Training in progress, step 1000, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5323528
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c53e59c2bd584a2174d8768ace772b5d5796aa08166aa25302904cb3a665ff7
|
| 3 |
size 5323528
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 10707706
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ed95370d354bc8f635abaa3992f7d5d462b1bcb514428235550ba0f48b08b85
|
| 3 |
size 10707706
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa5f9b3cb2653c573d5d70e945ac9e78ff4b3999c649bc26690d113787889e70
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74be72e979aeba041a40f5740c89e95223a2d1671e242dd571b2005ebd09a8c1
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "bart_lora_outputs\\checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 100,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -347,13 +347,353 @@
|
|
| 347 |
"eval_samples_per_second": 190.861,
|
| 348 |
"eval_steps_per_second": 23.96,
|
| 349 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 350 |
}
|
| 351 |
],
|
| 352 |
"logging_steps": 10,
|
| 353 |
"max_steps": 6130,
|
| 354 |
"num_train_epochs": 10,
|
| 355 |
"save_steps": 500,
|
| 356 |
-
"total_flos":
|
| 357 |
"trial_name": null,
|
| 358 |
"trial_params": null
|
| 359 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.48665139079093933,
|
| 3 |
+
"best_model_checkpoint": "bart_lora_outputs\\checkpoint-1000",
|
| 4 |
+
"epoch": 1.631321370309951,
|
| 5 |
"eval_steps": 100,
|
| 6 |
+
"global_step": 1000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 347 |
"eval_samples_per_second": 190.861,
|
| 348 |
"eval_steps_per_second": 23.96,
|
| 349 |
"step": 500
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.83,
|
| 353 |
+
"learning_rate": 0.0009982238010657195,
|
| 354 |
+
"loss": 0.6725,
|
| 355 |
+
"step": 510
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 0.85,
|
| 359 |
+
"learning_rate": 0.0009964476021314388,
|
| 360 |
+
"loss": 0.6612,
|
| 361 |
+
"step": 520
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.86,
|
| 365 |
+
"learning_rate": 0.000994671403197158,
|
| 366 |
+
"loss": 0.6202,
|
| 367 |
+
"step": 530
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.88,
|
| 371 |
+
"learning_rate": 0.0009928952042628776,
|
| 372 |
+
"loss": 0.6085,
|
| 373 |
+
"step": 540
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.9,
|
| 377 |
+
"learning_rate": 0.0009911190053285969,
|
| 378 |
+
"loss": 0.6023,
|
| 379 |
+
"step": 550
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 0.91,
|
| 383 |
+
"learning_rate": 0.0009893428063943162,
|
| 384 |
+
"loss": 0.6209,
|
| 385 |
+
"step": 560
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.93,
|
| 389 |
+
"learning_rate": 0.0009875666074600357,
|
| 390 |
+
"loss": 0.6128,
|
| 391 |
+
"step": 570
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 0.95,
|
| 395 |
+
"learning_rate": 0.000985790408525755,
|
| 396 |
+
"loss": 0.5971,
|
| 397 |
+
"step": 580
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.96,
|
| 401 |
+
"learning_rate": 0.0009840142095914742,
|
| 402 |
+
"loss": 0.6028,
|
| 403 |
+
"step": 590
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.98,
|
| 407 |
+
"learning_rate": 0.0009822380106571937,
|
| 408 |
+
"loss": 0.6105,
|
| 409 |
+
"step": 600
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.98,
|
| 413 |
+
"eval_loss": 0.527148425579071,
|
| 414 |
+
"eval_runtime": 6.0982,
|
| 415 |
+
"eval_samples_per_second": 192.024,
|
| 416 |
+
"eval_steps_per_second": 24.105,
|
| 417 |
+
"step": 600
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.0,
|
| 421 |
+
"learning_rate": 0.000980461811722913,
|
| 422 |
+
"loss": 0.6101,
|
| 423 |
+
"step": 610
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.01,
|
| 427 |
+
"learning_rate": 0.0009786856127886323,
|
| 428 |
+
"loss": 0.5349,
|
| 429 |
+
"step": 620
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.03,
|
| 433 |
+
"learning_rate": 0.0009769094138543518,
|
| 434 |
+
"loss": 0.5903,
|
| 435 |
+
"step": 630
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 1.04,
|
| 439 |
+
"learning_rate": 0.0009751332149200711,
|
| 440 |
+
"loss": 0.6033,
|
| 441 |
+
"step": 640
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.06,
|
| 445 |
+
"learning_rate": 0.0009733570159857904,
|
| 446 |
+
"loss": 0.544,
|
| 447 |
+
"step": 650
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 1.08,
|
| 451 |
+
"learning_rate": 0.0009715808170515098,
|
| 452 |
+
"loss": 0.5582,
|
| 453 |
+
"step": 660
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.09,
|
| 457 |
+
"learning_rate": 0.0009698046181172292,
|
| 458 |
+
"loss": 0.5488,
|
| 459 |
+
"step": 670
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.11,
|
| 463 |
+
"learning_rate": 0.0009680284191829485,
|
| 464 |
+
"loss": 0.5799,
|
| 465 |
+
"step": 680
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.13,
|
| 469 |
+
"learning_rate": 0.0009662522202486678,
|
| 470 |
+
"loss": 0.5857,
|
| 471 |
+
"step": 690
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.14,
|
| 475 |
+
"learning_rate": 0.0009644760213143872,
|
| 476 |
+
"loss": 0.5857,
|
| 477 |
+
"step": 700
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 1.14,
|
| 481 |
+
"eval_loss": 0.5239382982254028,
|
| 482 |
+
"eval_runtime": 6.2471,
|
| 483 |
+
"eval_samples_per_second": 187.448,
|
| 484 |
+
"eval_steps_per_second": 23.531,
|
| 485 |
+
"step": 700
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.16,
|
| 489 |
+
"learning_rate": 0.0009626998223801065,
|
| 490 |
+
"loss": 0.5289,
|
| 491 |
+
"step": 710
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 1.17,
|
| 495 |
+
"learning_rate": 0.0009609236234458259,
|
| 496 |
+
"loss": 0.6082,
|
| 497 |
+
"step": 720
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 1.19,
|
| 501 |
+
"learning_rate": 0.0009591474245115453,
|
| 502 |
+
"loss": 0.5837,
|
| 503 |
+
"step": 730
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 1.21,
|
| 507 |
+
"learning_rate": 0.0009573712255772646,
|
| 508 |
+
"loss": 0.5571,
|
| 509 |
+
"step": 740
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.22,
|
| 513 |
+
"learning_rate": 0.000955595026642984,
|
| 514 |
+
"loss": 0.5948,
|
| 515 |
+
"step": 750
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.24,
|
| 519 |
+
"learning_rate": 0.0009538188277087034,
|
| 520 |
+
"loss": 0.5455,
|
| 521 |
+
"step": 760
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.26,
|
| 525 |
+
"learning_rate": 0.0009520426287744227,
|
| 526 |
+
"loss": 0.5858,
|
| 527 |
+
"step": 770
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.27,
|
| 531 |
+
"learning_rate": 0.0009502664298401421,
|
| 532 |
+
"loss": 0.5289,
|
| 533 |
+
"step": 780
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 1.29,
|
| 537 |
+
"learning_rate": 0.0009484902309058615,
|
| 538 |
+
"loss": 0.6011,
|
| 539 |
+
"step": 790
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 1.31,
|
| 543 |
+
"learning_rate": 0.0009467140319715807,
|
| 544 |
+
"loss": 0.5841,
|
| 545 |
+
"step": 800
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 1.31,
|
| 549 |
+
"eval_loss": 0.5005862712860107,
|
| 550 |
+
"eval_runtime": 5.9494,
|
| 551 |
+
"eval_samples_per_second": 196.827,
|
| 552 |
+
"eval_steps_per_second": 24.708,
|
| 553 |
+
"step": 800
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 1.32,
|
| 557 |
+
"learning_rate": 0.0009449378330373001,
|
| 558 |
+
"loss": 0.5403,
|
| 559 |
+
"step": 810
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 1.34,
|
| 563 |
+
"learning_rate": 0.0009431616341030196,
|
| 564 |
+
"loss": 0.558,
|
| 565 |
+
"step": 820
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 1.35,
|
| 569 |
+
"learning_rate": 0.0009413854351687389,
|
| 570 |
+
"loss": 0.5435,
|
| 571 |
+
"step": 830
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 1.37,
|
| 575 |
+
"learning_rate": 0.0009396092362344583,
|
| 576 |
+
"loss": 0.5341,
|
| 577 |
+
"step": 840
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.39,
|
| 581 |
+
"learning_rate": 0.0009378330373001777,
|
| 582 |
+
"loss": 0.5398,
|
| 583 |
+
"step": 850
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.4,
|
| 587 |
+
"learning_rate": 0.000936056838365897,
|
| 588 |
+
"loss": 0.5548,
|
| 589 |
+
"step": 860
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 1.42,
|
| 593 |
+
"learning_rate": 0.0009342806394316164,
|
| 594 |
+
"loss": 0.5438,
|
| 595 |
+
"step": 870
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 1.44,
|
| 599 |
+
"learning_rate": 0.0009325044404973358,
|
| 600 |
+
"loss": 0.5845,
|
| 601 |
+
"step": 880
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 1.45,
|
| 605 |
+
"learning_rate": 0.0009307282415630552,
|
| 606 |
+
"loss": 0.5146,
|
| 607 |
+
"step": 890
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 1.47,
|
| 611 |
+
"learning_rate": 0.0009289520426287745,
|
| 612 |
+
"loss": 0.5274,
|
| 613 |
+
"step": 900
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 1.47,
|
| 617 |
+
"eval_loss": 0.49163827300071716,
|
| 618 |
+
"eval_runtime": 6.0349,
|
| 619 |
+
"eval_samples_per_second": 194.04,
|
| 620 |
+
"eval_steps_per_second": 24.359,
|
| 621 |
+
"step": 900
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 1.48,
|
| 625 |
+
"learning_rate": 0.0009271758436944939,
|
| 626 |
+
"loss": 0.5999,
|
| 627 |
+
"step": 910
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 1.5,
|
| 631 |
+
"learning_rate": 0.0009253996447602132,
|
| 632 |
+
"loss": 0.5798,
|
| 633 |
+
"step": 920
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.52,
|
| 637 |
+
"learning_rate": 0.0009236234458259325,
|
| 638 |
+
"loss": 0.5465,
|
| 639 |
+
"step": 930
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.53,
|
| 643 |
+
"learning_rate": 0.0009218472468916519,
|
| 644 |
+
"loss": 0.5752,
|
| 645 |
+
"step": 940
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 1.55,
|
| 649 |
+
"learning_rate": 0.0009200710479573713,
|
| 650 |
+
"loss": 0.5544,
|
| 651 |
+
"step": 950
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 1.57,
|
| 655 |
+
"learning_rate": 0.0009182948490230906,
|
| 656 |
+
"loss": 0.5576,
|
| 657 |
+
"step": 960
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 1.58,
|
| 661 |
+
"learning_rate": 0.00091651865008881,
|
| 662 |
+
"loss": 0.5351,
|
| 663 |
+
"step": 970
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 1.6,
|
| 667 |
+
"learning_rate": 0.0009147424511545294,
|
| 668 |
+
"loss": 0.5584,
|
| 669 |
+
"step": 980
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 1.62,
|
| 673 |
+
"learning_rate": 0.0009129662522202487,
|
| 674 |
+
"loss": 0.5191,
|
| 675 |
+
"step": 990
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.63,
|
| 679 |
+
"learning_rate": 0.0009111900532859681,
|
| 680 |
+
"loss": 0.5304,
|
| 681 |
+
"step": 1000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.63,
|
| 685 |
+
"eval_loss": 0.48665139079093933,
|
| 686 |
+
"eval_runtime": 5.92,
|
| 687 |
+
"eval_samples_per_second": 197.803,
|
| 688 |
+
"eval_steps_per_second": 24.831,
|
| 689 |
+
"step": 1000
|
| 690 |
}
|
| 691 |
],
|
| 692 |
"logging_steps": 10,
|
| 693 |
"max_steps": 6130,
|
| 694 |
"num_train_epochs": 10,
|
| 695 |
"save_steps": 500,
|
| 696 |
+
"total_flos": 1883435087757312.0,
|
| 697 |
"trial_name": null,
|
| 698 |
"trial_params": null
|
| 699 |
}
|