Commit
·
539447a
1
Parent(s):
8d53a12
Upload 8 files
Browse files- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +295 -3
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 995641861
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0665fe7d442f8bbba1ae059bff6270660242a07678e0703e7514cb19706073e0
|
| 3 |
size 995641861
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 497807197
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b013aed3f4a82aeebcba3e970e376727406e6a2ed7078b6b88a510efdcc8f6e2
|
| 3 |
size 497807197
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f6cf74835c1af9f9e3dc4bcfbc0eae1e84048401ffb87d26ff318411e17c02d
|
| 3 |
size 14575
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:381b4f1af09e750b9ce29da1e140136f186310be59fcc0dc325e00c9f5f3a3d0
|
| 3 |
size 627
|
trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -439,13 +439,305 @@
|
|
| 439 |
"eval_samples_per_second": 41.687,
|
| 440 |
"eval_steps_per_second": 5.211,
|
| 441 |
"step": 34431
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 442 |
}
|
| 443 |
],
|
| 444 |
"logging_steps": 500,
|
| 445 |
"max_steps": 91816,
|
| 446 |
"num_train_epochs": 8,
|
| 447 |
"save_steps": 500,
|
| 448 |
-
"total_flos":
|
| 449 |
"trial_name": null,
|
| 450 |
"trial_params": null
|
| 451 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 57385,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 439 |
"eval_samples_per_second": 41.687,
|
| 440 |
"eval_steps_per_second": 5.211,
|
| 441 |
"step": 34431
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 3.01,
|
| 445 |
+
"learning_rate": 6.24248496993988e-06,
|
| 446 |
+
"loss": 1.5506,
|
| 447 |
+
"step": 34500
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 3.05,
|
| 451 |
+
"learning_rate": 6.188028230373791e-06,
|
| 452 |
+
"loss": 1.559,
|
| 453 |
+
"step": 35000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 3.09,
|
| 457 |
+
"learning_rate": 6.133571490807702e-06,
|
| 458 |
+
"loss": 1.5388,
|
| 459 |
+
"step": 35500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 3.14,
|
| 463 |
+
"learning_rate": 6.079114751241613e-06,
|
| 464 |
+
"loss": 1.5467,
|
| 465 |
+
"step": 36000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 3.18,
|
| 469 |
+
"learning_rate": 6.024658011675526e-06,
|
| 470 |
+
"loss": 1.5391,
|
| 471 |
+
"step": 36500
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 3.22,
|
| 475 |
+
"learning_rate": 5.970201272109437e-06,
|
| 476 |
+
"loss": 1.5364,
|
| 477 |
+
"step": 37000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 3.27,
|
| 481 |
+
"learning_rate": 5.915744532543348e-06,
|
| 482 |
+
"loss": 1.5376,
|
| 483 |
+
"step": 37500
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 3.31,
|
| 487 |
+
"learning_rate": 5.861287792977259e-06,
|
| 488 |
+
"loss": 1.5397,
|
| 489 |
+
"step": 38000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 3.35,
|
| 493 |
+
"learning_rate": 5.806831053411171e-06,
|
| 494 |
+
"loss": 1.5336,
|
| 495 |
+
"step": 38500
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 3.4,
|
| 499 |
+
"learning_rate": 5.752374313845082e-06,
|
| 500 |
+
"loss": 1.5378,
|
| 501 |
+
"step": 39000
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 3.44,
|
| 505 |
+
"learning_rate": 5.697917574278993e-06,
|
| 506 |
+
"loss": 1.5318,
|
| 507 |
+
"step": 39500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 3.49,
|
| 511 |
+
"learning_rate": 5.643460834712905e-06,
|
| 512 |
+
"loss": 1.5252,
|
| 513 |
+
"step": 40000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 3.53,
|
| 517 |
+
"learning_rate": 5.589004095146816e-06,
|
| 518 |
+
"loss": 1.5333,
|
| 519 |
+
"step": 40500
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 3.57,
|
| 523 |
+
"learning_rate": 5.5345473555807275e-06,
|
| 524 |
+
"loss": 1.5299,
|
| 525 |
+
"step": 41000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 3.62,
|
| 529 |
+
"learning_rate": 5.4800906160146385e-06,
|
| 530 |
+
"loss": 1.5215,
|
| 531 |
+
"step": 41500
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 3.66,
|
| 535 |
+
"learning_rate": 5.4256338764485495e-06,
|
| 536 |
+
"loss": 1.52,
|
| 537 |
+
"step": 42000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 3.7,
|
| 541 |
+
"learning_rate": 5.3711771368824605e-06,
|
| 542 |
+
"loss": 1.5258,
|
| 543 |
+
"step": 42500
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 3.75,
|
| 547 |
+
"learning_rate": 5.316720397316373e-06,
|
| 548 |
+
"loss": 1.5256,
|
| 549 |
+
"step": 43000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 3.79,
|
| 553 |
+
"learning_rate": 5.262263657750284e-06,
|
| 554 |
+
"loss": 1.5205,
|
| 555 |
+
"step": 43500
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 3.83,
|
| 559 |
+
"learning_rate": 5.207806918184195e-06,
|
| 560 |
+
"loss": 1.5236,
|
| 561 |
+
"step": 44000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 3.88,
|
| 565 |
+
"learning_rate": 5.153350178618106e-06,
|
| 566 |
+
"loss": 1.5281,
|
| 567 |
+
"step": 44500
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 3.92,
|
| 571 |
+
"learning_rate": 5.098893439052017e-06,
|
| 572 |
+
"loss": 1.5175,
|
| 573 |
+
"step": 45000
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 3.96,
|
| 577 |
+
"learning_rate": 5.044436699485928e-06,
|
| 578 |
+
"loss": 1.5215,
|
| 579 |
+
"step": 45500
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 4.0,
|
| 583 |
+
"eval_loss": 1.5107132196426392,
|
| 584 |
+
"eval_runtime": 3.2672,
|
| 585 |
+
"eval_samples_per_second": 41.625,
|
| 586 |
+
"eval_steps_per_second": 5.203,
|
| 587 |
+
"step": 45908
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 4.01,
|
| 591 |
+
"learning_rate": 4.98997995991984e-06,
|
| 592 |
+
"loss": 1.5202,
|
| 593 |
+
"step": 46000
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 4.05,
|
| 597 |
+
"learning_rate": 4.935523220353751e-06,
|
| 598 |
+
"loss": 1.5136,
|
| 599 |
+
"step": 46500
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 4.1,
|
| 603 |
+
"learning_rate": 4.881066480787663e-06,
|
| 604 |
+
"loss": 1.5119,
|
| 605 |
+
"step": 47000
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 4.14,
|
| 609 |
+
"learning_rate": 4.826609741221574e-06,
|
| 610 |
+
"loss": 1.5052,
|
| 611 |
+
"step": 47500
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 4.18,
|
| 615 |
+
"learning_rate": 4.772153001655485e-06,
|
| 616 |
+
"loss": 1.5088,
|
| 617 |
+
"step": 48000
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 4.23,
|
| 621 |
+
"learning_rate": 4.717696262089397e-06,
|
| 622 |
+
"loss": 1.5078,
|
| 623 |
+
"step": 48500
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 4.27,
|
| 627 |
+
"learning_rate": 4.663239522523308e-06,
|
| 628 |
+
"loss": 1.5099,
|
| 629 |
+
"step": 49000
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 4.31,
|
| 633 |
+
"learning_rate": 4.608782782957219e-06,
|
| 634 |
+
"loss": 1.5098,
|
| 635 |
+
"step": 49500
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 4.36,
|
| 639 |
+
"learning_rate": 4.5543260433911305e-06,
|
| 640 |
+
"loss": 1.5044,
|
| 641 |
+
"step": 50000
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 4.4,
|
| 645 |
+
"learning_rate": 4.4998693038250415e-06,
|
| 646 |
+
"loss": 1.5049,
|
| 647 |
+
"step": 50500
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 4.44,
|
| 651 |
+
"learning_rate": 4.445412564258953e-06,
|
| 652 |
+
"loss": 1.4958,
|
| 653 |
+
"step": 51000
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 4.49,
|
| 657 |
+
"learning_rate": 4.390955824692864e-06,
|
| 658 |
+
"loss": 1.5073,
|
| 659 |
+
"step": 51500
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 4.53,
|
| 663 |
+
"learning_rate": 4.336499085126776e-06,
|
| 664 |
+
"loss": 1.5015,
|
| 665 |
+
"step": 52000
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 4.57,
|
| 669 |
+
"learning_rate": 4.282042345560687e-06,
|
| 670 |
+
"loss": 1.5022,
|
| 671 |
+
"step": 52500
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 4.62,
|
| 675 |
+
"learning_rate": 4.227585605994598e-06,
|
| 676 |
+
"loss": 1.4973,
|
| 677 |
+
"step": 53000
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 4.66,
|
| 681 |
+
"learning_rate": 4.17312886642851e-06,
|
| 682 |
+
"loss": 1.4944,
|
| 683 |
+
"step": 53500
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 4.71,
|
| 687 |
+
"learning_rate": 4.118672126862421e-06,
|
| 688 |
+
"loss": 1.5024,
|
| 689 |
+
"step": 54000
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 4.75,
|
| 693 |
+
"learning_rate": 4.064215387296332e-06,
|
| 694 |
+
"loss": 1.4981,
|
| 695 |
+
"step": 54500
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 4.79,
|
| 699 |
+
"learning_rate": 4.009758647730244e-06,
|
| 700 |
+
"loss": 1.4942,
|
| 701 |
+
"step": 55000
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 4.84,
|
| 705 |
+
"learning_rate": 3.955301908164155e-06,
|
| 706 |
+
"loss": 1.4964,
|
| 707 |
+
"step": 55500
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 4.88,
|
| 711 |
+
"learning_rate": 3.900845168598066e-06,
|
| 712 |
+
"loss": 1.4995,
|
| 713 |
+
"step": 56000
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 4.92,
|
| 717 |
+
"learning_rate": 3.846388429031978e-06,
|
| 718 |
+
"loss": 1.4959,
|
| 719 |
+
"step": 56500
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 4.97,
|
| 723 |
+
"learning_rate": 3.7919316894658886e-06,
|
| 724 |
+
"loss": 1.4922,
|
| 725 |
+
"step": 57000
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 5.0,
|
| 729 |
+
"eval_loss": 1.4904537200927734,
|
| 730 |
+
"eval_runtime": 3.2628,
|
| 731 |
+
"eval_samples_per_second": 41.682,
|
| 732 |
+
"eval_steps_per_second": 5.21,
|
| 733 |
+
"step": 57385
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 500,
|
| 737 |
"max_steps": 91816,
|
| 738 |
"num_train_epochs": 8,
|
| 739 |
"save_steps": 500,
|
| 740 |
+
"total_flos": 8.99595804672e+16,
|
| 741 |
"trial_name": null,
|
| 742 |
"trial_params": null
|
| 743 |
}
|