Training in progress, step 75, 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 159712
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7b2726c067ceb015977b793b11e76c3dd71c19e7f1770c1abf477e6dcc87497
|
| 3 |
size 159712
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 336202
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80aafa1870be89def46775c0f33f2aa72591701074aae27a7137bfd15797bcc8
|
| 3 |
size 336202
|
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 sha256:7390d69c035960909a3614dd1bb0738527d72c78eaafed1ea04f6c83d7885b4d
|
| 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:feed204db996a9f7ac3167cc4686c04dccd6605b9b2a7d539da6ff57c605983d
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 9,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -405,6 +405,205 @@
|
|
| 405 |
"learning_rate": 1.1736481776669307e-05,
|
| 406 |
"loss": 10.8299,
|
| 407 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 408 |
}
|
| 409 |
],
|
| 410 |
"logging_steps": 1,
|
|
@@ -424,7 +623,7 @@
|
|
| 424 |
"attributes": {}
|
| 425 |
}
|
| 426 |
},
|
| 427 |
-
"total_flos":
|
| 428 |
"train_batch_size": 8,
|
| 429 |
"trial_name": null,
|
| 430 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.12244897959183673,
|
| 5 |
"eval_steps": 9,
|
| 6 |
+
"global_step": 75,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 405 |
"learning_rate": 1.1736481776669307e-05,
|
| 406 |
"loss": 10.8299,
|
| 407 |
"step": 50
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.08326530612244898,
|
| 411 |
+
"grad_norm": 0.4201260507106781,
|
| 412 |
+
"learning_rate": 1.1391731009600655e-05,
|
| 413 |
+
"loss": 10.8119,
|
| 414 |
+
"step": 51
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.08489795918367347,
|
| 418 |
+
"grad_norm": 0.39234814047813416,
|
| 419 |
+
"learning_rate": 1.1045284632676535e-05,
|
| 420 |
+
"loss": 10.8114,
|
| 421 |
+
"step": 52
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.08653061224489796,
|
| 425 |
+
"grad_norm": 0.39883697032928467,
|
| 426 |
+
"learning_rate": 1.0697564737441254e-05,
|
| 427 |
+
"loss": 10.8213,
|
| 428 |
+
"step": 53
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.08816326530612245,
|
| 432 |
+
"grad_norm": 0.3016551434993744,
|
| 433 |
+
"learning_rate": 1.0348994967025012e-05,
|
| 434 |
+
"loss": 10.8257,
|
| 435 |
+
"step": 54
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.08816326530612245,
|
| 439 |
+
"eval_loss": 10.823841094970703,
|
| 440 |
+
"eval_runtime": 3.2735,
|
| 441 |
+
"eval_samples_per_second": 157.631,
|
| 442 |
+
"eval_steps_per_second": 19.857,
|
| 443 |
+
"step": 54
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.08979591836734693,
|
| 447 |
+
"grad_norm": 0.3536202907562256,
|
| 448 |
+
"learning_rate": 1e-05,
|
| 449 |
+
"loss": 10.8218,
|
| 450 |
+
"step": 55
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.09142857142857143,
|
| 454 |
+
"grad_norm": 0.3456736207008362,
|
| 455 |
+
"learning_rate": 9.651005032974994e-06,
|
| 456 |
+
"loss": 10.8277,
|
| 457 |
+
"step": 56
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.09306122448979592,
|
| 461 |
+
"grad_norm": 0.3298264145851135,
|
| 462 |
+
"learning_rate": 9.302435262558748e-06,
|
| 463 |
+
"loss": 10.8243,
|
| 464 |
+
"step": 57
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.0946938775510204,
|
| 468 |
+
"grad_norm": 0.4061192274093628,
|
| 469 |
+
"learning_rate": 8.954715367323468e-06,
|
| 470 |
+
"loss": 10.8157,
|
| 471 |
+
"step": 58
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.0963265306122449,
|
| 475 |
+
"grad_norm": 0.404811829328537,
|
| 476 |
+
"learning_rate": 8.60826899039935e-06,
|
| 477 |
+
"loss": 10.8105,
|
| 478 |
+
"step": 59
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.09795918367346938,
|
| 482 |
+
"grad_norm": 0.40592458844184875,
|
| 483 |
+
"learning_rate": 8.263518223330698e-06,
|
| 484 |
+
"loss": 10.8179,
|
| 485 |
+
"step": 60
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.09959183673469388,
|
| 489 |
+
"grad_norm": 0.3541053831577301,
|
| 490 |
+
"learning_rate": 7.92088309182241e-06,
|
| 491 |
+
"loss": 10.8242,
|
| 492 |
+
"step": 61
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.10122448979591837,
|
| 496 |
+
"grad_norm": 0.322318971157074,
|
| 497 |
+
"learning_rate": 7.580781044003324e-06,
|
| 498 |
+
"loss": 10.827,
|
| 499 |
+
"step": 62
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.10285714285714286,
|
| 503 |
+
"grad_norm": 0.36938780546188354,
|
| 504 |
+
"learning_rate": 7.243626441830009e-06,
|
| 505 |
+
"loss": 10.8152,
|
| 506 |
+
"step": 63
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.10285714285714286,
|
| 510 |
+
"eval_loss": 10.82233715057373,
|
| 511 |
+
"eval_runtime": 3.9005,
|
| 512 |
+
"eval_samples_per_second": 132.29,
|
| 513 |
+
"eval_steps_per_second": 16.664,
|
| 514 |
+
"step": 63
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.10448979591836735,
|
| 518 |
+
"grad_norm": 0.3522907495498657,
|
| 519 |
+
"learning_rate": 6.909830056250527e-06,
|
| 520 |
+
"loss": 10.813,
|
| 521 |
+
"step": 64
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.10612244897959183,
|
| 525 |
+
"grad_norm": 0.4052838385105133,
|
| 526 |
+
"learning_rate": 6.579798566743314e-06,
|
| 527 |
+
"loss": 10.8225,
|
| 528 |
+
"step": 65
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.10775510204081633,
|
| 532 |
+
"grad_norm": 0.3478013575077057,
|
| 533 |
+
"learning_rate": 6.25393406584088e-06,
|
| 534 |
+
"loss": 10.8207,
|
| 535 |
+
"step": 66
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.10938775510204081,
|
| 539 |
+
"grad_norm": 0.3661433160305023,
|
| 540 |
+
"learning_rate": 5.932633569242e-06,
|
| 541 |
+
"loss": 10.8141,
|
| 542 |
+
"step": 67
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.1110204081632653,
|
| 546 |
+
"grad_norm": 0.30546510219573975,
|
| 547 |
+
"learning_rate": 5.616288532109225e-06,
|
| 548 |
+
"loss": 10.8194,
|
| 549 |
+
"step": 68
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.1126530612244898,
|
| 553 |
+
"grad_norm": 0.3616853952407837,
|
| 554 |
+
"learning_rate": 5.305284372141095e-06,
|
| 555 |
+
"loss": 10.8135,
|
| 556 |
+
"step": 69
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.11428571428571428,
|
| 560 |
+
"grad_norm": 0.38204777240753174,
|
| 561 |
+
"learning_rate": 5.000000000000003e-06,
|
| 562 |
+
"loss": 10.8198,
|
| 563 |
+
"step": 70
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.11591836734693878,
|
| 567 |
+
"grad_norm": 0.347457617521286,
|
| 568 |
+
"learning_rate": 4.700807357667953e-06,
|
| 569 |
+
"loss": 10.8235,
|
| 570 |
+
"step": 71
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.11755102040816326,
|
| 574 |
+
"grad_norm": 0.30413001775741577,
|
| 575 |
+
"learning_rate": 4.408070965292534e-06,
|
| 576 |
+
"loss": 10.8379,
|
| 577 |
+
"step": 72
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.11755102040816326,
|
| 581 |
+
"eval_loss": 10.821290969848633,
|
| 582 |
+
"eval_runtime": 3.9229,
|
| 583 |
+
"eval_samples_per_second": 131.536,
|
| 584 |
+
"eval_steps_per_second": 16.569,
|
| 585 |
+
"step": 72
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.11918367346938775,
|
| 589 |
+
"grad_norm": 0.3408275246620178,
|
| 590 |
+
"learning_rate": 4.12214747707527e-06,
|
| 591 |
+
"loss": 10.823,
|
| 592 |
+
"step": 73
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.12081632653061225,
|
| 596 |
+
"grad_norm": 0.37985777854919434,
|
| 597 |
+
"learning_rate": 3.8433852467434175e-06,
|
| 598 |
+
"loss": 10.8096,
|
| 599 |
+
"step": 74
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.12244897959183673,
|
| 603 |
+
"grad_norm": 0.34624186158180237,
|
| 604 |
+
"learning_rate": 3.5721239031346067e-06,
|
| 605 |
+
"loss": 10.8258,
|
| 606 |
+
"step": 75
|
| 607 |
}
|
| 608 |
],
|
| 609 |
"logging_steps": 1,
|
|
|
|
| 623 |
"attributes": {}
|
| 624 |
}
|
| 625 |
},
|
| 626 |
+
"total_flos": 24752789913600.0,
|
| 627 |
"train_batch_size": 8,
|
| 628 |
"trial_name": null,
|
| 629 |
"trial_params": null
|