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 34456
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b4fa038c971ac34dcae7913a853823780441d4eea44dd0e4b73b1229a7813dd
|
| 3 |
size 34456
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 73222
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3007e9e0c04d0a10a1244ca12be9e308704feb9063386934a7ddb74f829db1ea
|
| 3 |
size 73222
|
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:f85f9af538cf2b77c6bd576ebfd9318e40eedb504d1dc93e89f48bbc8e18e06b
|
| 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:fb2481782945fd527fd68f03d6ecc086ae38c0c705bfbe5de3172ab751f2e6c8
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 11.5,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 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": 219.821,
|
| 374 |
"eval_steps_per_second": 54.977,
|
| 375 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 376 |
}
|
| 377 |
],
|
| 378 |
"logging_steps": 1,
|
|
@@ -387,7 +745,7 @@
|
|
| 387 |
"early_stopping_threshold": 0.0
|
| 388 |
},
|
| 389 |
"attributes": {
|
| 390 |
-
"early_stopping_patience_counter":
|
| 391 |
}
|
| 392 |
},
|
| 393 |
"TrainerControl": {
|
|
@@ -401,7 +759,7 @@
|
|
| 401 |
"attributes": {}
|
| 402 |
}
|
| 403 |
},
|
| 404 |
-
"total_flos":
|
| 405 |
"train_batch_size": 8,
|
| 406 |
"trial_name": null,
|
| 407 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 11.5,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 4 |
+
"epoch": 0.06749915626054674,
|
| 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": 219.821,
|
| 374 |
"eval_steps_per_second": 54.977,
|
| 375 |
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.03442456969287884,
|
| 379 |
+
"grad_norm": 5.4881169489817694e-05,
|
| 380 |
+
"learning_rate": 7.11550911504845e-05,
|
| 381 |
+
"loss": 46.0,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.03509956125548431,
|
| 386 |
+
"grad_norm": 7.321939483517781e-05,
|
| 387 |
+
"learning_rate": 7.073604443427437e-05,
|
| 388 |
+
"loss": 46.0,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.03577455281808977,
|
| 393 |
+
"grad_norm": 7.501189247705042e-05,
|
| 394 |
+
"learning_rate": 7.03085947904134e-05,
|
| 395 |
+
"loss": 46.0,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.03644954438069524,
|
| 400 |
+
"grad_norm": 7.780554005876184e-05,
|
| 401 |
+
"learning_rate": 6.987285907936617e-05,
|
| 402 |
+
"loss": 46.0,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.03712453594330071,
|
| 407 |
+
"grad_norm": 9.891616355162114e-05,
|
| 408 |
+
"learning_rate": 6.942895642692527e-05,
|
| 409 |
+
"loss": 46.0,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.03779952750590618,
|
| 414 |
+
"grad_norm": 0.00010379558807471767,
|
| 415 |
+
"learning_rate": 6.897700819164357e-05,
|
| 416 |
+
"loss": 46.0,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.038474519068511646,
|
| 421 |
+
"grad_norm": 6.376452802214772e-05,
|
| 422 |
+
"learning_rate": 6.851713793165589e-05,
|
| 423 |
+
"loss": 46.0,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.03914951063111711,
|
| 428 |
+
"grad_norm": 0.00011976366658927873,
|
| 429 |
+
"learning_rate": 6.804947137089955e-05,
|
| 430 |
+
"loss": 46.0,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.03982450219372258,
|
| 435 |
+
"grad_norm": 0.00011366497346898541,
|
| 436 |
+
"learning_rate": 6.757413636474263e-05,
|
| 437 |
+
"loss": 46.0,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.040499493756328046,
|
| 442 |
+
"grad_norm": 0.00012407948088366538,
|
| 443 |
+
"learning_rate": 6.709126286502965e-05,
|
| 444 |
+
"loss": 46.0,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.041174485318933515,
|
| 449 |
+
"grad_norm": 0.00011083694698754698,
|
| 450 |
+
"learning_rate": 6.660098288455393e-05,
|
| 451 |
+
"loss": 46.0,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.041849476881538984,
|
| 456 |
+
"grad_norm": 0.00012434367090463638,
|
| 457 |
+
"learning_rate": 6.610343046096674e-05,
|
| 458 |
+
"loss": 46.0,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.042524468444144446,
|
| 463 |
+
"grad_norm": 9.564027277519926e-05,
|
| 464 |
+
"learning_rate": 6.559874162013267e-05,
|
| 465 |
+
"loss": 46.0,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.043199460006749915,
|
| 470 |
+
"grad_norm": 8.99869337445125e-05,
|
| 471 |
+
"learning_rate": 6.508705433894149e-05,
|
| 472 |
+
"loss": 46.0,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.043874451569355384,
|
| 477 |
+
"grad_norm": 0.00011574227391975,
|
| 478 |
+
"learning_rate": 6.456850850758673e-05,
|
| 479 |
+
"loss": 46.0,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.04454944313196085,
|
| 484 |
+
"grad_norm": 0.00011398899368941784,
|
| 485 |
+
"learning_rate": 6.404324589132101e-05,
|
| 486 |
+
"loss": 46.0,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.045224434694566315,
|
| 491 |
+
"grad_norm": 8.823705138638616e-05,
|
| 492 |
+
"learning_rate": 6.351141009169893e-05,
|
| 493 |
+
"loss": 46.0,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.045899426257171784,
|
| 498 |
+
"grad_norm": 0.0001269930216949433,
|
| 499 |
+
"learning_rate": 6.297314650731775e-05,
|
| 500 |
+
"loss": 46.0,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.04657441781977725,
|
| 505 |
+
"grad_norm": 0.0001396976731484756,
|
| 506 |
+
"learning_rate": 6.242860229406692e-05,
|
| 507 |
+
"loss": 46.0,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.04724940938238272,
|
| 512 |
+
"grad_norm": 0.0001476786273997277,
|
| 513 |
+
"learning_rate": 6.18779263248971e-05,
|
| 514 |
+
"loss": 46.0,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.04792440094498819,
|
| 519 |
+
"grad_norm": 0.0001579802919877693,
|
| 520 |
+
"learning_rate": 6.132126914911976e-05,
|
| 521 |
+
"loss": 46.0,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.04859939250759365,
|
| 526 |
+
"grad_norm": 0.00014366269169840962,
|
| 527 |
+
"learning_rate": 6.075878295124861e-05,
|
| 528 |
+
"loss": 46.0,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.04927438407019912,
|
| 533 |
+
"grad_norm": 0.00015545522910542786,
|
| 534 |
+
"learning_rate": 6.019062150939376e-05,
|
| 535 |
+
"loss": 46.0,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.04994937563280459,
|
| 540 |
+
"grad_norm": 0.00011848592112073675,
|
| 541 |
+
"learning_rate": 5.9616940153220336e-05,
|
| 542 |
+
"loss": 46.0,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.05062436719541006,
|
| 547 |
+
"grad_norm": 0.00015544149209745228,
|
| 548 |
+
"learning_rate": 5.903789572148295e-05,
|
| 549 |
+
"loss": 46.0,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.05129935875801552,
|
| 554 |
+
"grad_norm": 0.00016012511332519352,
|
| 555 |
+
"learning_rate": 5.845364651914752e-05,
|
| 556 |
+
"loss": 46.0,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.05197435032062099,
|
| 561 |
+
"grad_norm": 0.00024290069995913655,
|
| 562 |
+
"learning_rate": 5.786435227411227e-05,
|
| 563 |
+
"loss": 46.0,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.05264934188322646,
|
| 568 |
+
"grad_norm": 0.00016308229533024132,
|
| 569 |
+
"learning_rate": 5.727017409353971e-05,
|
| 570 |
+
"loss": 46.0,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.05332433344583193,
|
| 575 |
+
"grad_norm": 0.0001312433450948447,
|
| 576 |
+
"learning_rate": 5.667127441981162e-05,
|
| 577 |
+
"loss": 46.0,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.0539993250084374,
|
| 582 |
+
"grad_norm": 0.00020814283925574273,
|
| 583 |
+
"learning_rate": 5.606781698611879e-05,
|
| 584 |
+
"loss": 46.0,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.05467431657104286,
|
| 589 |
+
"grad_norm": 0.00017544587899465114,
|
| 590 |
+
"learning_rate": 5.5459966771698096e-05,
|
| 591 |
+
"loss": 46.0,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.05534930813364833,
|
| 596 |
+
"grad_norm": 0.00021598087914753705,
|
| 597 |
+
"learning_rate": 5.4847889956728834e-05,
|
| 598 |
+
"loss": 46.0,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.0560242996962538,
|
| 603 |
+
"grad_norm": 0.00022435332357417792,
|
| 604 |
+
"learning_rate": 5.423175387690067e-05,
|
| 605 |
+
"loss": 46.0,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.056699291258859266,
|
| 610 |
+
"grad_norm": 0.00025759119307622313,
|
| 611 |
+
"learning_rate": 5.361172697766573e-05,
|
| 612 |
+
"loss": 46.0,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.05737428282146473,
|
| 617 |
+
"grad_norm": 0.00027369000599719584,
|
| 618 |
+
"learning_rate": 5.298797876818735e-05,
|
| 619 |
+
"loss": 46.0,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.0580492743840702,
|
| 624 |
+
"grad_norm": 0.00021083872707094997,
|
| 625 |
+
"learning_rate": 5.23606797749979e-05,
|
| 626 |
+
"loss": 46.0,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.058724265946675666,
|
| 631 |
+
"grad_norm": 0.00017781296628527343,
|
| 632 |
+
"learning_rate": 5.17300014953786e-05,
|
| 633 |
+
"loss": 46.0,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.059399257509281135,
|
| 638 |
+
"grad_norm": 0.0002701023768167943,
|
| 639 |
+
"learning_rate": 5.109611635047379e-05,
|
| 640 |
+
"loss": 46.0,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.060074249071886604,
|
| 645 |
+
"grad_norm": 0.00020761927589774132,
|
| 646 |
+
"learning_rate": 5.04591976381528e-05,
|
| 647 |
+
"loss": 46.0,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.060749240634492066,
|
| 652 |
+
"grad_norm": 0.0002119742421200499,
|
| 653 |
+
"learning_rate": 4.981941948563197e-05,
|
| 654 |
+
"loss": 46.0,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.061424232197097535,
|
| 659 |
+
"grad_norm": 0.0003119312459602952,
|
| 660 |
+
"learning_rate": 4.9176956801870065e-05,
|
| 661 |
+
"loss": 46.0,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.062099223759703004,
|
| 666 |
+
"grad_norm": 0.00029339047614485025,
|
| 667 |
+
"learning_rate": 4.853198522974988e-05,
|
| 668 |
+
"loss": 46.0,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.06277421532230847,
|
| 673 |
+
"grad_norm": 0.00024452415527775884,
|
| 674 |
+
"learning_rate": 4.788468109805921e-05,
|
| 675 |
+
"loss": 46.0,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.06344920688491394,
|
| 680 |
+
"grad_norm": 0.00024892069632187486,
|
| 681 |
+
"learning_rate": 4.7235221373284407e-05,
|
| 682 |
+
"loss": 46.0,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.0641241984475194,
|
| 687 |
+
"grad_norm": 0.00032684431062079966,
|
| 688 |
+
"learning_rate": 4.658378361122936e-05,
|
| 689 |
+
"loss": 46.0,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.06479919001012488,
|
| 694 |
+
"grad_norm": 0.00033167307265102863,
|
| 695 |
+
"learning_rate": 4.593054590847368e-05,
|
| 696 |
+
"loss": 46.0,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.06547418157273034,
|
| 701 |
+
"grad_norm": 0.00021435694361571223,
|
| 702 |
+
"learning_rate": 4.5275686853682765e-05,
|
| 703 |
+
"loss": 46.0,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.0661491731353358,
|
| 708 |
+
"grad_norm": 0.00033286900725215673,
|
| 709 |
+
"learning_rate": 4.4619385478783456e-05,
|
| 710 |
+
"loss": 46.0,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.06682416469794128,
|
| 715 |
+
"grad_norm": 0.0003271261812187731,
|
| 716 |
+
"learning_rate": 4.396182121001852e-05,
|
| 717 |
+
"loss": 46.0,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.06749915626054674,
|
| 722 |
+
"grad_norm": 0.0008189138607122004,
|
| 723 |
+
"learning_rate": 4.33031738188933e-05,
|
| 724 |
+
"loss": 46.0,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.06749915626054674,
|
| 729 |
+
"eval_loss": 11.5,
|
| 730 |
+
"eval_runtime": 11.1305,
|
| 731 |
+
"eval_samples_per_second": 224.16,
|
| 732 |
+
"eval_steps_per_second": 56.062,
|
| 733 |
+
"step": 100
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
|
|
| 745 |
"early_stopping_threshold": 0.0
|
| 746 |
},
|
| 747 |
"attributes": {
|
| 748 |
+
"early_stopping_patience_counter": 1
|
| 749 |
}
|
| 750 |
},
|
| 751 |
"TrainerControl": {
|
|
|
|
| 759 |
"attributes": {}
|
| 760 |
}
|
| 761 |
},
|
| 762 |
+
"total_flos": 16079231385600.0,
|
| 763 |
"train_batch_size": 8,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|