Training in progress, step 100, 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 124756544
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:540b43c27ce9d45f67e5362b6b4cfcbb10e6586ca874fac5db3612514de201fd
|
| 3 |
size 124756544
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 63958740
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58a8f70b234248e16553fb2e2efbdc0c248b9900aa542270ae5d7046f520e5b3
|
| 3 |
size 63958740
|
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 sha256:1587726aec1f75f737018a73e7de2d0d5713390c50e5b1386177a35ec2977d5a
|
| 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 sha256:3fc7800513a1b4dd006c457152c700dd768bb49ee4ed8e4d9665a4e42095b054
|
| 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": 50,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -373,6 +373,364 @@
|
|
| 373 |
"eval_samples_per_second": 10.602,
|
| 374 |
"eval_steps_per_second": 5.304,
|
| 375 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 376 |
}
|
| 377 |
],
|
| 378 |
"logging_steps": 1,
|
|
@@ -392,7 +750,7 @@
|
|
| 392 |
"attributes": {}
|
| 393 |
}
|
| 394 |
},
|
| 395 |
-
"total_flos":
|
| 396 |
"train_batch_size": 2,
|
| 397 |
"trial_name": null,
|
| 398 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.021831677764436196,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 100,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 373 |
"eval_samples_per_second": 10.602,
|
| 374 |
"eval_steps_per_second": 5.304,
|
| 375 |
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.011134155659862461,
|
| 379 |
+
"grad_norm": 0.16260926425457,
|
| 380 |
+
"learning_rate": 0.00017788772787621126,
|
| 381 |
+
"loss": 0.6544,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.011352472437506823,
|
| 386 |
+
"grad_norm": 0.16436129808425903,
|
| 387 |
+
"learning_rate": 0.00017684011108568592,
|
| 388 |
+
"loss": 0.5796,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.011570789215151185,
|
| 393 |
+
"grad_norm": 0.15874071419239044,
|
| 394 |
+
"learning_rate": 0.0001757714869760335,
|
| 395 |
+
"loss": 0.6229,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.011789105992795547,
|
| 400 |
+
"grad_norm": 0.17372044920921326,
|
| 401 |
+
"learning_rate": 0.0001746821476984154,
|
| 402 |
+
"loss": 0.8861,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.012007422770439908,
|
| 407 |
+
"grad_norm": 0.190564826130867,
|
| 408 |
+
"learning_rate": 0.00017357239106731317,
|
| 409 |
+
"loss": 0.779,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.01222573954808427,
|
| 414 |
+
"grad_norm": 0.17491184175014496,
|
| 415 |
+
"learning_rate": 0.00017244252047910892,
|
| 416 |
+
"loss": 0.528,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.012444056325728632,
|
| 421 |
+
"grad_norm": 0.1566992700099945,
|
| 422 |
+
"learning_rate": 0.00017129284482913972,
|
| 423 |
+
"loss": 0.5963,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.012662373103372994,
|
| 428 |
+
"grad_norm": 0.15744012594223022,
|
| 429 |
+
"learning_rate": 0.00017012367842724887,
|
| 430 |
+
"loss": 0.5224,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.012880689881017357,
|
| 435 |
+
"grad_norm": 0.1761963814496994,
|
| 436 |
+
"learning_rate": 0.0001689353409118566,
|
| 437 |
+
"loss": 0.8546,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.013099006658661719,
|
| 442 |
+
"grad_norm": 0.16946905851364136,
|
| 443 |
+
"learning_rate": 0.00016772815716257412,
|
| 444 |
+
"loss": 0.7221,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.01331732343630608,
|
| 449 |
+
"grad_norm": 0.17242185771465302,
|
| 450 |
+
"learning_rate": 0.0001665024572113848,
|
| 451 |
+
"loss": 0.7315,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.013535640213950442,
|
| 456 |
+
"grad_norm": 0.14320792257785797,
|
| 457 |
+
"learning_rate": 0.00016525857615241687,
|
| 458 |
+
"loss": 0.5442,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.013753956991594804,
|
| 463 |
+
"grad_norm": 0.14897648990154266,
|
| 464 |
+
"learning_rate": 0.00016399685405033167,
|
| 465 |
+
"loss": 0.6125,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.013972273769239166,
|
| 470 |
+
"grad_norm": 0.16310685873031616,
|
| 471 |
+
"learning_rate": 0.0001627176358473537,
|
| 472 |
+
"loss": 0.6272,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.014190590546883528,
|
| 477 |
+
"grad_norm": 0.15317314863204956,
|
| 478 |
+
"learning_rate": 0.0001614212712689668,
|
| 479 |
+
"loss": 0.5583,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.01440890732452789,
|
| 484 |
+
"grad_norm": 0.15903247892856598,
|
| 485 |
+
"learning_rate": 0.00016010811472830252,
|
| 486 |
+
"loss": 0.5744,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.014627224102172253,
|
| 491 |
+
"grad_norm": 0.14471517503261566,
|
| 492 |
+
"learning_rate": 0.00015877852522924732,
|
| 493 |
+
"loss": 0.4967,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.014845540879816614,
|
| 498 |
+
"grad_norm": 0.1645640879869461,
|
| 499 |
+
"learning_rate": 0.00015743286626829437,
|
| 500 |
+
"loss": 0.8364,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.015063857657460976,
|
| 505 |
+
"grad_norm": 0.2042667418718338,
|
| 506 |
+
"learning_rate": 0.0001560715057351673,
|
| 507 |
+
"loss": 0.5209,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.015282174435105338,
|
| 512 |
+
"grad_norm": 0.18461734056472778,
|
| 513 |
+
"learning_rate": 0.00015469481581224272,
|
| 514 |
+
"loss": 0.8209,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.0155004912127497,
|
| 519 |
+
"grad_norm": 0.17951343953609467,
|
| 520 |
+
"learning_rate": 0.0001533031728727994,
|
| 521 |
+
"loss": 0.7302,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.015718807990394063,
|
| 526 |
+
"grad_norm": 0.17561626434326172,
|
| 527 |
+
"learning_rate": 0.00015189695737812152,
|
| 528 |
+
"loss": 0.7459,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.015937124768038425,
|
| 533 |
+
"grad_norm": 0.17738279700279236,
|
| 534 |
+
"learning_rate": 0.0001504765537734844,
|
| 535 |
+
"loss": 0.7624,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.016155441545682787,
|
| 540 |
+
"grad_norm": 0.14604610204696655,
|
| 541 |
+
"learning_rate": 0.00014904235038305083,
|
| 542 |
+
"loss": 0.5576,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.01637375832332715,
|
| 547 |
+
"grad_norm": 0.162835031747818,
|
| 548 |
+
"learning_rate": 0.00014759473930370736,
|
| 549 |
+
"loss": 0.6048,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.01659207510097151,
|
| 554 |
+
"grad_norm": 0.16418945789337158,
|
| 555 |
+
"learning_rate": 0.0001461341162978688,
|
| 556 |
+
"loss": 0.5769,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.016810391878615872,
|
| 561 |
+
"grad_norm": 0.19126634299755096,
|
| 562 |
+
"learning_rate": 0.00014466088068528068,
|
| 563 |
+
"loss": 0.7973,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.017028708656260234,
|
| 568 |
+
"grad_norm": 0.1636025458574295,
|
| 569 |
+
"learning_rate": 0.00014317543523384928,
|
| 570 |
+
"loss": 0.6992,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.017247025433904595,
|
| 575 |
+
"grad_norm": 0.1639864444732666,
|
| 576 |
+
"learning_rate": 0.00014167818604952906,
|
| 577 |
+
"loss": 0.6315,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.017465342211548957,
|
| 582 |
+
"grad_norm": 0.20205020904541016,
|
| 583 |
+
"learning_rate": 0.00014016954246529696,
|
| 584 |
+
"loss": 1.0668,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.01768365898919332,
|
| 589 |
+
"grad_norm": 0.16580188274383545,
|
| 590 |
+
"learning_rate": 0.00013864991692924523,
|
| 591 |
+
"loss": 0.7294,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.01790197576683768,
|
| 596 |
+
"grad_norm": 0.17587777972221375,
|
| 597 |
+
"learning_rate": 0.00013711972489182208,
|
| 598 |
+
"loss": 0.6971,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.018120292544482042,
|
| 603 |
+
"grad_norm": 0.18422681093215942,
|
| 604 |
+
"learning_rate": 0.00013557938469225167,
|
| 605 |
+
"loss": 0.7526,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.018338609322126404,
|
| 610 |
+
"grad_norm": 0.16445504128932953,
|
| 611 |
+
"learning_rate": 0.00013402931744416433,
|
| 612 |
+
"loss": 0.6736,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.018556926099770766,
|
| 617 |
+
"grad_norm": 0.14754797518253326,
|
| 618 |
+
"learning_rate": 0.00013246994692046836,
|
| 619 |
+
"loss": 0.4737,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.018775242877415128,
|
| 624 |
+
"grad_norm": 0.19895146787166595,
|
| 625 |
+
"learning_rate": 0.00013090169943749476,
|
| 626 |
+
"loss": 0.7198,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.018993559655059493,
|
| 631 |
+
"grad_norm": 0.16792307794094086,
|
| 632 |
+
"learning_rate": 0.0001293250037384465,
|
| 633 |
+
"loss": 0.7405,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.019211876432703855,
|
| 638 |
+
"grad_norm": 0.1736898571252823,
|
| 639 |
+
"learning_rate": 0.00012774029087618446,
|
| 640 |
+
"loss": 0.6991,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.019430193210348216,
|
| 645 |
+
"grad_norm": 0.19027847051620483,
|
| 646 |
+
"learning_rate": 0.00012614799409538198,
|
| 647 |
+
"loss": 0.8642,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.019648509987992578,
|
| 652 |
+
"grad_norm": 0.16890498995780945,
|
| 653 |
+
"learning_rate": 0.00012454854871407994,
|
| 654 |
+
"loss": 0.5199,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.01986682676563694,
|
| 659 |
+
"grad_norm": 0.17198000848293304,
|
| 660 |
+
"learning_rate": 0.00012294239200467516,
|
| 661 |
+
"loss": 0.6932,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.0200851435432813,
|
| 666 |
+
"grad_norm": 0.17940305173397064,
|
| 667 |
+
"learning_rate": 0.0001213299630743747,
|
| 668 |
+
"loss": 0.5811,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.020303460320925663,
|
| 673 |
+
"grad_norm": 0.17034873366355896,
|
| 674 |
+
"learning_rate": 0.00011971170274514802,
|
| 675 |
+
"loss": 0.6274,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.020521777098570025,
|
| 680 |
+
"grad_norm": 0.17157679796218872,
|
| 681 |
+
"learning_rate": 0.000118088053433211,
|
| 682 |
+
"loss": 0.6947,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.020740093876214387,
|
| 687 |
+
"grad_norm": 0.18038637936115265,
|
| 688 |
+
"learning_rate": 0.00011645945902807341,
|
| 689 |
+
"loss": 0.6019,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.02095841065385875,
|
| 694 |
+
"grad_norm": 0.16414083540439606,
|
| 695 |
+
"learning_rate": 0.0001148263647711842,
|
| 696 |
+
"loss": 0.5772,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.02117672743150311,
|
| 701 |
+
"grad_norm": 0.17010308802127838,
|
| 702 |
+
"learning_rate": 0.00011318921713420691,
|
| 703 |
+
"loss": 0.6766,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.021395044209147472,
|
| 708 |
+
"grad_norm": 0.17190682888031006,
|
| 709 |
+
"learning_rate": 0.00011154846369695863,
|
| 710 |
+
"loss": 0.6057,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.021613360986791834,
|
| 715 |
+
"grad_norm": 0.18158312141895294,
|
| 716 |
+
"learning_rate": 0.0001099045530250463,
|
| 717 |
+
"loss": 0.7767,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.021831677764436196,
|
| 722 |
+
"grad_norm": 0.18446941673755646,
|
| 723 |
+
"learning_rate": 0.00010825793454723325,
|
| 724 |
+
"loss": 0.7482,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.021831677764436196,
|
| 729 |
+
"eval_loss": 0.6601452231407166,
|
| 730 |
+
"eval_runtime": 181.8265,
|
| 731 |
+
"eval_samples_per_second": 10.609,
|
| 732 |
+
"eval_steps_per_second": 5.307,
|
| 733 |
+
"step": 100
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
|
|
| 750 |
"attributes": {}
|
| 751 |
}
|
| 752 |
},
|
| 753 |
+
"total_flos": 6.563165450010624e+16,
|
| 754 |
"train_batch_size": 2,
|
| 755 |
"trial_name": null,
|
| 756 |
"trial_params": null
|