Upload folder using huggingface_hub
Browse files- model.safetensors +1 -1
- optimizer.pt +3 -0
- rng_state.pth +0 -0
- scheduler.pt +0 -0
- trainer_state.json +283 -3
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1426462208
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:670944acbbf85d809895ecabf59d038c6a56eec83ecc7dbc2170456ff81fefa9
|
| 3 |
size 1426462208
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a89b33001d76783cd0c9e2e7bf2659d37c66658149ddb1c1250c7d8f9aa23e50
|
| 3 |
+
size 2853107898
|
rng_state.pth
CHANGED
|
Binary files a/rng_state.pth and b/rng_state.pth differ
|
|
|
scheduler.pt
CHANGED
|
Binary files a/scheduler.pt and b/scheduler.pt differ
|
|
|
trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 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,
|
|
@@ -427,6 +427,286 @@
|
|
| 427 |
"learning_rate": 3.601696495848285e-05,
|
| 428 |
"loss": 2.5301,
|
| 429 |
"step": 600000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 430 |
}
|
| 431 |
],
|
| 432 |
"logging_steps": 10000,
|
|
@@ -446,7 +726,7 @@
|
|
| 446 |
"attributes": {}
|
| 447 |
}
|
| 448 |
},
|
| 449 |
-
"total_flos":
|
| 450 |
"train_batch_size": 4,
|
| 451 |
"trial_name": null,
|
| 452 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.46627524414171784,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 1000000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 427 |
"learning_rate": 3.601696495848285e-05,
|
| 428 |
"loss": 2.5301,
|
| 429 |
"step": 600000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.2844278989264479,
|
| 433 |
+
"grad_norm": 0.9649547338485718,
|
| 434 |
+
"learning_rate": 3.578389727769861e-05,
|
| 435 |
+
"loss": 2.5304,
|
| 436 |
+
"step": 610000
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.28909065136786505,
|
| 440 |
+
"grad_norm": 1.0385549068450928,
|
| 441 |
+
"learning_rate": 3.5550876224438794e-05,
|
| 442 |
+
"loss": 2.5179,
|
| 443 |
+
"step": 620000
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.2937534038092822,
|
| 447 |
+
"grad_norm": 1.1167703866958618,
|
| 448 |
+
"learning_rate": 3.5317785229892346e-05,
|
| 449 |
+
"loss": 2.5168,
|
| 450 |
+
"step": 630000
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.2984161562506994,
|
| 454 |
+
"grad_norm": 0.8988041281700134,
|
| 455 |
+
"learning_rate": 3.508476417663252e-05,
|
| 456 |
+
"loss": 2.519,
|
| 457 |
+
"step": 640000
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.30307890869211657,
|
| 461 |
+
"grad_norm": 1.2292715311050415,
|
| 462 |
+
"learning_rate": 3.485169649584828e-05,
|
| 463 |
+
"loss": 2.5102,
|
| 464 |
+
"step": 650000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.3077416611335338,
|
| 468 |
+
"grad_norm": 0.9778872728347778,
|
| 469 |
+
"learning_rate": 3.4618652128826254e-05,
|
| 470 |
+
"loss": 2.5115,
|
| 471 |
+
"step": 660000
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.31240441357495097,
|
| 475 |
+
"grad_norm": 0.9290140271186829,
|
| 476 |
+
"learning_rate": 3.4385584448042016e-05,
|
| 477 |
+
"loss": 2.5068,
|
| 478 |
+
"step": 670000
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.31706716601636814,
|
| 482 |
+
"grad_norm": 0.8549484610557556,
|
| 483 |
+
"learning_rate": 3.415254008101999e-05,
|
| 484 |
+
"loss": 2.5045,
|
| 485 |
+
"step": 680000
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.3217299184577853,
|
| 489 |
+
"grad_norm": 0.9482207894325256,
|
| 490 |
+
"learning_rate": 3.391949571399796e-05,
|
| 491 |
+
"loss": 2.5002,
|
| 492 |
+
"step": 690000
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.3263926708992025,
|
| 496 |
+
"grad_norm": 0.9213985204696655,
|
| 497 |
+
"learning_rate": 3.368642803321372e-05,
|
| 498 |
+
"loss": 2.499,
|
| 499 |
+
"step": 700000
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.33105542334061966,
|
| 503 |
+
"grad_norm": 0.9165827631950378,
|
| 504 |
+
"learning_rate": 3.345338366619169e-05,
|
| 505 |
+
"loss": 2.4978,
|
| 506 |
+
"step": 710000
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.33571817578203683,
|
| 510 |
+
"grad_norm": 0.9712676405906677,
|
| 511 |
+
"learning_rate": 3.3220315985407453e-05,
|
| 512 |
+
"loss": 2.4923,
|
| 513 |
+
"step": 720000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.340380928223454,
|
| 517 |
+
"grad_norm": 0.9476392865180969,
|
| 518 |
+
"learning_rate": 3.2987271618385425e-05,
|
| 519 |
+
"loss": 2.4921,
|
| 520 |
+
"step": 730000
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.3450436806648712,
|
| 524 |
+
"grad_norm": 0.8675413727760315,
|
| 525 |
+
"learning_rate": 3.275422725136339e-05,
|
| 526 |
+
"loss": 2.4913,
|
| 527 |
+
"step": 740000
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.34970643310628835,
|
| 531 |
+
"grad_norm": 1.0163840055465698,
|
| 532 |
+
"learning_rate": 3.252115957057915e-05,
|
| 533 |
+
"loss": 2.4876,
|
| 534 |
+
"step": 750000
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.3543691855477056,
|
| 538 |
+
"grad_norm": 0.8246685862541199,
|
| 539 |
+
"learning_rate": 3.228809188979491e-05,
|
| 540 |
+
"loss": 2.4848,
|
| 541 |
+
"step": 760000
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.35903193798912275,
|
| 545 |
+
"grad_norm": 1.1230520009994507,
|
| 546 |
+
"learning_rate": 3.205507083653509e-05,
|
| 547 |
+
"loss": 2.4856,
|
| 548 |
+
"step": 770000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.3636946904305399,
|
| 552 |
+
"grad_norm": 1.0105488300323486,
|
| 553 |
+
"learning_rate": 3.182200315575085e-05,
|
| 554 |
+
"loss": 2.4815,
|
| 555 |
+
"step": 780000
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.3683574428719571,
|
| 559 |
+
"grad_norm": 1.0298407077789307,
|
| 560 |
+
"learning_rate": 3.158893547496662e-05,
|
| 561 |
+
"loss": 2.4801,
|
| 562 |
+
"step": 790000
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.37302019531337427,
|
| 566 |
+
"grad_norm": 1.1969521045684814,
|
| 567 |
+
"learning_rate": 3.135589110794458e-05,
|
| 568 |
+
"loss": 2.4776,
|
| 569 |
+
"step": 800000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.37768294775479144,
|
| 573 |
+
"grad_norm": 0.9831893444061279,
|
| 574 |
+
"learning_rate": 3.112287005468476e-05,
|
| 575 |
+
"loss": 2.4787,
|
| 576 |
+
"step": 810000
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.3823457001962086,
|
| 580 |
+
"grad_norm": 1.2115819454193115,
|
| 581 |
+
"learning_rate": 3.0889825687662735e-05,
|
| 582 |
+
"loss": 2.4721,
|
| 583 |
+
"step": 820000
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.3870084526376258,
|
| 587 |
+
"grad_norm": 1.0241882801055908,
|
| 588 |
+
"learning_rate": 3.06567813206407e-05,
|
| 589 |
+
"loss": 2.4714,
|
| 590 |
+
"step": 830000
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.39167120507904296,
|
| 594 |
+
"grad_norm": 1.0166583061218262,
|
| 595 |
+
"learning_rate": 3.042373695361867e-05,
|
| 596 |
+
"loss": 2.4736,
|
| 597 |
+
"step": 840000
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.39633395752046013,
|
| 601 |
+
"grad_norm": 0.9006229639053345,
|
| 602 |
+
"learning_rate": 3.0190645959072226e-05,
|
| 603 |
+
"loss": 2.4678,
|
| 604 |
+
"step": 850000
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.40099670996187736,
|
| 608 |
+
"grad_norm": 1.0126405954360962,
|
| 609 |
+
"learning_rate": 2.9957624905812404e-05,
|
| 610 |
+
"loss": 2.4651,
|
| 611 |
+
"step": 860000
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.40565946240329454,
|
| 615 |
+
"grad_norm": 1.3557987213134766,
|
| 616 |
+
"learning_rate": 2.972458053879037e-05,
|
| 617 |
+
"loss": 2.466,
|
| 618 |
+
"step": 870000
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.4103222148447117,
|
| 622 |
+
"grad_norm": 1.241245150566101,
|
| 623 |
+
"learning_rate": 2.9491559485530546e-05,
|
| 624 |
+
"loss": 2.4611,
|
| 625 |
+
"step": 880000
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.4149849672861289,
|
| 629 |
+
"grad_norm": 1.0998499393463135,
|
| 630 |
+
"learning_rate": 2.9258491804746315e-05,
|
| 631 |
+
"loss": 2.4618,
|
| 632 |
+
"step": 890000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.41964771972754605,
|
| 636 |
+
"grad_norm": 0.9139440655708313,
|
| 637 |
+
"learning_rate": 2.902544743772428e-05,
|
| 638 |
+
"loss": 2.461,
|
| 639 |
+
"step": 900000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.4243104721689632,
|
| 643 |
+
"grad_norm": 0.8467987179756165,
|
| 644 |
+
"learning_rate": 2.8792426384464453e-05,
|
| 645 |
+
"loss": 2.4584,
|
| 646 |
+
"step": 910000
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.4289732246103804,
|
| 650 |
+
"grad_norm": 1.090574860572815,
|
| 651 |
+
"learning_rate": 2.8559335389918012e-05,
|
| 652 |
+
"loss": 2.4567,
|
| 653 |
+
"step": 920000
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.43363597705179757,
|
| 657 |
+
"grad_norm": 1.063254714012146,
|
| 658 |
+
"learning_rate": 2.832629102289598e-05,
|
| 659 |
+
"loss": 2.4572,
|
| 660 |
+
"step": 930000
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.43829872949321474,
|
| 664 |
+
"grad_norm": 0.962209165096283,
|
| 665 |
+
"learning_rate": 2.8093223342111742e-05,
|
| 666 |
+
"loss": 2.4525,
|
| 667 |
+
"step": 940000
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.4429614819346319,
|
| 671 |
+
"grad_norm": 0.9544676542282104,
|
| 672 |
+
"learning_rate": 2.7860202288851923e-05,
|
| 673 |
+
"loss": 2.4518,
|
| 674 |
+
"step": 950000
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.44762423437604915,
|
| 678 |
+
"grad_norm": 1.0543245077133179,
|
| 679 |
+
"learning_rate": 2.7627134608067685e-05,
|
| 680 |
+
"loss": 2.4423,
|
| 681 |
+
"step": 960000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.4522869868174663,
|
| 685 |
+
"grad_norm": 1.1137259006500244,
|
| 686 |
+
"learning_rate": 2.7394066927283447e-05,
|
| 687 |
+
"loss": 2.445,
|
| 688 |
+
"step": 970000
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.4569497392588835,
|
| 692 |
+
"grad_norm": 0.8332359790802002,
|
| 693 |
+
"learning_rate": 2.716102256026141e-05,
|
| 694 |
+
"loss": 2.4483,
|
| 695 |
+
"step": 980000
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.46161249170030066,
|
| 699 |
+
"grad_norm": 0.9382948875427246,
|
| 700 |
+
"learning_rate": 2.6927954879477173e-05,
|
| 701 |
+
"loss": 2.4451,
|
| 702 |
+
"step": 990000
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.46627524414171784,
|
| 706 |
+
"grad_norm": 0.8949111700057983,
|
| 707 |
+
"learning_rate": 2.6694910512455145e-05,
|
| 708 |
+
"loss": 2.4431,
|
| 709 |
+
"step": 1000000
|
| 710 |
}
|
| 711 |
],
|
| 712 |
"logging_steps": 10000,
|
|
|
|
| 726 |
"attributes": {}
|
| 727 |
}
|
| 728 |
},
|
| 729 |
+
"total_flos": 2.4657896443479982e+19,
|
| 730 |
"train_batch_size": 4,
|
| 731 |
"trial_name": null,
|
| 732 |
"trial_params": null
|