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 767856
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f60d2e9ae32d1985aa65462862ca4b70c3a8998e596c04a5f721ece25854dbe1
|
| 3 |
size 767856
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1601338
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82f30fd5719e050daf7167fa83b2a9cab144fb5fbf8a1cecc61e1b04d9d5a001
|
| 3 |
size 1601338
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14512
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:486cd21b30f7f4b647912779f0f99f9cd55f4d5bc4247b3ed077084036f1e10a
|
| 3 |
size 14512
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14512
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19ca30fccc09c76ea95914a475456a7ee2561fa696312099871f01293924d014
|
| 3 |
size 14512
|
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:ba41b4d003bf4f315ef5ca1f1b9201e78a8c869e239253754ed9ce404d87fd4f
|
| 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": 39.139,
|
| 374 |
"eval_steps_per_second": 9.843,
|
| 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": 0.505369551484523,
|
| 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": 39.139,
|
| 374 |
"eval_steps_per_second": 9.843,
|
| 375 |
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.25773847125710675,
|
| 379 |
+
"grad_norm": 2.438196897506714,
|
| 380 |
+
"learning_rate": 9.99885820390154e-05,
|
| 381 |
+
"loss": 9.9308,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.262792166771952,
|
| 386 |
+
"grad_norm": 2.2800676822662354,
|
| 387 |
+
"learning_rate": 9.995433337085491e-05,
|
| 388 |
+
"loss": 9.7762,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.26784586228679724,
|
| 393 |
+
"grad_norm": 2.2999722957611084,
|
| 394 |
+
"learning_rate": 9.989726963751682e-05,
|
| 395 |
+
"loss": 9.6314,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.27289955780164243,
|
| 400 |
+
"grad_norm": 2.0864381790161133,
|
| 401 |
+
"learning_rate": 9.981741690106034e-05,
|
| 402 |
+
"loss": 9.5644,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.2779532533164877,
|
| 407 |
+
"grad_norm": 1.9628472328186035,
|
| 408 |
+
"learning_rate": 9.971481163170268e-05,
|
| 409 |
+
"loss": 9.6852,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.2830069488313329,
|
| 414 |
+
"grad_norm": 2.0100128650665283,
|
| 415 |
+
"learning_rate": 9.95895006911623e-05,
|
| 416 |
+
"loss": 9.532,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.2880606443461781,
|
| 421 |
+
"grad_norm": 1.903132438659668,
|
| 422 |
+
"learning_rate": 9.944154131125642e-05,
|
| 423 |
+
"loss": 9.5968,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.29311433986102337,
|
| 428 |
+
"grad_norm": 1.8894416093826294,
|
| 429 |
+
"learning_rate": 9.927100106776212e-05,
|
| 430 |
+
"loss": 9.45,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.2981680353758686,
|
| 435 |
+
"grad_norm": 1.8624144792556763,
|
| 436 |
+
"learning_rate": 9.907795784955327e-05,
|
| 437 |
+
"loss": 9.462,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.30322173089071386,
|
| 442 |
+
"grad_norm": 1.88225519657135,
|
| 443 |
+
"learning_rate": 9.88624998230272e-05,
|
| 444 |
+
"loss": 9.3977,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.30827542640555905,
|
| 449 |
+
"grad_norm": 1.9469467401504517,
|
| 450 |
+
"learning_rate": 9.862472539183756e-05,
|
| 451 |
+
"loss": 9.2517,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.3133291219204043,
|
| 456 |
+
"grad_norm": 1.6683619022369385,
|
| 457 |
+
"learning_rate": 9.836474315195147e-05,
|
| 458 |
+
"loss": 9.4305,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.31838281743524954,
|
| 463 |
+
"grad_norm": 1.663127064704895,
|
| 464 |
+
"learning_rate": 9.808267184205183e-05,
|
| 465 |
+
"loss": 9.2934,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.32343651295009473,
|
| 470 |
+
"grad_norm": 1.6440531015396118,
|
| 471 |
+
"learning_rate": 9.777864028930705e-05,
|
| 472 |
+
"loss": 9.3013,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.32849020846494,
|
| 477 |
+
"grad_norm": 1.6826865673065186,
|
| 478 |
+
"learning_rate": 9.745278735053343e-05,
|
| 479 |
+
"loss": 9.2594,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.33354390397978523,
|
| 484 |
+
"grad_norm": 1.596401572227478,
|
| 485 |
+
"learning_rate": 9.710526184877667e-05,
|
| 486 |
+
"loss": 9.2143,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.3385975994946305,
|
| 491 |
+
"grad_norm": 1.764570951461792,
|
| 492 |
+
"learning_rate": 9.673622250534156e-05,
|
| 493 |
+
"loss": 9.0152,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.34365129500947567,
|
| 498 |
+
"grad_norm": 1.5638481378555298,
|
| 499 |
+
"learning_rate": 9.63458378673011e-05,
|
| 500 |
+
"loss": 9.1172,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.3487049905243209,
|
| 505 |
+
"grad_norm": 1.5338134765625,
|
| 506 |
+
"learning_rate": 9.593428623051792e-05,
|
| 507 |
+
"loss": 9.0363,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.35375868603916616,
|
| 512 |
+
"grad_norm": 1.6992957592010498,
|
| 513 |
+
"learning_rate": 9.550175555821333e-05,
|
| 514 |
+
"loss": 9.0962,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.35881238155401135,
|
| 519 |
+
"grad_norm": 1.6055617332458496,
|
| 520 |
+
"learning_rate": 9.504844339512095e-05,
|
| 521 |
+
"loss": 9.1217,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.3638660770688566,
|
| 526 |
+
"grad_norm": 1.7240350246429443,
|
| 527 |
+
"learning_rate": 9.457455677726448e-05,
|
| 528 |
+
"loss": 9.2245,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.36891977258370184,
|
| 533 |
+
"grad_norm": 1.9936858415603638,
|
| 534 |
+
"learning_rate": 9.408031213740045e-05,
|
| 535 |
+
"loss": 9.3585,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.37397346809854703,
|
| 540 |
+
"grad_norm": 2.1292333602905273,
|
| 541 |
+
"learning_rate": 9.356593520616948e-05,
|
| 542 |
+
"loss": 9.4107,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.3790271636133923,
|
| 547 |
+
"grad_norm": 3.4360055923461914,
|
| 548 |
+
"learning_rate": 9.303166090900082e-05,
|
| 549 |
+
"loss": 9.1299,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.38408085912823753,
|
| 554 |
+
"grad_norm": 1.3017970323562622,
|
| 555 |
+
"learning_rate": 9.24777332588177e-05,
|
| 556 |
+
"loss": 9.224,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.3891345546430828,
|
| 561 |
+
"grad_norm": 1.1683531999588013,
|
| 562 |
+
"learning_rate": 9.190440524459203e-05,
|
| 563 |
+
"loss": 9.2729,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.39418825015792797,
|
| 568 |
+
"grad_norm": 1.235701084136963,
|
| 569 |
+
"learning_rate": 9.131193871579975e-05,
|
| 570 |
+
"loss": 9.0347,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.3992419456727732,
|
| 575 |
+
"grad_norm": 1.1109133958816528,
|
| 576 |
+
"learning_rate": 9.070060426282925e-05,
|
| 577 |
+
"loss": 9.0375,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.40429564118761846,
|
| 582 |
+
"grad_norm": 1.2668910026550293,
|
| 583 |
+
"learning_rate": 9.007068109339784e-05,
|
| 584 |
+
"loss": 8.9948,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.40934933670246365,
|
| 589 |
+
"grad_norm": 1.3104698657989502,
|
| 590 |
+
"learning_rate": 8.942245690503239e-05,
|
| 591 |
+
"loss": 8.9623,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.4144030322173089,
|
| 596 |
+
"grad_norm": 1.198638916015625,
|
| 597 |
+
"learning_rate": 8.87562277536726e-05,
|
| 598 |
+
"loss": 9.0571,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.41945672773215414,
|
| 603 |
+
"grad_norm": 1.2889971733093262,
|
| 604 |
+
"learning_rate": 8.807229791845673e-05,
|
| 605 |
+
"loss": 8.9898,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.4245104232469994,
|
| 610 |
+
"grad_norm": 1.2756685018539429,
|
| 611 |
+
"learning_rate": 8.737097976275178e-05,
|
| 612 |
+
"loss": 8.896,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.4295641187618446,
|
| 617 |
+
"grad_norm": 1.1489578485488892,
|
| 618 |
+
"learning_rate": 8.665259359149132e-05,
|
| 619 |
+
"loss": 9.067,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.43461781427668983,
|
| 624 |
+
"grad_norm": 1.1491981744766235,
|
| 625 |
+
"learning_rate": 8.591746750488639e-05,
|
| 626 |
+
"loss": 8.8872,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.4396715097915351,
|
| 631 |
+
"grad_norm": 1.072772741317749,
|
| 632 |
+
"learning_rate": 8.516593724857598e-05,
|
| 633 |
+
"loss": 8.887,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.44472520530638027,
|
| 638 |
+
"grad_norm": 1.0014466047286987,
|
| 639 |
+
"learning_rate": 8.439834606028594e-05,
|
| 640 |
+
"loss": 8.8939,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.4497789008212255,
|
| 645 |
+
"grad_norm": 1.1188455820083618,
|
| 646 |
+
"learning_rate": 8.361504451306585e-05,
|
| 647 |
+
"loss": 8.7898,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.45483259633607076,
|
| 652 |
+
"grad_norm": 1.039220929145813,
|
| 653 |
+
"learning_rate": 8.28163903551759e-05,
|
| 654 |
+
"loss": 8.8616,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.459886291850916,
|
| 659 |
+
"grad_norm": 1.1389069557189941,
|
| 660 |
+
"learning_rate": 8.200274834669675e-05,
|
| 661 |
+
"loss": 8.7895,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.4649399873657612,
|
| 666 |
+
"grad_norm": 1.1462750434875488,
|
| 667 |
+
"learning_rate": 8.117449009293668e-05,
|
| 668 |
+
"loss": 8.8468,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.46999368288060644,
|
| 673 |
+
"grad_norm": 1.1461669206619263,
|
| 674 |
+
"learning_rate": 8.033199387471277e-05,
|
| 675 |
+
"loss": 8.7652,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.4750473783954517,
|
| 680 |
+
"grad_norm": 1.254766583442688,
|
| 681 |
+
"learning_rate": 7.9475644475583e-05,
|
| 682 |
+
"loss": 8.612,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.4801010739102969,
|
| 687 |
+
"grad_norm": 1.3156293630599976,
|
| 688 |
+
"learning_rate": 7.860583300610849e-05,
|
| 689 |
+
"loss": 8.7556,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.48515476942514213,
|
| 694 |
+
"grad_norm": 1.2289044857025146,
|
| 695 |
+
"learning_rate": 7.772295672522615e-05,
|
| 696 |
+
"loss": 8.8208,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.4902084649399874,
|
| 701 |
+
"grad_norm": 1.7439113855361938,
|
| 702 |
+
"learning_rate": 7.682741885881315e-05,
|
| 703 |
+
"loss": 9.0702,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.4952621604548326,
|
| 708 |
+
"grad_norm": 1.3451626300811768,
|
| 709 |
+
"learning_rate": 7.591962841552627e-05,
|
| 710 |
+
"loss": 8.8565,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.5003158559696779,
|
| 715 |
+
"grad_norm": 1.7298027276992798,
|
| 716 |
+
"learning_rate": 7.500000000000001e-05,
|
| 717 |
+
"loss": 9.0691,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.505369551484523,
|
| 722 |
+
"grad_norm": 2.368654727935791,
|
| 723 |
+
"learning_rate": 7.406895362348916e-05,
|
| 724 |
+
"loss": 8.8959,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.505369551484523,
|
| 729 |
+
"eval_loss": 8.748159408569336,
|
| 730 |
+
"eval_runtime": 8.2562,
|
| 731 |
+
"eval_samples_per_second": 40.455,
|
| 732 |
+
"eval_steps_per_second": 10.174,
|
| 733 |
+
"step": 100
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
|
|
| 750 |
"attributes": {}
|
| 751 |
}
|
| 752 |
},
|
| 753 |
+
"total_flos": 113484993921024.0,
|
| 754 |
"train_batch_size": 2,
|
| 755 |
"trial_name": null,
|
| 756 |
"trial_params": null
|