Training in progress, step 600, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1540577008
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:299e14e199d99f2186b7062868e1a5691909e05241c4f4d12f8927273aa7c7f4
|
| 3 |
size 1540577008
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1695317131
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca229c2cf19b6a65b0f9ec8abfcb44b522c1caa75d6d8332038337af7197f5a8
|
| 3 |
size 1695317131
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06b6bed560ba82ad938724499dcd6b1144659f41214cf5bc1f5da6347e162b25
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca2b96950726cb5d1ecc220f8fe4a4ed97580d0d059753b7132b783c68be6714
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 150,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -446,6 +446,444 @@
|
|
| 446 |
"eval_samples_per_second": 10.074,
|
| 447 |
"eval_steps_per_second": 1.713,
|
| 448 |
"step": 300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 449 |
}
|
| 450 |
],
|
| 451 |
"logging_steps": 5,
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.12,
|
| 6 |
"eval_steps": 150,
|
| 7 |
+
"global_step": 600,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 446 |
"eval_samples_per_second": 10.074,
|
| 447 |
"eval_steps_per_second": 1.713,
|
| 448 |
"step": 300
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 0.061,
|
| 452 |
+
"grad_norm": 0.39879587292671204,
|
| 453 |
+
"learning_rate": 3.998724578066421e-06,
|
| 454 |
+
"loss": 8.460777282714844,
|
| 455 |
+
"step": 305
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 0.062,
|
| 459 |
+
"grad_norm": 0.39906880259513855,
|
| 460 |
+
"learning_rate": 3.998477485490638e-06,
|
| 461 |
+
"loss": 8.430789184570312,
|
| 462 |
+
"step": 310
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 0.063,
|
| 466 |
+
"grad_norm": 0.35292986035346985,
|
| 467 |
+
"learning_rate": 3.998208537885259e-06,
|
| 468 |
+
"loss": 8.430660247802734,
|
| 469 |
+
"step": 315
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 0.064,
|
| 473 |
+
"grad_norm": 0.346780002117157,
|
| 474 |
+
"learning_rate": 3.997917738191449e-06,
|
| 475 |
+
"loss": 8.45125732421875,
|
| 476 |
+
"step": 320
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 0.065,
|
| 480 |
+
"grad_norm": 0.5084764361381531,
|
| 481 |
+
"learning_rate": 3.99760508958935e-06,
|
| 482 |
+
"loss": 8.386634826660156,
|
| 483 |
+
"step": 325
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.066,
|
| 487 |
+
"grad_norm": 0.40600430965423584,
|
| 488 |
+
"learning_rate": 3.997270595498036e-06,
|
| 489 |
+
"loss": 8.341055297851563,
|
| 490 |
+
"step": 330
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.067,
|
| 494 |
+
"grad_norm": 0.34203389286994934,
|
| 495 |
+
"learning_rate": 3.99691425957548e-06,
|
| 496 |
+
"loss": 8.48632354736328,
|
| 497 |
+
"step": 335
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 0.068,
|
| 501 |
+
"grad_norm": 0.3634227514266968,
|
| 502 |
+
"learning_rate": 3.996536085718516e-06,
|
| 503 |
+
"loss": 8.400882720947266,
|
| 504 |
+
"step": 340
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.069,
|
| 508 |
+
"grad_norm": 0.33795344829559326,
|
| 509 |
+
"learning_rate": 3.996136078062792e-06,
|
| 510 |
+
"loss": 8.43860092163086,
|
| 511 |
+
"step": 345
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 0.07,
|
| 515 |
+
"grad_norm": 0.36207878589630127,
|
| 516 |
+
"learning_rate": 3.995714240982727e-06,
|
| 517 |
+
"loss": 8.418954467773437,
|
| 518 |
+
"step": 350
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.071,
|
| 522 |
+
"grad_norm": 0.380937397480011,
|
| 523 |
+
"learning_rate": 3.995270579091465e-06,
|
| 524 |
+
"loss": 8.300949096679688,
|
| 525 |
+
"step": 355
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.072,
|
| 529 |
+
"grad_norm": 0.3572588860988617,
|
| 530 |
+
"learning_rate": 3.99480509724082e-06,
|
| 531 |
+
"loss": 8.41064453125,
|
| 532 |
+
"step": 360
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.073,
|
| 536 |
+
"grad_norm": 0.4473942220211029,
|
| 537 |
+
"learning_rate": 3.994317800521228e-06,
|
| 538 |
+
"loss": 8.382225036621094,
|
| 539 |
+
"step": 365
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.074,
|
| 543 |
+
"grad_norm": 0.40747135877609253,
|
| 544 |
+
"learning_rate": 3.993808694261687e-06,
|
| 545 |
+
"loss": 8.360281372070313,
|
| 546 |
+
"step": 370
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.075,
|
| 550 |
+
"grad_norm": 0.42307648062705994,
|
| 551 |
+
"learning_rate": 3.993277784029702e-06,
|
| 552 |
+
"loss": 8.374369812011718,
|
| 553 |
+
"step": 375
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.076,
|
| 557 |
+
"grad_norm": 0.38264399766921997,
|
| 558 |
+
"learning_rate": 3.992725075631223e-06,
|
| 559 |
+
"loss": 8.344956207275391,
|
| 560 |
+
"step": 380
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.077,
|
| 564 |
+
"grad_norm": 0.34773537516593933,
|
| 565 |
+
"learning_rate": 3.992150575110579e-06,
|
| 566 |
+
"loss": 8.235700988769532,
|
| 567 |
+
"step": 385
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.078,
|
| 571 |
+
"grad_norm": 0.37760239839553833,
|
| 572 |
+
"learning_rate": 3.991554288750416e-06,
|
| 573 |
+
"loss": 8.38818130493164,
|
| 574 |
+
"step": 390
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 0.079,
|
| 578 |
+
"grad_norm": 0.4430180490016937,
|
| 579 |
+
"learning_rate": 3.990936223071627e-06,
|
| 580 |
+
"loss": 8.25281982421875,
|
| 581 |
+
"step": 395
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 0.08,
|
| 585 |
+
"grad_norm": 0.37283849716186523,
|
| 586 |
+
"learning_rate": 3.990296384833279e-06,
|
| 587 |
+
"loss": 8.315816497802734,
|
| 588 |
+
"step": 400
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 0.081,
|
| 592 |
+
"grad_norm": 0.40707769989967346,
|
| 593 |
+
"learning_rate": 3.989634781032539e-06,
|
| 594 |
+
"loss": 8.215055084228515,
|
| 595 |
+
"step": 405
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 0.082,
|
| 599 |
+
"grad_norm": 0.38030412793159485,
|
| 600 |
+
"learning_rate": 3.9889514189046015e-06,
|
| 601 |
+
"loss": 8.311016845703126,
|
| 602 |
+
"step": 410
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.083,
|
| 606 |
+
"grad_norm": 0.37480244040489197,
|
| 607 |
+
"learning_rate": 3.988246305922606e-06,
|
| 608 |
+
"loss": 8.189589691162109,
|
| 609 |
+
"step": 415
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.084,
|
| 613 |
+
"grad_norm": 0.3482901453971863,
|
| 614 |
+
"learning_rate": 3.987519449797554e-06,
|
| 615 |
+
"loss": 8.21697540283203,
|
| 616 |
+
"step": 420
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 0.085,
|
| 620 |
+
"grad_norm": 0.34717708826065063,
|
| 621 |
+
"learning_rate": 3.986770858478227e-06,
|
| 622 |
+
"loss": 8.241048431396484,
|
| 623 |
+
"step": 425
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 0.086,
|
| 627 |
+
"grad_norm": 0.36790233850479126,
|
| 628 |
+
"learning_rate": 3.986000540151101e-06,
|
| 629 |
+
"loss": 8.249729919433594,
|
| 630 |
+
"step": 430
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 0.087,
|
| 634 |
+
"grad_norm": 0.3420678973197937,
|
| 635 |
+
"learning_rate": 3.985208503240253e-06,
|
| 636 |
+
"loss": 8.281121063232423,
|
| 637 |
+
"step": 435
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 0.088,
|
| 641 |
+
"grad_norm": 0.34600451588630676,
|
| 642 |
+
"learning_rate": 3.9843947564072725e-06,
|
| 643 |
+
"loss": 8.357573699951171,
|
| 644 |
+
"step": 440
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 0.089,
|
| 648 |
+
"grad_norm": 0.35705456137657166,
|
| 649 |
+
"learning_rate": 3.983559308551164e-06,
|
| 650 |
+
"loss": 8.280086517333984,
|
| 651 |
+
"step": 445
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.09,
|
| 655 |
+
"grad_norm": 0.3669961392879486,
|
| 656 |
+
"learning_rate": 3.982702168808252e-06,
|
| 657 |
+
"loss": 8.206847381591796,
|
| 658 |
+
"step": 450
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 0.09,
|
| 662 |
+
"eval_accuracy": 0.12533089133089134,
|
| 663 |
+
"eval_loss": 8.183599472045898,
|
| 664 |
+
"eval_runtime": 9.8934,
|
| 665 |
+
"eval_samples_per_second": 10.108,
|
| 666 |
+
"eval_steps_per_second": 1.718,
|
| 667 |
+
"step": 450
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.091,
|
| 671 |
+
"grad_norm": 0.37337207794189453,
|
| 672 |
+
"learning_rate": 3.981823346552078e-06,
|
| 673 |
+
"loss": 8.199935913085938,
|
| 674 |
+
"step": 455
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.092,
|
| 678 |
+
"grad_norm": 0.44037237763404846,
|
| 679 |
+
"learning_rate": 3.980922851393302e-06,
|
| 680 |
+
"loss": 8.162527465820313,
|
| 681 |
+
"step": 460
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.093,
|
| 685 |
+
"grad_norm": 0.3508804142475128,
|
| 686 |
+
"learning_rate": 3.9800006931795954e-06,
|
| 687 |
+
"loss": 8.137972259521485,
|
| 688 |
+
"step": 465
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.094,
|
| 692 |
+
"grad_norm": 0.3387139141559601,
|
| 693 |
+
"learning_rate": 3.979056881995533e-06,
|
| 694 |
+
"loss": 8.121975708007813,
|
| 695 |
+
"step": 470
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.095,
|
| 699 |
+
"grad_norm": 0.341962069272995,
|
| 700 |
+
"learning_rate": 3.978091428162482e-06,
|
| 701 |
+
"loss": 8.128800964355468,
|
| 702 |
+
"step": 475
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.096,
|
| 706 |
+
"grad_norm": 0.3712274730205536,
|
| 707 |
+
"learning_rate": 3.97710434223849e-06,
|
| 708 |
+
"loss": 8.214947509765626,
|
| 709 |
+
"step": 480
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.097,
|
| 713 |
+
"grad_norm": 0.4289889335632324,
|
| 714 |
+
"learning_rate": 3.976095635018172e-06,
|
| 715 |
+
"loss": 8.149790954589843,
|
| 716 |
+
"step": 485
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.098,
|
| 720 |
+
"grad_norm": 0.33974844217300415,
|
| 721 |
+
"learning_rate": 3.975065317532588e-06,
|
| 722 |
+
"loss": 8.15101318359375,
|
| 723 |
+
"step": 490
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.099,
|
| 727 |
+
"grad_norm": 0.3340671956539154,
|
| 728 |
+
"learning_rate": 3.974013401049125e-06,
|
| 729 |
+
"loss": 8.08057861328125,
|
| 730 |
+
"step": 495
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.1,
|
| 734 |
+
"grad_norm": 0.3514098525047302,
|
| 735 |
+
"learning_rate": 3.972939897071373e-06,
|
| 736 |
+
"loss": 8.09535903930664,
|
| 737 |
+
"step": 500
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.101,
|
| 741 |
+
"grad_norm": 0.34814581274986267,
|
| 742 |
+
"learning_rate": 3.971844817338999e-06,
|
| 743 |
+
"loss": 8.083773803710937,
|
| 744 |
+
"step": 505
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.102,
|
| 748 |
+
"grad_norm": 0.34985920786857605,
|
| 749 |
+
"learning_rate": 3.97072817382762e-06,
|
| 750 |
+
"loss": 8.11724853515625,
|
| 751 |
+
"step": 510
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.103,
|
| 755 |
+
"grad_norm": 0.3791492283344269,
|
| 756 |
+
"learning_rate": 3.969589978748671e-06,
|
| 757 |
+
"loss": 8.136322021484375,
|
| 758 |
+
"step": 515
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.104,
|
| 762 |
+
"grad_norm": 0.32822874188423157,
|
| 763 |
+
"learning_rate": 3.968430244549271e-06,
|
| 764 |
+
"loss": 8.104237365722657,
|
| 765 |
+
"step": 520
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.105,
|
| 769 |
+
"grad_norm": 0.3564032018184662,
|
| 770 |
+
"learning_rate": 3.967248983912086e-06,
|
| 771 |
+
"loss": 8.096965026855468,
|
| 772 |
+
"step": 525
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.106,
|
| 776 |
+
"grad_norm": 0.376220703125,
|
| 777 |
+
"learning_rate": 3.966046209755195e-06,
|
| 778 |
+
"loss": 8.00832748413086,
|
| 779 |
+
"step": 530
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.107,
|
| 783 |
+
"grad_norm": 0.36956483125686646,
|
| 784 |
+
"learning_rate": 3.964821935231942e-06,
|
| 785 |
+
"loss": 8.112174224853515,
|
| 786 |
+
"step": 535
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.108,
|
| 790 |
+
"grad_norm": 0.34770211577415466,
|
| 791 |
+
"learning_rate": 3.963576173730798e-06,
|
| 792 |
+
"loss": 8.067781066894531,
|
| 793 |
+
"step": 540
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.109,
|
| 797 |
+
"grad_norm": 0.3450458347797394,
|
| 798 |
+
"learning_rate": 3.9623089388752105e-06,
|
| 799 |
+
"loss": 8.181710815429687,
|
| 800 |
+
"step": 545
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.11,
|
| 804 |
+
"grad_norm": 0.35391199588775635,
|
| 805 |
+
"learning_rate": 3.961020244523458e-06,
|
| 806 |
+
"loss": 8.074383544921876,
|
| 807 |
+
"step": 550
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.111,
|
| 811 |
+
"grad_norm": 0.35581737756729126,
|
| 812 |
+
"learning_rate": 3.959710104768493e-06,
|
| 813 |
+
"loss": 8.113288879394531,
|
| 814 |
+
"step": 555
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.112,
|
| 818 |
+
"grad_norm": 0.3356166481971741,
|
| 819 |
+
"learning_rate": 3.958378533937797e-06,
|
| 820 |
+
"loss": 8.000715637207032,
|
| 821 |
+
"step": 560
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.113,
|
| 825 |
+
"grad_norm": 0.4040232300758362,
|
| 826 |
+
"learning_rate": 3.957025546593213e-06,
|
| 827 |
+
"loss": 8.02787094116211,
|
| 828 |
+
"step": 565
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.114,
|
| 832 |
+
"grad_norm": 0.3501885235309601,
|
| 833 |
+
"learning_rate": 3.9556511575307956e-06,
|
| 834 |
+
"loss": 8.096998596191407,
|
| 835 |
+
"step": 570
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.115,
|
| 839 |
+
"grad_norm": 0.4042588472366333,
|
| 840 |
+
"learning_rate": 3.954255381780641e-06,
|
| 841 |
+
"loss": 7.963522338867188,
|
| 842 |
+
"step": 575
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.116,
|
| 846 |
+
"grad_norm": 0.35777050256729126,
|
| 847 |
+
"learning_rate": 3.952838234606732e-06,
|
| 848 |
+
"loss": 8.016288757324219,
|
| 849 |
+
"step": 580
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.117,
|
| 853 |
+
"grad_norm": 0.35311609506607056,
|
| 854 |
+
"learning_rate": 3.951399731506761e-06,
|
| 855 |
+
"loss": 8.053848266601562,
|
| 856 |
+
"step": 585
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.118,
|
| 860 |
+
"grad_norm": 0.41893506050109863,
|
| 861 |
+
"learning_rate": 3.949939888211968e-06,
|
| 862 |
+
"loss": 8.02327651977539,
|
| 863 |
+
"step": 590
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.119,
|
| 867 |
+
"grad_norm": 0.44586342573165894,
|
| 868 |
+
"learning_rate": 3.948458720686966e-06,
|
| 869 |
+
"loss": 7.9286552429199215,
|
| 870 |
+
"step": 595
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.12,
|
| 874 |
+
"grad_norm": 0.34198442101478577,
|
| 875 |
+
"learning_rate": 3.946956245129566e-06,
|
| 876 |
+
"loss": 7.989341735839844,
|
| 877 |
+
"step": 600
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.12,
|
| 881 |
+
"eval_accuracy": 0.12831746031746033,
|
| 882 |
+
"eval_loss": 8.00243091583252,
|
| 883 |
+
"eval_runtime": 9.9685,
|
| 884 |
+
"eval_samples_per_second": 10.032,
|
| 885 |
+
"eval_steps_per_second": 1.705,
|
| 886 |
+
"step": 600
|
| 887 |
}
|
| 888 |
],
|
| 889 |
"logging_steps": 5,
|