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 83945296
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27181cf1af8cd6ab09bdd6e86509935d6815cf8e2ba87b51987b3b929dbbf15e
|
| 3 |
size 83945296
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 43122580
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31903c9e1781861fe55c4c0d1bc48a981e34b9e68b3cb04073e11d1775cfbb59
|
| 3 |
size 43122580
|
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 sha256:355e76fc8598e2798497bc3f2005a10b27ba180fd974991d896736ff11192f57
|
| 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": 31.678,
|
| 374 |
"eval_steps_per_second": 15.839,
|
| 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": 0.030557677616501147,
|
| 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": 31.678,
|
| 374 |
"eval_steps_per_second": 15.839,
|
| 375 |
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.015584415584415584,
|
| 379 |
+
"grad_norm": 2.4259822368621826,
|
| 380 |
+
"learning_rate": 0.00017788772787621126,
|
| 381 |
+
"loss": 4.0701,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.015889992360580595,
|
| 386 |
+
"grad_norm": 1.828935146331787,
|
| 387 |
+
"learning_rate": 0.00017684011108568592,
|
| 388 |
+
"loss": 3.8272,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.016195569136745608,
|
| 393 |
+
"grad_norm": 1.6015702486038208,
|
| 394 |
+
"learning_rate": 0.0001757714869760335,
|
| 395 |
+
"loss": 4.0941,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.01650114591291062,
|
| 400 |
+
"grad_norm": 1.4622135162353516,
|
| 401 |
+
"learning_rate": 0.0001746821476984154,
|
| 402 |
+
"loss": 2.8427,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.01680672268907563,
|
| 407 |
+
"grad_norm": 2.106966018676758,
|
| 408 |
+
"learning_rate": 0.00017357239106731317,
|
| 409 |
+
"loss": 2.3866,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.017112299465240642,
|
| 414 |
+
"grad_norm": 2.9907472133636475,
|
| 415 |
+
"learning_rate": 0.00017244252047910892,
|
| 416 |
+
"loss": 3.2555,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.017417876241405655,
|
| 421 |
+
"grad_norm": 1.2781822681427002,
|
| 422 |
+
"learning_rate": 0.00017129284482913972,
|
| 423 |
+
"loss": 2.8657,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.017723453017570664,
|
| 428 |
+
"grad_norm": 1.5655877590179443,
|
| 429 |
+
"learning_rate": 0.00017012367842724887,
|
| 430 |
+
"loss": 2.6976,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.018029029793735676,
|
| 435 |
+
"grad_norm": 1.7124484777450562,
|
| 436 |
+
"learning_rate": 0.0001689353409118566,
|
| 437 |
+
"loss": 2.5161,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.01833460656990069,
|
| 442 |
+
"grad_norm": 2.1622180938720703,
|
| 443 |
+
"learning_rate": 0.00016772815716257412,
|
| 444 |
+
"loss": 2.9102,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.018640183346065698,
|
| 449 |
+
"grad_norm": 1.4135297536849976,
|
| 450 |
+
"learning_rate": 0.0001665024572113848,
|
| 451 |
+
"loss": 1.7485,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.01894576012223071,
|
| 456 |
+
"grad_norm": 1.8781421184539795,
|
| 457 |
+
"learning_rate": 0.00016525857615241687,
|
| 458 |
+
"loss": 3.8095,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.019251336898395723,
|
| 463 |
+
"grad_norm": 1.5626355409622192,
|
| 464 |
+
"learning_rate": 0.00016399685405033167,
|
| 465 |
+
"loss": 1.9366,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.019556913674560732,
|
| 470 |
+
"grad_norm": 1.412752389907837,
|
| 471 |
+
"learning_rate": 0.0001627176358473537,
|
| 472 |
+
"loss": 1.9336,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.019862490450725745,
|
| 477 |
+
"grad_norm": 5.998400688171387,
|
| 478 |
+
"learning_rate": 0.0001614212712689668,
|
| 479 |
+
"loss": 3.1919,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.020168067226890758,
|
| 484 |
+
"grad_norm": 1.5334243774414062,
|
| 485 |
+
"learning_rate": 0.00016010811472830252,
|
| 486 |
+
"loss": 2.7113,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.020473644003055767,
|
| 491 |
+
"grad_norm": 2.1354057788848877,
|
| 492 |
+
"learning_rate": 0.00015877852522924732,
|
| 493 |
+
"loss": 2.988,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.02077922077922078,
|
| 498 |
+
"grad_norm": 1.9327161312103271,
|
| 499 |
+
"learning_rate": 0.00015743286626829437,
|
| 500 |
+
"loss": 2.9572,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.021084797555385792,
|
| 505 |
+
"grad_norm": 2.1718881130218506,
|
| 506 |
+
"learning_rate": 0.0001560715057351673,
|
| 507 |
+
"loss": 3.5648,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.0213903743315508,
|
| 512 |
+
"grad_norm": 1.8955811262130737,
|
| 513 |
+
"learning_rate": 0.00015469481581224272,
|
| 514 |
+
"loss": 3.1244,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.021695951107715813,
|
| 519 |
+
"grad_norm": 1.5830830335617065,
|
| 520 |
+
"learning_rate": 0.0001533031728727994,
|
| 521 |
+
"loss": 2.7921,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.022001527883880826,
|
| 526 |
+
"grad_norm": 2.2739856243133545,
|
| 527 |
+
"learning_rate": 0.00015189695737812152,
|
| 528 |
+
"loss": 3.5455,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.022307104660045835,
|
| 533 |
+
"grad_norm": 0.9828822612762451,
|
| 534 |
+
"learning_rate": 0.0001504765537734844,
|
| 535 |
+
"loss": 1.6882,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.022612681436210848,
|
| 540 |
+
"grad_norm": 1.9325013160705566,
|
| 541 |
+
"learning_rate": 0.00014904235038305083,
|
| 542 |
+
"loss": 2.1146,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.02291825821237586,
|
| 547 |
+
"grad_norm": 1.3537631034851074,
|
| 548 |
+
"learning_rate": 0.00014759473930370736,
|
| 549 |
+
"loss": 2.2816,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.02322383498854087,
|
| 554 |
+
"grad_norm": 1.826690673828125,
|
| 555 |
+
"learning_rate": 0.0001461341162978688,
|
| 556 |
+
"loss": 1.5235,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.023529411764705882,
|
| 561 |
+
"grad_norm": 1.8681014776229858,
|
| 562 |
+
"learning_rate": 0.00014466088068528068,
|
| 563 |
+
"loss": 4.0703,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.023834988540870895,
|
| 568 |
+
"grad_norm": 4.881453514099121,
|
| 569 |
+
"learning_rate": 0.00014317543523384928,
|
| 570 |
+
"loss": 3.2547,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.024140565317035904,
|
| 575 |
+
"grad_norm": 2.301090955734253,
|
| 576 |
+
"learning_rate": 0.00014167818604952906,
|
| 577 |
+
"loss": 2.3378,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.024446142093200916,
|
| 582 |
+
"grad_norm": 1.1395305395126343,
|
| 583 |
+
"learning_rate": 0.00014016954246529696,
|
| 584 |
+
"loss": 1.5157,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.02475171886936593,
|
| 589 |
+
"grad_norm": 1.7658803462982178,
|
| 590 |
+
"learning_rate": 0.00013864991692924523,
|
| 591 |
+
"loss": 4.2361,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.025057295645530938,
|
| 596 |
+
"grad_norm": 1.827609896659851,
|
| 597 |
+
"learning_rate": 0.00013711972489182208,
|
| 598 |
+
"loss": 3.0601,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.02536287242169595,
|
| 603 |
+
"grad_norm": 1.9651907682418823,
|
| 604 |
+
"learning_rate": 0.00013557938469225167,
|
| 605 |
+
"loss": 3.6306,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.025668449197860963,
|
| 610 |
+
"grad_norm": 2.074267625808716,
|
| 611 |
+
"learning_rate": 0.00013402931744416433,
|
| 612 |
+
"loss": 2.9667,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.025974025974025976,
|
| 617 |
+
"grad_norm": 1.3315553665161133,
|
| 618 |
+
"learning_rate": 0.00013246994692046836,
|
| 619 |
+
"loss": 1.88,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.026279602750190985,
|
| 624 |
+
"grad_norm": 1.5968420505523682,
|
| 625 |
+
"learning_rate": 0.00013090169943749476,
|
| 626 |
+
"loss": 3.7276,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.026585179526355997,
|
| 631 |
+
"grad_norm": 1.9459774494171143,
|
| 632 |
+
"learning_rate": 0.0001293250037384465,
|
| 633 |
+
"loss": 2.5366,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.02689075630252101,
|
| 638 |
+
"grad_norm": 1.9473600387573242,
|
| 639 |
+
"learning_rate": 0.00012774029087618446,
|
| 640 |
+
"loss": 3.8513,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.02719633307868602,
|
| 645 |
+
"grad_norm": 1.4431513547897339,
|
| 646 |
+
"learning_rate": 0.00012614799409538198,
|
| 647 |
+
"loss": 2.5023,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.02750190985485103,
|
| 652 |
+
"grad_norm": 3.223552703857422,
|
| 653 |
+
"learning_rate": 0.00012454854871407994,
|
| 654 |
+
"loss": 2.0943,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.027807486631016044,
|
| 659 |
+
"grad_norm": 2.679762363433838,
|
| 660 |
+
"learning_rate": 0.00012294239200467516,
|
| 661 |
+
"loss": 3.3053,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.028113063407181053,
|
| 666 |
+
"grad_norm": 2.0697975158691406,
|
| 667 |
+
"learning_rate": 0.0001213299630743747,
|
| 668 |
+
"loss": 3.5176,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.028418640183346066,
|
| 673 |
+
"grad_norm": 2.661999464035034,
|
| 674 |
+
"learning_rate": 0.00011971170274514802,
|
| 675 |
+
"loss": 3.7355,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.02872421695951108,
|
| 680 |
+
"grad_norm": 1.8615680932998657,
|
| 681 |
+
"learning_rate": 0.000118088053433211,
|
| 682 |
+
"loss": 2.0932,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.029029793735676088,
|
| 687 |
+
"grad_norm": 2.583749532699585,
|
| 688 |
+
"learning_rate": 0.00011645945902807341,
|
| 689 |
+
"loss": 4.0713,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.0293353705118411,
|
| 694 |
+
"grad_norm": 1.8530974388122559,
|
| 695 |
+
"learning_rate": 0.0001148263647711842,
|
| 696 |
+
"loss": 1.5702,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.029640947288006113,
|
| 701 |
+
"grad_norm": 1.7810598611831665,
|
| 702 |
+
"learning_rate": 0.00011318921713420691,
|
| 703 |
+
"loss": 3.71,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.029946524064171122,
|
| 708 |
+
"grad_norm": 2.1363232135772705,
|
| 709 |
+
"learning_rate": 0.00011154846369695863,
|
| 710 |
+
"loss": 3.1915,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.030252100840336135,
|
| 715 |
+
"grad_norm": 1.8341383934020996,
|
| 716 |
+
"learning_rate": 0.0001099045530250463,
|
| 717 |
+
"loss": 2.4543,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.030557677616501147,
|
| 722 |
+
"grad_norm": 1.8934003114700317,
|
| 723 |
+
"learning_rate": 0.00010825793454723325,
|
| 724 |
+
"loss": 2.6079,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.030557677616501147,
|
| 729 |
+
"eval_loss": 3.186122417449951,
|
| 730 |
+
"eval_runtime": 43.6356,
|
| 731 |
+
"eval_samples_per_second": 31.58,
|
| 732 |
+
"eval_steps_per_second": 15.79,
|
| 733 |
+
"step": 100
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
|
|
| 750 |
"attributes": {}
|
| 751 |
}
|
| 752 |
},
|
| 753 |
+
"total_flos": 1.895803354349568e+16,
|
| 754 |
"train_batch_size": 2,
|
| 755 |
"trial_name": null,
|
| 756 |
"trial_params": null
|