File size: 49,284 Bytes
fe1ea1f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 |
2025-06-05 15:02:25,280 - INFO - ================================================================================ - [multilabel_classify.py:100:log_section]
2025-06-05 15:02:25,281 - INFO - = 📌 INITIALIZING TRAINING ENVIRONMENT = - [multilabel_classify.py:101:log_section]
2025-06-05 15:02:25,281 - INFO - ================================================================================ - [multilabel_classify.py:104:log_section]
2025-06-05 15:02:25,281 - INFO - 🚀 Setting up data paths and environment variables... - [multilabel_classify.py:3560:main]
2025-06-05 15:02:25,281 - INFO - 📂 Using output directory: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:3566:main]
2025-06-05 15:02:25,281 - INFO - 🛠️ Command-line Arguments: - [multilabel_classify.py:368:print_args]
2025-06-05 15:02:25,281 - INFO -
🔹 output_dir: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b
🔹 source_url: XURLs.MIMIC4_DEMO
🔹 data: mimic4_icd10_full
🔹 logfile: classification_log
🔹 base_dir: ../tmp/MIMIC4_DEMO
🔹 hub_model_id: deb101/mistral-7b-instruct-v0.3-mimic4-adapt
🔹 model_name: mistralai/Mistral-7B-Instruct-v0.3
🔹 max_length: 512
🔹 do_fresh_training: True
🔹 load_from_checkpoint: False
🔹 task: multilabel-classify
🔹 num_train_epochs: 4
🔹 per_device_train_batch_size: 8
🔹 per_device_eval_batch_size: 8
🔹 metric_for_best_model: precision_at_15
🔹 learning_rate: 0.0001
🔹 final_lr_scheduling: 1e-06
🔹 warmup_steps: 500
🔹 logfile_path: ../tmp/logs/classification_log_2025-06-05_15-02-25.log
🔹 source: /home/ubuntu/.xcube/data/mimic4_demo - [multilabel_classify.py:369:print_args]
2025-06-05 15:02:25,281 - INFO - ➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖ - [multilabel_classify.py:370:print_args]
2025-06-05 15:02:25,281 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:100:log_section]
2025-06-05 15:02:25,281 - INFO - + ✨ LOADING DATASETS + - [multilabel_classify.py:101:log_section]
2025-06-05 15:02:25,281 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:104:log_section]
2025-06-05 15:02:25,282 - INFO - 📊 Loading main datasets.... - [multilabel_classify.py:3572:main]
2025-06-05 15:02:33,869 - INFO - 🔍 Total unique labels in dataset: 7942 - [multilabel_classify.py:3353:sample_df_with_full_label_coverage]
2025-06-05 15:02:33,882 - INFO - 🧪 Attempt 1: Sampled 122 rows covering 863 labels. - [multilabel_classify.py:3367:sample_df_with_full_label_coverage]
2025-06-05 15:02:33,892 - INFO - 🧪 Attempt 2: Sampled 122 rows covering 816 labels. - [multilabel_classify.py:3367:sample_df_with_full_label_coverage]
2025-06-05 15:02:33,901 - INFO - 🧪 Attempt 3: Sampled 122 rows covering 885 labels. - [multilabel_classify.py:3367:sample_df_with_full_label_coverage]
2025-06-05 15:02:33,910 - INFO - 🧪 Attempt 4: Sampled 122 rows covering 828 labels. - [multilabel_classify.py:3367:sample_df_with_full_label_coverage]
2025-06-05 15:02:33,920 - INFO - 🧪 Attempt 5: Sampled 122 rows covering 879 labels. - [multilabel_classify.py:3367:sample_df_with_full_label_coverage]
2025-06-05 15:02:33,928 - INFO - 🧪 Attempt 6: Sampled 122 rows covering 852 labels. - [multilabel_classify.py:3367:sample_df_with_full_label_coverage]
2025-06-05 15:02:33,937 - INFO - 🧪 Attempt 7: Sampled 122 rows covering 838 labels. - [multilabel_classify.py:3367:sample_df_with_full_label_coverage]
2025-06-05 15:02:33,946 - INFO - 🧪 Attempt 8: Sampled 122 rows covering 851 labels. - [multilabel_classify.py:3367:sample_df_with_full_label_coverage]
2025-06-05 15:02:33,955 - INFO - 🧪 Attempt 9: Sampled 122 rows covering 825 labels. - [multilabel_classify.py:3367:sample_df_with_full_label_coverage]
2025-06-05 15:02:33,964 - INFO - 🧪 Attempt 10: Sampled 122 rows covering 833 labels. - [multilabel_classify.py:3367:sample_df_with_full_label_coverage]
2025-06-05 15:02:33,964 - INFO - ⚠️ Skipping label coverage fix. 7109 labels are missing. - [multilabel_classify.py:3385:sample_df_with_full_label_coverage]
2025-06-05 15:02:33,964 - INFO - ✅ Final row count: 122 (Valid: 20, Not-valid: 102) - [multilabel_classify.py:3390:sample_df_with_full_label_coverage]
2025-06-05 15:02:33,983 - INFO - ******************************************************************************** - [multilabel_classify.py:100:log_section]
2025-06-05 15:02:33,983 - INFO - * 🌟 STARTING MULTI_LABEL CLASSIFICATION MODEL TRAINING * - [multilabel_classify.py:101:log_section]
2025-06-05 15:02:33,983 - INFO - ******************************************************************************** - [multilabel_classify.py:104:log_section]
2025-06-05 15:02:33,983 - INFO - 🔐 Loaded authentication token from environment - [multilabel_classify.py:3599:main]
2025-06-05 15:02:33,983 - INFO - 🏷️ Hub Model ID for this Classification task: deb101/mistral-7b-instruct-v0.3-mimic4-adapt-multilabel-classify - [multilabel_classify.py:3603:main]
2025-06-05 15:02:33,984 - INFO - -------------------------------------------------------------------------------- - [multilabel_classify.py:100:log_section]
2025-06-05 15:02:33,984 - INFO - - 📋 MODEL EXISTENCE CHECK - - [multilabel_classify.py:101:log_section]
2025-06-05 15:02:33,984 - INFO - -------------------------------------------------------------------------------- - [multilabel_classify.py:104:log_section]
2025-06-05 15:02:33,984 - INFO - 🔍 Checking model existence locally and on Hugging Face Hub... - [multilabel_classify.py:3468:check_model_existence]
2025-06-05 15:02:33,984 - INFO - ✅ Model exists locally at: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:3473:check_model_existence]
2025-06-05 15:02:34,066 - INFO - ✅ Model exists on Hugging Face Hub with ID: deb101/mistral-7b-instruct-v0.3-mimic4-adapt-multilabel-classify - [multilabel_classify.py:3487:check_model_existence]
2025-06-05 15:02:34,066 - INFO - 📁 Model exists either locally or on Hub - [multilabel_classify.py:3513:check_model_existence]
2025-06-05 15:02:34,067 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:100:log_section]
2025-06-05 15:02:34,067 - INFO - + ✨ STARTING FRESH TRAINING + - [multilabel_classify.py:101:log_section]
2025-06-05 15:02:34,067 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:104:log_section]
2025-06-05 15:02:34,067 - INFO - 🔄 Starting fresh training (either forced or model not found)... - [multilabel_classify.py:3616:main]
2025-06-05 15:02:34,081 - WARNING - Note: Environment variable`HF_TOKEN` is set and is the current active token independently from the token you've just configured. - [_login.py:415:_login]
2025-06-05 15:02:34,081 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:100:log_section]
2025-06-05 15:02:34,081 - INFO - + ✨ LOADING BASE MODEL + - [multilabel_classify.py:101:log_section]
2025-06-05 15:02:34,081 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:104:log_section]
2025-06-05 15:02:34,081 - INFO - 📥 Loading pretrained model and tokenizer... - [multilabel_classify.py:3646:main]
2025-06-05 15:02:34,081 - INFO - 🚀 Starting model and tokenizer loading process... - [multilabel_classify.py:1243:load_base_model_and_tokenizer]
2025-06-05 15:02:34,082 - INFO - 📊 Quantization config: BitsAndBytesConfig {
"_load_in_4bit": true,
"_load_in_8bit": false,
"bnb_4bit_compute_dtype": "bfloat16",
"bnb_4bit_quant_storage": "uint8",
"bnb_4bit_quant_type": "nf4",
"bnb_4bit_use_double_quant": true,
"llm_int8_enable_fp32_cpu_offload": false,
"llm_int8_has_fp16_weight": false,
"llm_int8_skip_modules": null,
"llm_int8_threshold": 6.0,
"load_in_4bit": true,
"load_in_8bit": false,
"quant_method": "bitsandbytes"
}
- [multilabel_classify.py:1252:load_base_model_and_tokenizer]
2025-06-05 15:02:34,082 - INFO - 🔤 Loading tokenizer for model: deb101/mistral-7b-instruct-v0.3-mimic4-adapt... - [multilabel_classify.py:1256:load_base_model_and_tokenizer]
2025-06-05 15:02:34,439 - INFO - 🔍 Checking if deb101/mistral-7b-instruct-v0.3-mimic4-adapt is a PEFT model... - [multilabel_classify.py:1268:load_base_model_and_tokenizer]
2025-06-05 15:02:34,464 - INFO - ✅ Detected PEFT model. Base model: mistralai/Mistral-7B-Instruct-v0.3 - [multilabel_classify.py:1272:load_base_model_and_tokenizer]
2025-06-05 15:02:34,464 - INFO - 🔍 Loading model configuration for mistralai/Mistral-7B-Instruct-v0.3... - [multilabel_classify.py:1282:load_base_model_and_tokenizer]
2025-06-05 15:02:34,496 - INFO - Model type: mistral, Architectures: ['MistralForCausalLM'] - [multilabel_classify.py:1288:load_base_model_and_tokenizer]
2025-06-05 15:02:34,496 - INFO - 🧠 Loading base model: mistralai/Mistral-7B-Instruct-v0.3... - [multilabel_classify.py:1351:load_base_model_and_tokenizer]
2025-06-05 15:02:35,026 - INFO - We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). - [modeling.py:991:get_balanced_memory]
2025-06-05 15:02:40,290 - INFO - 🧩 Loading PEFT adapters for deb101/mistral-7b-instruct-v0.3-mimic4-adapt... - [multilabel_classify.py:1366:load_base_model_and_tokenizer]
2025-06-05 15:02:40,733 - INFO - 🔧 Before enabling PEFT adapters for training - [multilabel_classify.py:1368:load_base_model_and_tokenizer]
2025-06-05 15:02:40,735 - INFO - 📊 trainable params: 0 || all params: 7,254,839,296 || trainable%: 0.0000 - [multilabel_classify.py:159:log_print_output]
2025-06-05 15:02:40,738 - INFO - 🔧 After Enabling PEFT adapters for training - [multilabel_classify.py:1375:load_base_model_and_tokenizer]
2025-06-05 15:02:40,740 - INFO - 📊 trainable params: 6,815,744 || all params: 7,254,839,296 || trainable%: 0.0939 - [multilabel_classify.py:159:log_print_output]
2025-06-05 15:02:40,741 - INFO - ✅ Model and tokenizer successfully loaded! - [multilabel_classify.py:1416:load_base_model_and_tokenizer]
2025-06-05 15:02:40,741 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:100:log_section]
2025-06-05 15:02:40,741 - INFO - + ✨ DATA PREPROCESSING + - [multilabel_classify.py:101:log_section]
2025-06-05 15:02:40,741 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:104:log_section]
2025-06-05 15:02:40,742 - INFO - 🔄 Loading and preprocessing training data... - [multilabel_classify.py:3654:main]
2025-06-05 15:02:40,746 - INFO - Total number of labels: 833 - [multilabel_classify.py:1044:preprocess_data]
2025-06-05 15:02:40,746 - INFO - Rare labels (freq < 50): 832 - [multilabel_classify.py:1045:preprocess_data]
2025-06-05 15:02:40,746 - INFO - Not rare labels (freq >= 50): 1 - [multilabel_classify.py:1046:preprocess_data]
2025-06-05 15:02:40,746 - INFO - Label partitions and classes saved to ../tmp/MIMIC4_DEMO/labels_partition.json - [multilabel_classify.py:1047:preprocess_data]
2025-06-05 15:02:42,069 - INFO - The size of training set: 567 - [multilabel_classify.py:1143:preprocess_data]
2025-06-05 15:02:42,069 - INFO - The size of Evaluation set: 136 - [multilabel_classify.py:1144:preprocess_data]
2025-06-05 15:02:42,074 - INFO - Number of unique ICD-10 codes: 833 - [multilabel_classify.py:3660:main]
2025-06-05 15:02:42,074 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:100:log_section]
2025-06-05 15:02:42,074 - INFO - + ✨ MODEL INITIALIZATION + - [multilabel_classify.py:101:log_section]
2025-06-05 15:02:42,074 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:104:log_section]
2025-06-05 15:02:42,075 - INFO - 🧠 Initializing custom L2R model for outputting per-token relevance scores per ICD-10 codes. - [multilabel_classify.py:3663:main]
2025-06-05 15:02:42,075 - INFO - Will now start to create Multilabel-Classification Model from the base model - [multilabel_classify.py:560:__init__]
2025-06-05 15:02:42,078 - INFO - 📊 trainable params: 6,815,744 || all params: 3,765,178,368 || trainable%: 0.1810 - [multilabel_classify.py:614:compute_trainable_params]
2025-06-05 15:02:42,416 - INFO - Creating the Multi-Label Classification Model from base model mistralai/Mistral-7B-Instruct-v0.3 completed!!! - [multilabel_classify.py:602:__init__]
2025-06-05 15:02:42,419 - INFO - 📊 trainable params: 84,177,025 || all params: 3,842,539,649 || trainable%: 2.1907 - [multilabel_classify.py:614:compute_trainable_params]
2025-06-05 15:02:42,419 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:100:log_section]
2025-06-05 15:02:42,419 - INFO - + ✨ TRAINING PREPARATION + - [multilabel_classify.py:101:log_section]
2025-06-05 15:02:42,419 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:104:log_section]
2025-06-05 15:02:42,419 - INFO - ⚙️ Preparing training components and optimizers... - [multilabel_classify.py:3670:main]
2025-06-05 15:02:42,476 - INFO - 🖥️ Device: NVIDIA GH200 480GB - [multilabel_classify.py:891:log_training_configuration]
2025-06-05 15:02:42,476 - INFO - 🔋 CUDA Available: True - [multilabel_classify.py:894:log_training_configuration]
2025-06-05 15:02:42,476 - INFO - 💾 CUDA Device Count: 1 - [multilabel_classify.py:895:log_training_configuration]
2025-06-05 15:02:42,478 - INFO -
📋 Training Configuration 📋
+----------+-----------------------------+------------------------------------------------------------------+
| 🌟 Emoji | 🏷️ Parameter | 📊 Value |
+----------+-----------------------------+------------------------------------------------------------------+
| 📁 | Output Directory | ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b |
| 🔁 | Training Epochs | 4 |
| 🏋️ | Train Batch Size | 8 |
| 🔍 | Eval Batch Size | 8 |
| 📊 | Gradient Accumulation Steps | 4 |
| 🚀 | Learning Rate | 0.0001 |
| 🌅 | Warmup Steps | 500 |
| 💾 | Save Strategy | epoch |
| 💾 | Save Total Limit | 10 |
| 📊 | Evaluation Strategy | epoch |
| 🎯 | Best Model Metric | precision_at_15 |
| 📝 | Logging Strategy | steps (every 10 steps) |
| 🌐 | Push to Hub | True |
| 🌐 | Hub Model ID | deb101/mistral-7b-instruct-v0.3-mimic4-adapt-multilabel-classify |
| 🔢 | Steps per Epoch | 17 |
| 🔢 | Total Training Steps | 68 |
| 🔢 | Evaluation Steps | 17 |
| 📊 | Training Dataset Size | 567 samples 🏋️ |
| 📊 | Evaluation Dataset Size | 136 samples 🔍 |
+----------+-----------------------------+------------------------------------------------------------------+ - [multilabel_classify.py:883:log_training_args]
2025-06-05 15:02:42,478 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:100:log_section]
2025-06-05 15:02:42,478 - INFO - + ✨ MODEL TRAINING + - [multilabel_classify.py:101:log_section]
2025-06-05 15:02:42,478 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:104:log_section]
2025-06-05 15:02:42,479 - INFO - 🏋️ Starting model training process... - [multilabel_classify.py:3692:main]
2025-06-05 15:02:42,520 - INFO - We are registering the tokenizer deb101/mistral-7b-instruct-v0.3-mimic4-adapt in Custom Trainer - [multilabel_classify.py:1988:__init__]
2025-06-05 15:02:42,770 - INFO - 🚀 Starting Training... - [multilabel_classify.py:1642:on_train_begin]
2025-06-05 15:03:03,122 - INFO -
[36m🚂 Training Metrics (Step 10) 🚂
+---------------+---------+
| Metric | Value |
+===============+=========+
| loss | 0.6384 |
+---------------+---------+
| grad_norm | 6.84453 |
+---------------+---------+
| learning_rate | 2e-06 |
+---------------+---------+
| epoch | 0.56338 |
+---------------+---------+[0m - [multilabel_classify.py:1836:on_log]
2025-06-05 15:03:17,100 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [multilabel_classify.py:2000:evaluate]
2025-06-05 15:03:52,220 - INFO -
[33m🔍 Evaluation Metrics 🔍
+-------------------------------+----------+
| Metric | Value |
+===============================+==========+
| eval_f1_micro | 0 |
+-------------------------------+----------+
| eval_f1_macro | 0 |
+-------------------------------+----------+
| eval_precision_at_5 | 0.036765 |
+-------------------------------+----------+
| eval_recall_at_5 | 0.008744 |
+-------------------------------+----------+
| eval_precision_at_8 | 0.037684 |
+-------------------------------+----------+
| eval_recall_at_8 | 0.017401 |
+-------------------------------+----------+
| eval_precision_at_15 | 0.037745 |
+-------------------------------+----------+
| eval_recall_at_15 | 0.032384 |
+-------------------------------+----------+
| eval_rare_f1_micro | 0 |
+-------------------------------+----------+
| eval_rare_f1_macro | 0 |
+-------------------------------+----------+
| eval_rare_precision | 0 |
+-------------------------------+----------+
| eval_rare_recall | 0 |
+-------------------------------+----------+
| eval_rare_precision_at_5 | 0.029412 |
+-------------------------------+----------+
| eval_rare_recall_at_5 | 0.00805 |
+-------------------------------+----------+
| eval_rare_precision_at_8 | 0.026654 |
+-------------------------------+----------+
| eval_rare_recall_at_8 | 0.010721 |
+-------------------------------+----------+
| eval_rare_precision_at_15 | 0.027451 |
+-------------------------------+----------+
| eval_rare_recall_at_15 | 0.021147 |
+-------------------------------+----------+
| eval_not_rare_f1_micro | 0.595588 |
+-------------------------------+----------+
| eval_not_rare_f1_macro | 0.373272 |
+-------------------------------+----------+
| eval_not_rare_precision | 0.595588 |
+-------------------------------+----------+
| eval_not_rare_recall | 0.595588 |
+-------------------------------+----------+
| eval_not_rare_precision_at_5 | 0.080882 |
+-------------------------------+----------+
| eval_not_rare_recall_at_5 | 0.404412 |
+-------------------------------+----------+
| eval_not_rare_precision_at_8 | 0.050551 |
+-------------------------------+----------+
| eval_not_rare_recall_at_8 | 0.404412 |
+-------------------------------+----------+
| eval_not_rare_precision_at_15 | 0.026961 |
+-------------------------------+----------+
| eval_not_rare_recall_at_15 | 0.404412 |
+-------------------------------+----------+
| eval_loss | 0.229106 |
+-------------------------------+----------+[0m - [multilabel_classify.py:1855:on_evaluate]
2025-06-05 15:03:55,736 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-18 - [multilabel_classify.py:2093:_save]
2025-06-05 15:03:55,737 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-18 - [multilabel_classify.py:2098:_save]
2025-06-05 15:03:55,738 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-18:
+---------+--------------------+------------+
| Index | Saved File | Size |
+=========+====================+============+
| 1 | training_args.bin | 0.01 MB |
+---------+--------------------+------------+
| 2 | optimizer.pt | 642.30 MB |
+---------+--------------------+------------+
| 3 | model.safetensors | 4267.74 MB |
+---------+--------------------+------------+
| 4 | scaler.pt | 0.00 MB |
+---------+--------------------+------------+
| 5 | config.json | 0.00 MB |
+---------+--------------------+------------+
| 6 | scheduler.pt | 0.00 MB |
+---------+--------------------+------------+
| 7 | trainer_state.json | 0.00 MB |
+---------+--------------------+------------+
| 8 | rng_state.pth | 0.01 MB |
+---------+--------------------+------------+ - [multilabel_classify.py:2115:_save]
2025-06-05 15:04:01,845 - INFO -
[36m🚂 Training Metrics (Step 20) 🚂
+---------------+---------+
| Metric | Value |
+===============+=========+
| loss | 0.345 |
+---------------+---------+
| grad_norm | 2.53065 |
+---------------+---------+
| learning_rate | 4e-06 |
+---------------+---------+
| epoch | 1.11268 |
+---------------+---------+[0m - [multilabel_classify.py:1836:on_log]
2025-06-05 15:04:19,966 - INFO -
[36m🚂 Training Metrics (Step 30) 🚂
+---------------+----------+
| Metric | Value |
+===============+==========+
| loss | 0.1265 |
+---------------+----------+
| grad_norm | 0.237818 |
+---------------+----------+
| learning_rate | 6e-06 |
+---------------+----------+
| epoch | 1.67606 |
+---------------+----------+[0m - [multilabel_classify.py:1836:on_log]
2025-06-05 15:04:30,351 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [multilabel_classify.py:2000:evaluate]
2025-06-05 15:05:05,550 - INFO -
[33m🔍 Evaluation Metrics 🔍
+-------------------------------+----------+
| Metric | Value |
+===============================+==========+
| eval_f1_micro | 0 |
+-------------------------------+----------+
| eval_f1_macro | 0 |
+-------------------------------+----------+
| eval_precision_at_5 | 0.041176 |
+-------------------------------+----------+
| eval_recall_at_5 | 0.009645 |
+-------------------------------+----------+
| eval_precision_at_8 | 0.039522 |
+-------------------------------+----------+
| eval_recall_at_8 | 0.016571 |
+-------------------------------+----------+
| eval_precision_at_15 | 0.037255 |
+-------------------------------+----------+
| eval_recall_at_15 | 0.030333 |
+-------------------------------+----------+
| eval_rare_f1_micro | 0 |
+-------------------------------+----------+
| eval_rare_f1_macro | 0 |
+-------------------------------+----------+
| eval_rare_precision | 0 |
+-------------------------------+----------+
| eval_rare_recall | 0 |
+-------------------------------+----------+
| eval_rare_precision_at_5 | 0.025 |
+-------------------------------+----------+
| eval_rare_recall_at_5 | 0.004753 |
+-------------------------------+----------+
| eval_rare_precision_at_8 | 0.027574 |
+-------------------------------+----------+
| eval_rare_recall_at_8 | 0.010902 |
+-------------------------------+----------+
| eval_rare_precision_at_15 | 0.028431 |
+-------------------------------+----------+
| eval_rare_recall_at_15 | 0.02441 |
+-------------------------------+----------+
| eval_not_rare_f1_micro | 0.595588 |
+-------------------------------+----------+
| eval_not_rare_f1_macro | 0.373272 |
+-------------------------------+----------+
| eval_not_rare_precision | 0.595588 |
+-------------------------------+----------+
| eval_not_rare_recall | 0.595588 |
+-------------------------------+----------+
| eval_not_rare_precision_at_5 | 0.080882 |
+-------------------------------+----------+
| eval_not_rare_recall_at_5 | 0.404412 |
+-------------------------------+----------+
| eval_not_rare_precision_at_8 | 0.050551 |
+-------------------------------+----------+
| eval_not_rare_recall_at_8 | 0.404412 |
+-------------------------------+----------+
| eval_not_rare_precision_at_15 | 0.026961 |
+-------------------------------+----------+
| eval_not_rare_recall_at_15 | 0.404412 |
+-------------------------------+----------+
| eval_loss | 0.12156 |
+-------------------------------+----------+[0m - [multilabel_classify.py:1855:on_evaluate]
2025-06-05 15:05:09,029 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-36 - [multilabel_classify.py:2093:_save]
2025-06-05 15:05:09,030 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-36 - [multilabel_classify.py:2098:_save]
2025-06-05 15:05:09,031 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-36:
+---------+--------------------+------------+
| Index | Saved File | Size |
+=========+====================+============+
| 1 | training_args.bin | 0.01 MB |
+---------+--------------------+------------+
| 2 | optimizer.pt | 642.30 MB |
+---------+--------------------+------------+
| 3 | model.safetensors | 4267.74 MB |
+---------+--------------------+------------+
| 4 | scaler.pt | 0.00 MB |
+---------+--------------------+------------+
| 5 | config.json | 0.00 MB |
+---------+--------------------+------------+
| 6 | scheduler.pt | 0.00 MB |
+---------+--------------------+------------+
| 7 | trainer_state.json | 0.00 MB |
+---------+--------------------+------------+
| 8 | rng_state.pth | 0.01 MB |
+---------+--------------------+------------+ - [multilabel_classify.py:2115:_save]
2025-06-05 15:05:19,082 - INFO -
[36m🚂 Training Metrics (Step 40) 🚂
+---------------+----------+
| Metric | Value |
+===============+==========+
| loss | 0.1096 |
+---------------+----------+
| grad_norm | 0.465592 |
+---------------+----------+
| learning_rate | 8e-06 |
+---------------+----------+
| epoch | 2.22535 |
+---------------+----------+[0m - [multilabel_classify.py:1836:on_log]
2025-06-05 15:05:37,209 - INFO -
[36m🚂 Training Metrics (Step 50) 🚂
+---------------+----------+
| Metric | Value |
+===============+==========+
| loss | 0.1092 |
+---------------+----------+
| grad_norm | 0.099644 |
+---------------+----------+
| learning_rate | 1e-05 |
+---------------+----------+
| epoch | 2.78873 |
+---------------+----------+[0m - [multilabel_classify.py:1836:on_log]
2025-06-05 15:05:43,993 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [multilabel_classify.py:2000:evaluate]
2025-06-05 15:06:19,081 - INFO -
[33m🔍 Evaluation Metrics 🔍
+-------------------------------+----------+
| Metric | Value |
+===============================+==========+
| eval_f1_micro | 0 |
+-------------------------------+----------+
| eval_f1_macro | 0 |
+-------------------------------+----------+
| eval_precision_at_5 | 0.116176 |
+-------------------------------+----------+
| eval_recall_at_5 | 0.039057 |
+-------------------------------+----------+
| eval_precision_at_8 | 0.100184 |
+-------------------------------+----------+
| eval_recall_at_8 | 0.059546 |
+-------------------------------+----------+
| eval_precision_at_15 | 0.081373 |
+-------------------------------+----------+
| eval_recall_at_15 | 0.089004 |
+-------------------------------+----------+
| eval_rare_f1_micro | 0 |
+-------------------------------+----------+
| eval_rare_f1_macro | 0 |
+-------------------------------+----------+
| eval_rare_precision | 0 |
+-------------------------------+----------+
| eval_rare_recall | 0 |
+-------------------------------+----------+
| eval_rare_precision_at_5 | 0.060294 |
+-------------------------------+----------+
| eval_rare_recall_at_5 | 0.020816 |
+-------------------------------+----------+
| eval_rare_precision_at_8 | 0.057904 |
+-------------------------------+----------+
| eval_rare_recall_at_8 | 0.033152 |
+-------------------------------+----------+
| eval_rare_precision_at_15 | 0.056373 |
+-------------------------------+----------+
| eval_rare_recall_at_15 | 0.059526 |
+-------------------------------+----------+
| eval_not_rare_f1_micro | 0.595588 |
+-------------------------------+----------+
| eval_not_rare_f1_macro | 0.373272 |
+-------------------------------+----------+
| eval_not_rare_precision | 0.595588 |
+-------------------------------+----------+
| eval_not_rare_recall | 0.595588 |
+-------------------------------+----------+
| eval_not_rare_precision_at_5 | 0.080882 |
+-------------------------------+----------+
| eval_not_rare_recall_at_5 | 0.404412 |
+-------------------------------+----------+
| eval_not_rare_precision_at_8 | 0.050551 |
+-------------------------------+----------+
| eval_not_rare_recall_at_8 | 0.404412 |
+-------------------------------+----------+
| eval_not_rare_precision_at_15 | 0.026961 |
+-------------------------------+----------+
| eval_not_rare_recall_at_15 | 0.404412 |
+-------------------------------+----------+
| eval_loss | 0.106887 |
+-------------------------------+----------+[0m - [multilabel_classify.py:1855:on_evaluate]
2025-06-05 15:06:22,738 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-54 - [multilabel_classify.py:2093:_save]
2025-06-05 15:06:22,739 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-54 - [multilabel_classify.py:2098:_save]
2025-06-05 15:06:22,740 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-54:
+---------+--------------------+------------+
| Index | Saved File | Size |
+=========+====================+============+
| 1 | training_args.bin | 0.01 MB |
+---------+--------------------+------------+
| 2 | optimizer.pt | 642.30 MB |
+---------+--------------------+------------+
| 3 | model.safetensors | 4267.74 MB |
+---------+--------------------+------------+
| 4 | scaler.pt | 0.00 MB |
+---------+--------------------+------------+
| 5 | config.json | 0.00 MB |
+---------+--------------------+------------+
| 6 | scheduler.pt | 0.00 MB |
+---------+--------------------+------------+
| 7 | trainer_state.json | 0.01 MB |
+---------+--------------------+------------+
| 8 | rng_state.pth | 0.01 MB |
+---------+--------------------+------------+ - [multilabel_classify.py:2115:_save]
2025-06-05 15:06:36,356 - INFO -
[36m🚂 Training Metrics (Step 60) 🚂
+---------------+----------+
| Metric | Value |
+===============+==========+
| loss | 0.1033 |
+---------------+----------+
| grad_norm | 0.216208 |
+---------------+----------+
| learning_rate | 1.2e-05 |
+---------------+----------+
| epoch | 3.33803 |
+---------------+----------+[0m - [multilabel_classify.py:1836:on_log]
2025-06-05 15:06:54,505 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-68 - [multilabel_classify.py:2093:_save]
2025-06-05 15:06:54,507 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-68 - [multilabel_classify.py:2098:_save]
2025-06-05 15:06:54,508 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-68:
+---------+--------------------+------------+
| Index | Saved File | Size |
+=========+====================+============+
| 1 | training_args.bin | 0.01 MB |
+---------+--------------------+------------+
| 2 | optimizer.pt | 642.30 MB |
+---------+--------------------+------------+
| 3 | model.safetensors | 4267.74 MB |
+---------+--------------------+------------+
| 4 | scaler.pt | 0.00 MB |
+---------+--------------------+------------+
| 5 | config.json | 0.00 MB |
+---------+--------------------+------------+
| 6 | scheduler.pt | 0.00 MB |
+---------+--------------------+------------+
| 7 | trainer_state.json | 0.01 MB |
+---------+--------------------+------------+
| 8 | rng_state.pth | 0.01 MB |
+---------+--------------------+------------+ - [multilabel_classify.py:2115:_save]
2025-06-05 15:06:54,897 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [multilabel_classify.py:2000:evaluate]
2025-06-05 15:07:30,167 - INFO -
[33m🔍 Evaluation Metrics 🔍
+-------------------------------+----------+
| Metric | Value |
+===============================+==========+
| eval_f1_micro | 0 |
+-------------------------------+----------+
| eval_f1_macro | 0 |
+-------------------------------+----------+
| eval_precision_at_5 | 0.227941 |
+-------------------------------+----------+
| eval_recall_at_5 | 0.094901 |
+-------------------------------+----------+
| eval_precision_at_8 | 0.16636 |
+-------------------------------+----------+
| eval_recall_at_8 | 0.103783 |
+-------------------------------+----------+
| eval_precision_at_15 | 0.113725 |
+-------------------------------+----------+
| eval_recall_at_15 | 0.128501 |
+-------------------------------+----------+
| eval_rare_f1_micro | 0 |
+-------------------------------+----------+
| eval_rare_f1_macro | 0 |
+-------------------------------+----------+
| eval_rare_precision | 0 |
+-------------------------------+----------+
| eval_rare_recall | 0 |
+-------------------------------+----------+
| eval_rare_precision_at_5 | 0.15 |
+-------------------------------+----------+
| eval_rare_recall_at_5 | 0.06448 |
+-------------------------------+----------+
| eval_rare_precision_at_8 | 0.120404 |
+-------------------------------+----------+
| eval_rare_recall_at_8 | 0.078831 |
+-------------------------------+----------+
| eval_rare_precision_at_15 | 0.087255 |
+-------------------------------+----------+
| eval_rare_recall_at_15 | 0.099736 |
+-------------------------------+----------+
| eval_not_rare_f1_micro | 0.595588 |
+-------------------------------+----------+
| eval_not_rare_f1_macro | 0.373272 |
+-------------------------------+----------+
| eval_not_rare_precision | 0.595588 |
+-------------------------------+----------+
| eval_not_rare_recall | 0.595588 |
+-------------------------------+----------+
| eval_not_rare_precision_at_5 | 0.080882 |
+-------------------------------+----------+
| eval_not_rare_recall_at_5 | 0.404412 |
+-------------------------------+----------+
| eval_not_rare_precision_at_8 | 0.050551 |
+-------------------------------+----------+
| eval_not_rare_recall_at_8 | 0.404412 |
+-------------------------------+----------+
| eval_not_rare_precision_at_15 | 0.026961 |
+-------------------------------+----------+
| eval_not_rare_recall_at_15 | 0.404412 |
+-------------------------------+----------+
| eval_loss | 0.104832 |
+-------------------------------+----------+[0m - [multilabel_classify.py:1855:on_evaluate]
2025-06-05 15:07:33,859 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-68 - [multilabel_classify.py:2093:_save]
2025-06-05 15:07:33,860 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-68 - [multilabel_classify.py:2098:_save]
2025-06-05 15:07:33,862 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-68:
+---------+--------------------+------------+
| Index | Saved File | Size |
+=========+====================+============+
| 1 | training_args.bin | 0.01 MB |
+---------+--------------------+------------+
| 2 | optimizer.pt | 642.30 MB |
+---------+--------------------+------------+
| 3 | model.safetensors | 4267.74 MB |
+---------+--------------------+------------+
| 4 | scaler.pt | 0.00 MB |
+---------+--------------------+------------+
| 5 | config.json | 0.00 MB |
+---------+--------------------+------------+
| 6 | scheduler.pt | 0.00 MB |
+---------+--------------------+------------+
| 7 | trainer_state.json | 0.01 MB |
+---------+--------------------+------------+
| 8 | rng_state.pth | 0.01 MB |
+---------+--------------------+------------+ - [multilabel_classify.py:2115:_save]
2025-06-05 15:07:34,327 - INFO - 📂 Loading best model from ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-68 - [multilabel_classify.py:2167:_load_best_model]
2025-06-05 15:07:34,327 - INFO - 🖥️ Model is on device: cuda:0 - [multilabel_classify.py:2177:_load_best_model]
2025-06-05 15:07:34,399 - INFO - 🔑 Key order comparison:
+---------+--------------------------------------------+--------------------------------------------------------------------------------------+
| Index | Saved state_dict Keys | Model state_dict Keys |
+=========+============================================+======================================================================================+
| 1 | attention.in_proj_bias | boost_mul |
+---------+--------------------------------------------+--------------------------------------------------------------------------------------+
| 2 | attention.in_proj_weight | boost_add |
+---------+--------------------------------------------+--------------------------------------------------------------------------------------+
| 3 | attention.out_proj.bias | base_model.base_model.model.model.embed_tokens.weight |
+---------+--------------------------------------------+--------------------------------------------------------------------------------------+
| 4 | attention.out_proj.weight | base_model.base_model.model.model.layers.0.self_attn.q_proj.base_layer.weight |
+---------+--------------------------------------------+--------------------------------------------------------------------------------------+
| 5 | base_model.base_model.model.lm_head.weight | base_model.base_model.model.model.layers.0.self_attn.q_proj.base_layer.weight.absmax |
+---------+--------------------------------------------+--------------------------------------------------------------------------------------+ - [multilabel_classify.py:2201:_load_best_model]
2025-06-05 15:07:35,427 - INFO - ✅ Loaded best model weights from ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/checkpoint-68/model.safetensors - [multilabel_classify.py:2218:_load_best_model]
2025-06-05 15:07:35,452 - INFO - ✔️ Weight for boost_mul matches between saved and loaded state_dict - [multilabel_classify.py:2230:_load_best_model]
2025-06-05 15:07:35,475 - INFO - ✔️ Weight for boost_add matches between saved and loaded state_dict - [multilabel_classify.py:2230:_load_best_model]
2025-06-05 15:07:35,490 - INFO -
[36m🚂 Training Metrics (Step 68) 🚂
+--------------------------+----------+
| Metric | Value |
+==========================+==========+
| train_runtime | 292.721 |
+--------------------------+----------+
| train_samples_per_second | 7.748 |
+--------------------------+----------+
| train_steps_per_second | 0.232 |
+--------------------------+----------+
| total_flos | 0 |
+--------------------------+----------+
| train_loss | 0.222837 |
+--------------------------+----------+
| epoch | 3.78873 |
+--------------------------+----------+[0m - [multilabel_classify.py:1836:on_log]
2025-06-05 15:07:35,490 - INFO - ✨ Training Completed! ✨ - [multilabel_classify.py:1709:on_train_end]
2025-06-05 15:07:35,559 - INFO - 📊 Training loss plot saved as '../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/train_loss_plot.png' - [multilabel_classify.py:1905:on_train_end]
2025-06-05 15:07:35,619 - INFO - 📊 Evaluation loss plot saved as '../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/eval_loss_plot.png' - [multilabel_classify.py:1919:on_train_end]
2025-06-05 15:07:35,680 - INFO - 📊 Evaluation metric plot saved as '../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b/eval_precision_at_15_plot.png' - [multilabel_classify.py:1940:on_train_end]
2025-06-05 15:07:35,680 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:100:log_section]
2025-06-05 15:07:35,680 - INFO - + ✨ MODEL SAVING + - [multilabel_classify.py:101:log_section]
2025-06-05 15:07:35,680 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [multilabel_classify.py:104:log_section]
2025-06-05 15:07:35,680 - INFO - 💾 Saving trained model and pushing to Hugging Face Hub... - [multilabel_classify.py:3706:main]
2025-06-05 15:07:35,680 - INFO - 📁 Creating/using output directory: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2693:save_and_push]
2025-06-05 15:07:39,183 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2093:_save]
2025-06-05 15:07:39,184 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2098:_save]
2025-06-05 15:07:39,186 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b:
+---------+--------------------------------------------+------------+
| Index | Saved File | Size |
+=========+============================================+============+
| 1 | eval_loss_plot.png | 0.03 MB |
+---------+--------------------------------------------+------------+
| 2 | training_args.bin | 0.01 MB |
+---------+--------------------------------------------+------------+
| 3 | tokenizer.model | 0.56 MB |
+---------+--------------------------------------------+------------+
| 4 | tokenizer.json | 3.50 MB |
+---------+--------------------------------------------+------------+
| 5 | model.safetensors | 4267.74 MB |
+---------+--------------------------------------------+------------+
| 6 | config.json | 0.00 MB |
+---------+--------------------------------------------+------------+
| 7 | special_tokens_map.json | 0.00 MB |
+---------+--------------------------------------------+------------+
| 8 | tokenizer_config.json | 0.13 MB |
+---------+--------------------------------------------+------------+
| 9 | train_loss_plot.png | 0.02 MB |
+---------+--------------------------------------------+------------+
| 10 | eval_precision_at_15_plot.png | 0.03 MB |
+---------+--------------------------------------------+------------+
| 11 | README.md | 0.01 MB |
+---------+--------------------------------------------+------------+
| 12 | classification_log_2025-06-05_14-33-04.log | 0.04 MB |
+---------+--------------------------------------------+------------+ - [multilabel_classify.py:2115:_save]
2025-06-05 15:07:42,412 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2093:_save]
2025-06-05 15:07:42,413 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2098:_save]
2025-06-05 15:07:42,415 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b:
+---------+--------------------------------------------+------------+
| Index | Saved File | Size |
+=========+============================================+============+
| 1 | eval_loss_plot.png | 0.03 MB |
+---------+--------------------------------------------+------------+
| 2 | training_args.bin | 0.01 MB |
+---------+--------------------------------------------+------------+
| 3 | tokenizer.model | 0.56 MB |
+---------+--------------------------------------------+------------+
| 4 | tokenizer.json | 3.50 MB |
+---------+--------------------------------------------+------------+
| 5 | model.safetensors | 4267.74 MB |
+---------+--------------------------------------------+------------+
| 6 | config.json | 0.00 MB |
+---------+--------------------------------------------+------------+
| 7 | special_tokens_map.json | 0.00 MB |
+---------+--------------------------------------------+------------+
| 8 | tokenizer_config.json | 0.13 MB |
+---------+--------------------------------------------+------------+
| 9 | train_loss_plot.png | 0.02 MB |
+---------+--------------------------------------------+------------+
| 10 | eval_precision_at_15_plot.png | 0.03 MB |
+---------+--------------------------------------------+------------+
| 11 | README.md | 0.01 MB |
+---------+--------------------------------------------+------------+
| 12 | classification_log_2025-06-05_14-33-04.log | 0.04 MB |
+---------+--------------------------------------------+------------+ - [multilabel_classify.py:2115:_save]
2025-06-05 15:09:03,581 - INFO - 💾 Model saved to: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2697:save_and_push]
2025-06-05 15:09:03,611 - INFO - 🖌️ Tokenizer saved to: ../tmp/MIMIC4_DEMO/mimic4_classify_mistral7b - [multilabel_classify.py:2701:save_and_push]
|