:31:23,022 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/checkpoint-44 - [learning2rank.py:2884:_save]
|
| 238 |
+
2025-05-29 19:31:23,023 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/checkpoint-44:
|
| 239 |
+
+---------+-------------------+------------+
|
| 240 |
+
| Index | Saved File | Size |
|
| 241 |
+
+=========+===================+============+
|
| 242 |
+
| 1 | training_args.bin | 0.01 MB |
|
| 243 |
+
+---------+-------------------+------------+
|
| 244 |
+
| 2 | model.safetensors | 4122.74 MB |
|
| 245 |
+
+---------+-------------------+------------+
|
| 246 |
+
| 3 | config.json | 0.00 MB |
|
| 247 |
+
+---------+-------------------+------------+ - [learning2rank.py:2901:_save]
|
| 248 |
+
2025-05-29 19:31:36,370 - INFO -
|
| 249 |
+
[36m🚂 Training Metrics (Step 50) 🚂
|
| 250 |
+
+---------------+--------------+
|
| 251 |
+
| Metric | Value |
|
| 252 |
+
+===============+==============+
|
| 253 |
+
| loss | -4.29741e+18 |
|
| 254 |
+
+---------------+--------------+
|
| 255 |
+
| grad_norm | nan |
|
| 256 |
+
+---------------+--------------+
|
| 257 |
+
| learning_rate | 0.0001 |
|
| 258 |
+
+---------------+--------------+
|
| 259 |
+
| epoch | 1.13873 |
|
| 260 |
+
+---------------+--------------+[0m - [learning2rank.py:2307:on_log]
|
| 261 |
+
2025-05-29 19:31:50,557 - INFO -
|
| 262 |
+
[36m🚂 Training Metrics (Step 60) 🚂
|
| 263 |
+
+---------------+--------------+
|
| 264 |
+
| Metric | Value |
|
| 265 |
+
+===============+==============+
|
| 266 |
+
| loss | -1.10586e+17 |
|
| 267 |
+
+---------------+--------------+
|
| 268 |
+
| grad_norm | nan |
|
| 269 |
+
+---------------+--------------+
|
| 270 |
+
| learning_rate | 9.9e-05 |
|
| 271 |
+
+---------------+--------------+
|
| 272 |
+
| epoch | 1.36994 |
|
| 273 |
+
+---------------+--------------+[0m - [learning2rank.py:2307:on_log]
|
| 274 |
+
2025-05-29 19:32:04,594 - INFO -
|
| 275 |
+
[36m🚂 Training Metrics (Step 70) 🚂
|
| 276 |
+
+---------------+--------------+
|
| 277 |
+
| Metric | Value |
|
| 278 |
+
+===============+==============+
|
| 279 |
+
| loss | -6.65756e+18 |
|
| 280 |
+
+---------------+--------------+
|
| 281 |
+
| grad_norm | 2.41222e+18 |
|
| 282 |
+
+---------------+--------------+
|
| 283 |
+
| learning_rate | 9.4e-05 |
|
| 284 |
+
+---------------+--------------+
|
| 285 |
+
| epoch | 1.60116 |
|
| 286 |
+
+---------------+--------------+[0m - [learning2rank.py:2307:on_log]
|
| 287 |
+
2025-05-29 19:32:18,534 - INFO -
|
| 288 |
+
[36m🚂 Training Metrics (Step 80) 🚂
|
| 289 |
+
+---------------+--------------+
|
| 290 |
+
| Metric | Value |
|
| 291 |
+
+===============+==============+
|
| 292 |
+
| loss | -9.52556e+16 |
|
| 293 |
+
+---------------+--------------+
|
| 294 |
+
| grad_norm | 1.31876e+18 |
|
| 295 |
+
+---------------+--------------+
|
| 296 |
+
| learning_rate | 8.8e-05 |
|
| 297 |
+
+---------------+--------------+
|
| 298 |
+
| epoch | 1.83237 |
|
| 299 |
+
+---------------+--------------+[0m - [learning2rank.py:2307:on_log]
|
| 300 |
+
2025-05-29 19:32:28,622 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [learning2rank.py:2755:evaluate]
|
| 301 |
+
2025-05-29 19:35:41,610 - INFO -
|
| 302 |
+
[33m🔍 Evaluation Metrics 🔍
|
| 303 |
+
+-------------------+--------------+
|
| 304 |
+
| Metric | Value |
|
| 305 |
+
+===================+==============+
|
| 306 |
+
| eval_loss | -3.19605e+17 |
|
| 307 |
+
+-------------------+--------------+
|
| 308 |
+
| eval_ndcg | 0.956218 |
|
| 309 |
+
+-------------------+--------------+
|
| 310 |
+
| eval_ndcg@25 | 0.644859 |
|
| 311 |
+
+-------------------+--------------+
|
| 312 |
+
| eval_precision@25 | 0.524571 |
|
| 313 |
+
+-------------------+--------------+[0m - [learning2rank.py:2326:on_evaluate]
|
| 314 |
+
2025-05-29 19:35:42,773 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/checkpoint-88 - [learning2rank.py:2879:_save]
|
| 315 |
+
2025-05-29 19:35:42,774 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/checkpoint-88 - [learning2rank.py:2884:_save]
|
| 316 |
+
2025-05-29 19:35:42,775 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/checkpoint-88:
|
| 317 |
+
+---------+-------------------+------------+
|
| 318 |
+
| Index | Saved File | Size |
|
| 319 |
+
+=========+===================+============+
|
| 320 |
+
| 1 | training_args.bin | 0.01 MB |
|
| 321 |
+
+---------+-------------------+------------+
|
| 322 |
+
| 2 | model.safetensors | 4122.74 MB |
|
| 323 |
+
+---------+-------------------+------------+
|
| 324 |
+
| 3 | config.json | 0.00 MB |
|
| 325 |
+
+---------+-------------------+------------+ - [learning2rank.py:2901:_save]
|
| 326 |
+
2025-05-29 19:35:50,541 - INFO -
|
| 327 |
+
[36m🚂 Training Metrics (Step 90) 🚂
|
| 328 |
+
+---------------+--------------+
|
| 329 |
+
| Metric | Value |
|
| 330 |
+
+===============+==============+
|
| 331 |
+
| loss | -7.78904e+17 |
|
| 332 |
+
+---------------+--------------+
|
| 333 |
+
| grad_norm | 4.04588e+17 |
|
| 334 |
+
+---------------+--------------+
|
| 335 |
+
| learning_rate | 8.3e-05 |
|
| 336 |
+
+---------------+--------------+
|
| 337 |
+
| epoch | 2.04624 |
|
| 338 |
+
+---------------+--------------+[0m - [learning2rank.py:2307:on_log]
|
| 339 |
+
2025-05-29 19:36:04,506 - INFO -
|
| 340 |
+
[36m🚂 Training Metrics (Step 100) 🚂
|
| 341 |
+
+---------------+--------------+
|
| 342 |
+
| Metric | Value |
|
| 343 |
+
+===============+==============+
|
| 344 |
+
| loss | -2.16708e+17 |
|
| 345 |
+
+---------------+--------------+
|
| 346 |
+
| grad_norm | 6.69977e+17 |
|
| 347 |
+
+---------------+--------------+
|
| 348 |
+
| learning_rate | 7.7e-05 |
|
| 349 |
+
+---------------+--------------+
|
| 350 |
+
| epoch | 2.27746 |
|
| 351 |
+
+---------------+--------------+[0m - [learning2rank.py:2307:on_log]
|
| 352 |
+
2025-05-29 19:36:18,486 - INFO -
|
| 353 |
+
[36m🚂 Training Metrics (Step 110) 🚂
|
| 354 |
+
+---------------+-------------+
|
| 355 |
+
| Metric | Value |
|
| 356 |
+
+===============+=============+
|
| 357 |
+
| loss | -3.3602e+18 |
|
| 358 |
+
+---------------+-------------+
|
| 359 |
+
| grad_norm | nan |
|
| 360 |
+
+---------------+-------------+
|
| 361 |
+
| learning_rate | 7.3e-05 |
|
| 362 |
+
+---------------+-------------+
|
| 363 |
+
| epoch | 2.50867 |
|
| 364 |
+
+---------------+-------------+[0m - [learning2rank.py:2307:on_log]
|
| 365 |
+
2025-05-29 19:36:32,497 - INFO -
|
| 366 |
+
[36m🚂 Training Metrics (Step 120) 🚂
|
| 367 |
+
+---------------+--------------+
|
| 368 |
+
| Metric | Value |
|
| 369 |
+
+===============+==============+
|
| 370 |
+
| loss | -4.15132e+17 |
|
| 371 |
+
+---------------+--------------+
|
| 372 |
+
| grad_norm | 7.31787e+17 |
|
| 373 |
+
+---------------+--------------+
|
| 374 |
+
| learning_rate | 6.7e-05 |
|
| 375 |
+
+---------------+--------------+
|
| 376 |
+
| epoch | 2.73988 |
|
| 377 |
+
+---------------+--------------+[0m - [learning2rank.py:2307:on_log]
|
| 378 |
+
2025-05-29 19:36:46,461 - INFO -
|
| 379 |
+
[36m🚂 Training Metrics (Step 130) 🚂
|
| 380 |
+
+---------------+--------------+
|
| 381 |
+
| Metric | Value |
|
| 382 |
+
+===============+==============+
|
| 383 |
+
| loss | -1.23755e+18 |
|
| 384 |
+
+---------------+--------------+
|
| 385 |
+
| grad_norm | 2.11757e+17 |
|
| 386 |
+
+---------------+--------------+
|
| 387 |
+
| learning_rate | 6.2e-05 |
|
| 388 |
+
+---------------+--------------+
|
| 389 |
+
| epoch | 2.9711 |
|
| 390 |
+
+---------------+--------------+[0m - [learning2rank.py:2307:on_log]
|
| 391 |
+
2025-05-29 19:36:48,212 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [learning2rank.py:2755:evaluate]
|
| 392 |
+
2025-05-29 19:40:00,995 - INFO -
|
| 393 |
+
[33m🔍 Evaluation Metrics 🔍
|
| 394 |
+
+-------------------+--------------+
|
| 395 |
+
| Metric | Value |
|
| 396 |
+
+===================+==============+
|
| 397 |
+
| eval_loss | -4.05479e+17 |
|
| 398 |
+
+-------------------+--------------+
|
| 399 |
+
| eval_ndcg | 0.956806 |
|
| 400 |
+
+-------------------+--------------+
|
| 401 |
+
| eval_ndcg@25 | 0.793177 |
|
| 402 |
+
+-------------------+--------------+
|
| 403 |
+
| eval_precision@25 | 0.890286 |
|
| 404 |
+
+-------------------+--------------+[0m - [learning2rank.py:2326:on_evaluate]
|
| 405 |
+
2025-05-29 19:40:02,153 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/checkpoint-132 - [learning2rank.py:2879:_save]
|
| 406 |
+
2025-05-29 19:40:02,154 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/checkpoint-132 - [learning2rank.py:2884:_save]
|
| 407 |
+
2025-05-29 19:40:02,155 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/checkpoint-132:
|
| 408 |
+
+---------+-------------------+------------+
|
| 409 |
+
| Index | Saved File | Size |
|
| 410 |
+
+=========+===================+============+
|
| 411 |
+
| 1 | training_args.bin | 0.01 MB |
|
| 412 |
+
+---------+-------------------+------------+
|
| 413 |
+
| 2 | model.safetensors | 4122.74 MB |
|
| 414 |
+
+---------+-------------------+------------+
|
| 415 |
+
| 3 | config.json | 0.00 MB |
|
| 416 |
+
+---------+-------------------+------------+ - [learning2rank.py:2901:_save]
|
| 417 |
+
2025-05-29 19:40:18,266 - INFO -
|
| 418 |
+
[36m🚂 Training Metrics (Step 140) 🚂
|
| 419 |
+
+---------------+--------------+
|
| 420 |
+
| Metric | Value |
|
| 421 |
+
+===============+==============+
|
| 422 |
+
| loss | -9.65112e+18 |
|
| 423 |
+
+---------------+--------------+
|
| 424 |
+
| grad_norm | 1.7024e+17 |
|
| 425 |
+
+---------------+--------------+
|
| 426 |
+
| learning_rate | 5.7e-05 |
|
| 427 |
+
+---------------+--------------+
|
| 428 |
+
| epoch | 3.18497 |
|
| 429 |
+
+---------------+--------------+[0m - [learning2rank.py:2307:on_log]
|
| 430 |
+
2025-05-29 19:40:32,114 - INFO -
|
| 431 |
+
[36m🚂 Training Metrics (Step 150) 🚂
|
| 432 |
+
+---------------+--------------+
|
| 433 |
+
| Metric | Value |
|
| 434 |
+
+===============+==============+
|
| 435 |
+
| loss | -6.81527e+18 |
|
| 436 |
+
+---------------+--------------+
|
| 437 |
+
| grad_norm | 1.33906e+17 |
|
| 438 |
+
+---------------+--------------+
|
| 439 |
+
| learning_rate | 5.2e-05 |
|
| 440 |
+
+---------------+--------------+
|
| 441 |
+
| epoch | 3.41619 |
|
| 442 |
+
+---------------+--------------+[0m - [learning2rank.py:2307:on_log]
|
| 443 |
+
2025-05-29 19:40:45,965 - INFO -
|
| 444 |
+
[36m🚂 Training Metrics (Step 160) 🚂
|
| 445 |
+
+---------------+--------------+
|
| 446 |
+
| Metric | Value |
|
| 447 |
+
+===============+==============+
|
| 448 |
+
| loss | -4.90954e+17 |
|
| 449 |
+
+---------------+--------------+
|
| 450 |
+
| grad_norm | 2.87998e+17 |
|
| 451 |
+
+---------------+--------------+
|
| 452 |
+
| learning_rate | 4.6e-05 |
|
| 453 |
+
+---------------+--------------+
|
| 454 |
+
| epoch | 3.6474 |
|
| 455 |
+
+---------------+--------------+[0m - [learning2rank.py:2307:on_log]
|
| 456 |
+
2025-05-29 19:40:59,736 - INFO -
|
| 457 |
+
[36m🚂 Training Metrics (Step 170) 🚂
|
| 458 |
+
+---------------+--------------+
|
| 459 |
+
| Metric | Value |
|
| 460 |
+
+===============+==============+
|
| 461 |
+
| loss | -3.49743e+17 |
|
| 462 |
+
+---------------+--------------+
|
| 463 |
+
| grad_norm | 2.0459e+17 |
|
| 464 |
+
+---------------+--------------+
|
| 465 |
+
| learning_rate | 4e-05 |
|
| 466 |
+
+---------------+--------------+
|
| 467 |
+
| epoch | 3.87861 |
|
| 468 |
+
+---------------+--------------+[0m - [learning2rank.py:2307:on_log]
|
| 469 |
+
2025-05-29 19:41:03,699 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/checkpoint-172 - [learning2rank.py:2879:_save]
|
| 470 |
+
2025-05-29 19:41:03,701 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/checkpoint-172 - [learning2rank.py:2884:_save]
|
| 471 |
+
2025-05-29 19:41:03,701 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/checkpoint-172:
|
| 472 |
+
+---------+-------------------+------------+
|
| 473 |
+
| Index | Saved File | Size |
|
| 474 |
+
+=========+===================+============+
|
| 475 |
+
| 1 | training_args.bin | 0.01 MB |
|
| 476 |
+
+---------+-------------------+------------+
|
| 477 |
+
| 2 | model.safetensors | 4122.74 MB |
|
| 478 |
+
+---------+-------------------+------------+
|
| 479 |
+
| 3 | config.json | 0.00 MB |
|
| 480 |
+
+---------+-------------------+------------+ - [learning2rank.py:2901:_save]
|
| 481 |
+
2025-05-29 19:41:03,908 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [learning2rank.py:2755:evaluate]
|
| 482 |
+
2025-05-29 19:44:16,555 - INFO -
|
| 483 |
+
[33m🔍 Evaluation Metrics 🔍
|
| 484 |
+
+-------------------+-------------+
|
| 485 |
+
| Metric | Value |
|
| 486 |
+
+===================+=============+
|
| 487 |
+
| eval_loss | -4.1649e+17 |
|
| 488 |
+
+-------------------+-------------+
|
| 489 |
+
| eval_ndcg | 0.956866 |
|
| 490 |
+
+-------------------+-------------+
|
| 491 |
+
| eval_ndcg@25 | 0.873974 |
|
| 492 |
+
+-------------------+-------------+
|
| 493 |
+
| eval_precision@25 | 0.930286 |
|
| 494 |
+
+-------------------+-------------+[0m - [learning2rank.py:2326:on_evaluate]
|
| 495 |
+
2025-05-29 19:44:18,478 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/checkpoint-172 - [learning2rank.py:2879:_save]
|
| 496 |
+
2025-05-29 19:44:18,479 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/checkpoint-172 - [learning2rank.py:2884:_save]
|
| 497 |
+
2025-05-29 19:44:18,480 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/checkpoint-172:
|
| 498 |
+
+---------+--------------------+------------+
|
| 499 |
+
| Index | Saved File | Size |
|
| 500 |
+
+=========+====================+============+
|
| 501 |
+
| 1 | training_args.bin | 0.01 MB |
|
| 502 |
+
+---------+--------------------+------------+
|
| 503 |
+
| 2 | optimizer.pt | 352.39 MB |
|
| 504 |
+
+---------+--------------------+------------+
|
| 505 |
+
| 3 | model.safetensors | 4122.74 MB |
|
| 506 |
+
+---------+--------------------+------------+
|
| 507 |
+
| 4 | scaler.pt | 0.00 MB |
|
| 508 |
+
+---------+--------------------+------------+
|
| 509 |
+
| 5 | config.json | 0.00 MB |
|
| 510 |
+
+---------+--------------------+------------+
|
| 511 |
+
| 6 | scheduler.pt | 0.00 MB |
|
| 512 |
+
+---------+--------------------+------------+
|
| 513 |
+
| 7 | trainer_state.json | 0.00 MB |
|
| 514 |
+
+---------+--------------------+------------+
|
| 515 |
+
| 8 | rng_state.pth | 0.01 MB |
|
| 516 |
+
+---------+--------------------+------------+ - [learning2rank.py:2901:_save]
|
| 517 |
+
2025-05-29 19:44:18,765 - INFO - 📂 Loading best model from ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/checkpoint-172 - [learning2rank.py:2957:_load_best_model]
|
| 518 |
+
2025-05-29 19:44:18,765 - INFO - 🖥️ Model is on device: cuda:0 - [learning2rank.py:2967:_load_best_model]
|
| 519 |
+
2025-05-29 19:44:18,821 - INFO - 🔑 Key order comparison:
|
| 520 |
+
+---------+------------------------------------------------------------------------+---------------------------------------------------------------------------------------------+
|
| 521 |
+
| Index | Saved state_dict Keys | Model state_dict Keys |
|
| 522 |
+
+=========+========================================================================+=============================================================================================+
|
| 523 |
+
| 1 | base_model.base_model.model.lm_head.weight | base_model.base_model.model.model.embed_tokens.weight |
|
| 524 |
+
+---------+------------------------------------------------------------------------+---------------------------------------------------------------------------------------------+
|
| 525 |
+
| 2 | base_model.base_model.model.model.embed_tokens.weight | base_model.base_model.model.model.layers.0.self_attn.q_proj.base_layer.weight |
|
| 526 |
+
+---------+------------------------------------------------------------------------+---------------------------------------------------------------------------------------------+
|
| 527 |
+
| 3 | base_model.base_model.model.model.layers.0.input_layernorm.weight | base_model.base_model.model.model.layers.0.self_attn.q_proj.base_layer.weight.absmax |
|
| 528 |
+
+---------+------------------------------------------------------------------------+---------------------------------------------------------------------------------------------+
|
| 529 |
+
| 4 | base_model.base_model.model.model.layers.0.mlp.down_proj.weight | base_model.base_model.model.model.layers.0.self_attn.q_proj.base_layer.weight.quant_map |
|
| 530 |
+
+---------+------------------------------------------------------------------------+---------------------------------------------------------------------------------------------+
|
| 531 |
+
| 5 | base_model.base_model.model.model.layers.0.mlp.down_proj.weight.absmax | base_model.base_model.model.model.layers.0.self_attn.q_proj.base_layer.weight.nested_absmax |
|
| 532 |
+
+---------+------------------------------------------------------------------------+---------------------------------------------------------------------------------------------+ - [learning2rank.py:2991:_load_best_model]
|
| 533 |
+
2025-05-29 19:44:19,629 - INFO - ✅ Loaded best model weights from ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/checkpoint-172/model.safetensors - [learning2rank.py:3008:_load_best_model]
|
| 534 |
+
2025-05-29 19:44:19,686 - INFO - ✔️ Weight for base_model.base_model.model.model.embed_tokens.weight matches between saved and loaded state_dict - [learning2rank.py:3020:_load_best_model]
|
| 535 |
+
2025-05-29 19:44:19,708 - INFO - ✔️ Weight for base_model.base_model.model.model.layers.0.self_attn.q_proj.base_layer.weight matches between saved and loaded state_dict - [learning2rank.py:3020:_load_best_model]
|
| 536 |
+
2025-05-29 19:44:19,725 - INFO -
|
| 537 |
+
[36m🚂 Training Metrics (Step 172) 🚂
|
| 538 |
+
+--------------------------+--------------+
|
| 539 |
+
| Metric | Value |
|
| 540 |
+
+==========================+==============+
|
| 541 |
+
| train_runtime | 1038.68 |
|
| 542 |
+
+--------------------------+--------------+
|
| 543 |
+
| train_samples_per_second | 0.666 |
|
| 544 |
+
+--------------------------+--------------+
|
| 545 |
+
| train_steps_per_second | 0.166 |
|
| 546 |
+
+--------------------------+--------------+
|
| 547 |
+
| total_flos | 0 |
|
| 548 |
+
+--------------------------+--------------+
|
| 549 |
+
| train_loss | -2.40817e+18 |
|
| 550 |
+
+--------------------------+--------------+
|
| 551 |
+
| epoch | 3.92485 |
|
| 552 |
+
+--------------------------+--------------+[0m - [learning2rank.py:2307:on_log]
|
| 553 |
+
2025-05-29 19:44:19,726 - INFO - ✨ Training Completed! ✨ - [learning2rank.py:2456:on_train_end]
|
| 554 |
+
2025-05-29 19:44:19,800 - INFO - 📊 Training loss plot saved as '../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/train_loss_plot.png' - [learning2rank.py:2559:on_train_end]
|
| 555 |
+
2025-05-29 19:44:19,858 - INFO - 📊 Evaluation loss plot saved as '../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/eval_loss_plot.png' - [learning2rank.py:2573:on_train_end]
|
| 556 |
+
2025-05-29 19:44:19,918 - INFO - 📊 Evaluation metric plot saved as '../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/eval_ndcg@25_plot.png' - [learning2rank.py:2594:on_train_end]
|
| 557 |
+
2025-05-29 19:44:19,919 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:108:log_section]
|
| 558 |
+
2025-05-29 19:44:19,919 - INFO - + ✨ MODEL SAVING + - [learning2rank.py:109:log_section]
|
| 559 |
+
2025-05-29 19:44:19,919 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:112:log_section]
|
| 560 |
+
2025-05-29 19:44:19,919 - INFO - 💾 Saving trained model and pushing to Hugging Face Hub... - [learning2rank.py:4014:main]
|
| 561 |
+
2025-05-29 19:44:19,919 - INFO - 📁 Creating/using output directory: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r - [learning2rank.py:3275:save_and_push]
|
| 562 |
+
2025-05-29 19:44:21,100 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r - [learning2rank.py:2879:_save]
|
| 563 |
+
2025-05-29 19:44:21,102 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r - [learning2rank.py:2884:_save]
|
| 564 |
+
2025-05-29 19:44:21,103 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r:
|
| 565 |
+
+---------+-----------------------+------------+
|
| 566 |
+
| Index | Saved File | Size |
|
| 567 |
+
+=========+=======================+============+
|
| 568 |
+
| 1 | eval_loss_plot.png | 0.03 MB |
|
| 569 |
+
+---------+-----------------------+------------+
|
| 570 |
+
| 2 | training_args.bin | 0.01 MB |
|
| 571 |
+
+---------+-----------------------+------------+
|
| 572 |
+
| 3 | model.safetensors | 4122.74 MB |
|
| 573 |
+
+---------+-----------------------+------------+
|
| 574 |
+
| 4 | eval_ndcg@25_plot.png | 0.03 MB |
|
| 575 |
+
+---------+-----------------------+------------+
|
| 576 |
+
| 5 | config.json | 0.00 MB |
|
| 577 |
+
+---------+-----------------------+------------+
|
| 578 |
+
| 6 | train_loss_plot.png | 0.04 MB |
|
| 579 |
+
+---------+-----------------------+------------+ - [learning2rank.py:2901:_save]
|
| 580 |
+
2025-05-29 19:44:24,684 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r - [learning2rank.py:2879:_save]
|
| 581 |
+
2025-05-29 19:44:24,685 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r - [learning2rank.py:2884:_save]
|
| 582 |
+
2025-05-29 19:44:24,686 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r:
|
| 583 |
+
+---------+-----------------------+------------+
|
| 584 |
+
| Index | Saved File | Size |
|
| 585 |
+
+=========+=======================+============+
|
| 586 |
+
| 1 | eval_loss_plot.png | 0.03 MB |
|
| 587 |
+
+---------+-----------------------+------------+
|
| 588 |
+
| 2 | training_args.bin | 0.01 MB |
|
| 589 |
+
+---------+-----------------------+------------+
|
| 590 |
+
| 3 | model.safetensors | 4122.74 MB |
|
| 591 |
+
+---------+-----------------------+------------+
|
| 592 |
+
| 4 | eval_ndcg@25_plot.png | 0.03 MB |
|
| 593 |
+
+---------+-----------------------+------------+
|
| 594 |
+
| 5 | config.json | 0.00 MB |
|
| 595 |
+
+---------+-----------------------+------------+
|
| 596 |
+
| 6 | train_loss_plot.png | 0.04 MB |
|
| 597 |
+
+---------+-----------------------+------------+ - [learning2rank.py:2901:_save]
|
| 598 |
+
2025-05-29 19:45:41,784 - INFO - 💾 Model saved to: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r - [learning2rank.py:3279:save_and_push]
|
| 599 |
+
2025-05-29 19:45:41,814 - INFO - 🖌️ Tokenizer saved to: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r - [learning2rank.py:3283:save_and_push]
|