Training in progress, step 97, 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 671149168
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29c9ecc0eff52e3c93da5ca0685f03befb6ce7f689ab0378640778320fc59851
|
| 3 |
size 671149168
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 341314196
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fce16f9080ff43d2ed9ac8277c2134e046f188de7651fb0d7b55ef70e7685521
|
| 3 |
size 341314196
|
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 sha256:1cbbd5da4666b8639391ee33441e55f127790762a3fc34b80d583c7901f0de39
|
| 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 sha256:6145c7e827928ce363c3dece9b28ea4d59912ec6339b2dd62ab9cd74a51e4307
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 2.33044171333313,
|
| 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 +373,335 @@
|
|
| 373 |
"eval_samples_per_second": 7.527,
|
| 374 |
"eval_steps_per_second": 1.893,
|
| 375 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 376 |
}
|
| 377 |
],
|
| 378 |
"logging_steps": 1,
|
|
@@ -396,12 +725,12 @@
|
|
| 396 |
"should_evaluate": false,
|
| 397 |
"should_log": false,
|
| 398 |
"should_save": true,
|
| 399 |
-
"should_training_stop":
|
| 400 |
},
|
| 401 |
"attributes": {}
|
| 402 |
}
|
| 403 |
},
|
| 404 |
-
"total_flos":
|
| 405 |
"train_batch_size": 8,
|
| 406 |
"trial_name": null,
|
| 407 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 2.33044171333313,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 97,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 373 |
"eval_samples_per_second": 7.527,
|
| 374 |
"eval_steps_per_second": 1.893,
|
| 375 |
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.5257731958762887,
|
| 379 |
+
"grad_norm": 3.0543136596679688,
|
| 380 |
+
"learning_rate": 5.4507654055603275e-05,
|
| 381 |
+
"loss": 8.95,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.5360824742268041,
|
| 386 |
+
"grad_norm": 3.10390567779541,
|
| 387 |
+
"learning_rate": 5.270694542927088e-05,
|
| 388 |
+
"loss": 9.3079,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.5463917525773195,
|
| 393 |
+
"grad_norm": 3.123366594314575,
|
| 394 |
+
"learning_rate": 5.090270746252802e-05,
|
| 395 |
+
"loss": 9.4765,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.5567010309278351,
|
| 400 |
+
"grad_norm": 3.072674036026001,
|
| 401 |
+
"learning_rate": 4.909729253747197e-05,
|
| 402 |
+
"loss": 9.0482,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.5670103092783505,
|
| 407 |
+
"grad_norm": 3.2493770122528076,
|
| 408 |
+
"learning_rate": 4.729305457072913e-05,
|
| 409 |
+
"loss": 9.3959,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.5773195876288659,
|
| 414 |
+
"grad_norm": 3.2565178871154785,
|
| 415 |
+
"learning_rate": 4.549234594439674e-05,
|
| 416 |
+
"loss": 9.1795,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.5876288659793815,
|
| 421 |
+
"grad_norm": 3.469116449356079,
|
| 422 |
+
"learning_rate": 4.3697514438985536e-05,
|
| 423 |
+
"loss": 9.3815,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.5979381443298969,
|
| 428 |
+
"grad_norm": 3.3789870738983154,
|
| 429 |
+
"learning_rate": 4.1910900172361764e-05,
|
| 430 |
+
"loss": 9.1261,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.6082474226804123,
|
| 435 |
+
"grad_norm": 3.5949292182922363,
|
| 436 |
+
"learning_rate": 4.0134832548680006e-05,
|
| 437 |
+
"loss": 9.5144,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.6185567010309279,
|
| 442 |
+
"grad_norm": 3.9358599185943604,
|
| 443 |
+
"learning_rate": 3.8371627221284495e-05,
|
| 444 |
+
"loss": 9.5832,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.6288659793814433,
|
| 449 |
+
"grad_norm": 3.6911466121673584,
|
| 450 |
+
"learning_rate": 3.6623583073538966e-05,
|
| 451 |
+
"loss": 9.5956,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.6391752577319587,
|
| 456 |
+
"grad_norm": 4.07518196105957,
|
| 457 |
+
"learning_rate": 3.489297922152136e-05,
|
| 458 |
+
"loss": 9.6749,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.6494845360824743,
|
| 463 |
+
"grad_norm": 4.45421028137207,
|
| 464 |
+
"learning_rate": 3.3182072042491244e-05,
|
| 465 |
+
"loss": 9.6024,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.6597938144329897,
|
| 470 |
+
"grad_norm": 4.890519142150879,
|
| 471 |
+
"learning_rate": 3.149309223300428e-05,
|
| 472 |
+
"loss": 10.0055,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.6701030927835051,
|
| 477 |
+
"grad_norm": 5.906216621398926,
|
| 478 |
+
"learning_rate": 2.982824190050958e-05,
|
| 479 |
+
"loss": 9.3131,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.6804123711340206,
|
| 484 |
+
"grad_norm": 4.849588871002197,
|
| 485 |
+
"learning_rate": 2.8189691692221627e-05,
|
| 486 |
+
"loss": 10.0371,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.6907216494845361,
|
| 491 |
+
"grad_norm": 4.628223419189453,
|
| 492 |
+
"learning_rate": 2.65795779650105e-05,
|
| 493 |
+
"loss": 9.2911,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.7010309278350515,
|
| 498 |
+
"grad_norm": 5.0194091796875,
|
| 499 |
+
"learning_rate": 2.500000000000001e-05,
|
| 500 |
+
"loss": 9.3699,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.711340206185567,
|
| 505 |
+
"grad_norm": 5.742042541503906,
|
| 506 |
+
"learning_rate": 2.3453017265505673e-05,
|
| 507 |
+
"loss": 10.0186,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.7216494845360825,
|
| 512 |
+
"grad_norm": 7.58469295501709,
|
| 513 |
+
"learning_rate": 2.194064673188089e-05,
|
| 514 |
+
"loss": 10.1395,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.7319587628865979,
|
| 519 |
+
"grad_norm": 9.0633544921875,
|
| 520 |
+
"learning_rate": 2.0464860241772455e-05,
|
| 521 |
+
"loss": 10.7651,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.7422680412371134,
|
| 526 |
+
"grad_norm": 13.465816497802734,
|
| 527 |
+
"learning_rate": 1.902758193921385e-05,
|
| 528 |
+
"loss": 11.2877,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.7525773195876289,
|
| 533 |
+
"grad_norm": 2.8348264694213867,
|
| 534 |
+
"learning_rate": 1.7630685760908622e-05,
|
| 535 |
+
"loss": 8.8791,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.7628865979381443,
|
| 540 |
+
"grad_norm": 2.8698973655700684,
|
| 541 |
+
"learning_rate": 1.6275992992974308e-05,
|
| 542 |
+
"loss": 9.1762,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.7731958762886598,
|
| 547 |
+
"grad_norm": 2.901054859161377,
|
| 548 |
+
"learning_rate": 1.4965269896332885e-05,
|
| 549 |
+
"loss": 9.4653,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.7835051546391752,
|
| 554 |
+
"grad_norm": 2.7682125568389893,
|
| 555 |
+
"learning_rate": 1.3700225403843469e-05,
|
| 556 |
+
"loss": 8.8307,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.7938144329896907,
|
| 561 |
+
"grad_norm": 2.992018461227417,
|
| 562 |
+
"learning_rate": 1.2482508892179884e-05,
|
| 563 |
+
"loss": 9.4491,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.8041237113402062,
|
| 568 |
+
"grad_norm": 3.0246708393096924,
|
| 569 |
+
"learning_rate": 1.1313708031358183e-05,
|
| 570 |
+
"loss": 8.9525,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.8144329896907216,
|
| 575 |
+
"grad_norm": 3.0064706802368164,
|
| 576 |
+
"learning_rate": 1.0195346714717813e-05,
|
| 577 |
+
"loss": 8.53,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.8247422680412371,
|
| 582 |
+
"grad_norm": 3.0492849349975586,
|
| 583 |
+
"learning_rate": 9.12888307205541e-06,
|
| 584 |
+
"loss": 8.8614,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.8350515463917526,
|
| 589 |
+
"grad_norm": 3.388885974884033,
|
| 590 |
+
"learning_rate": 8.115707568501768e-06,
|
| 591 |
+
"loss": 9.3091,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.845360824742268,
|
| 596 |
+
"grad_norm": 3.690394401550293,
|
| 597 |
+
"learning_rate": 7.157141191620548e-06,
|
| 598 |
+
"loss": 9.4763,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.8556701030927835,
|
| 603 |
+
"grad_norm": 3.538125514984131,
|
| 604 |
+
"learning_rate": 6.2544337290925185e-06,
|
| 605 |
+
"loss": 8.9925,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.865979381443299,
|
| 610 |
+
"grad_norm": 3.762061834335327,
|
| 611 |
+
"learning_rate": 5.408762139230888e-06,
|
| 612 |
+
"loss": 9.3558,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.8762886597938144,
|
| 617 |
+
"grad_norm": 3.6624767780303955,
|
| 618 |
+
"learning_rate": 4.621229016452156e-06,
|
| 619 |
+
"loss": 9.5321,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.8865979381443299,
|
| 624 |
+
"grad_norm": 4.024722099304199,
|
| 625 |
+
"learning_rate": 3.892861153703342e-06,
|
| 626 |
+
"loss": 9.2549,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.8969072164948454,
|
| 631 |
+
"grad_norm": 4.6499409675598145,
|
| 632 |
+
"learning_rate": 3.2246082037199532e-06,
|
| 633 |
+
"loss": 8.8971,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.9072164948453608,
|
| 638 |
+
"grad_norm": 4.980355739593506,
|
| 639 |
+
"learning_rate": 2.6173414408598827e-06,
|
| 640 |
+
"loss": 9.8878,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.9175257731958762,
|
| 645 |
+
"grad_norm": 4.445894241333008,
|
| 646 |
+
"learning_rate": 2.0718526251279346e-06,
|
| 647 |
+
"loss": 9.3811,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.9278350515463918,
|
| 652 |
+
"grad_norm": 5.819360256195068,
|
| 653 |
+
"learning_rate": 1.5888529698718346e-06,
|
| 654 |
+
"loss": 9.7881,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.9381443298969072,
|
| 659 |
+
"grad_norm": 4.284760475158691,
|
| 660 |
+
"learning_rate": 1.1689722144956671e-06,
|
| 661 |
+
"loss": 9.7274,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.9484536082474226,
|
| 666 |
+
"grad_norm": 4.918863296508789,
|
| 667 |
+
"learning_rate": 8.127578033998662e-07,
|
| 668 |
+
"loss": 9.4289,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.9587628865979382,
|
| 673 |
+
"grad_norm": 4.962632656097412,
|
| 674 |
+
"learning_rate": 5.206741722181386e-07,
|
| 675 |
+
"loss": 9.3278,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.9690721649484536,
|
| 680 |
+
"grad_norm": 6.412735462188721,
|
| 681 |
+
"learning_rate": 2.9310214228202013e-07,
|
| 682 |
+
"loss": 9.6937,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.979381443298969,
|
| 687 |
+
"grad_norm": 7.41445779800415,
|
| 688 |
+
"learning_rate": 1.3033842410251075e-07,
|
| 689 |
+
"loss": 10.3619,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.9896907216494846,
|
| 694 |
+
"grad_norm": 15.090306282043457,
|
| 695 |
+
"learning_rate": 3.259523051615254e-08,
|
| 696 |
+
"loss": 10.6881,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 1.0,
|
| 701 |
+
"grad_norm": 7.387956619262695,
|
| 702 |
+
"learning_rate": 0.0,
|
| 703 |
+
"loss": 9.4936,
|
| 704 |
+
"step": 97
|
| 705 |
}
|
| 706 |
],
|
| 707 |
"logging_steps": 1,
|
|
|
|
| 725 |
"should_evaluate": false,
|
| 726 |
"should_log": false,
|
| 727 |
"should_save": true,
|
| 728 |
+
"should_training_stop": true
|
| 729 |
},
|
| 730 |
"attributes": {}
|
| 731 |
}
|
| 732 |
},
|
| 733 |
+
"total_flos": 2.4188338220669338e+17,
|
| 734 |
"train_batch_size": 8,
|
| 735 |
"trial_name": null,
|
| 736 |
"trial_params": null
|