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 167832240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb88684cfafcd438ba0d2b9d9af3a7be2a7a87f17b1fc76839bb3a5b5be8ca63
|
| 3 |
size 167832240
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 335922386
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31cb0b24d91fd82b0e5de438f3f7332029266fa5f9a68a220cdd61dc4f096f29
|
| 3 |
size 335922386
|
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 sha256:4092a550b12144cfbd52f651bb3cf2e7f01e3dd71c726d1720dd8d68f5c254b2
|
| 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:c5d2a6c6aafc669cea03b9634666f204de949a3d45ce2f48a07e7e3eaf18c715
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 25,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -381,6 +381,372 @@
|
|
| 381 |
"eval_samples_per_second": 11.819,
|
| 382 |
"eval_steps_per_second": 1.655,
|
| 383 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 384 |
}
|
| 385 |
],
|
| 386 |
"logging_steps": 1,
|
|
@@ -409,7 +775,7 @@
|
|
| 409 |
"attributes": {}
|
| 410 |
}
|
| 411 |
},
|
| 412 |
-
"total_flos":
|
| 413 |
"train_batch_size": 8,
|
| 414 |
"trial_name": null,
|
| 415 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.23561157286167145,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 0.049813200498132,
|
| 5 |
"eval_steps": 25,
|
| 6 |
+
"global_step": 100,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 381 |
"eval_samples_per_second": 11.819,
|
| 382 |
"eval_steps_per_second": 1.655,
|
| 383 |
"step": 50
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.025404732254047324,
|
| 387 |
+
"grad_norm": 1.4346284866333008,
|
| 388 |
+
"learning_rate": 0.0002668315918143169,
|
| 389 |
+
"loss": 0.2574,
|
| 390 |
+
"step": 51
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.025902864259028643,
|
| 394 |
+
"grad_norm": 1.349393367767334,
|
| 395 |
+
"learning_rate": 0.00026526016662852886,
|
| 396 |
+
"loss": 0.2641,
|
| 397 |
+
"step": 52
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.026400996264009963,
|
| 401 |
+
"grad_norm": 2.0565531253814697,
|
| 402 |
+
"learning_rate": 0.00026365723046405023,
|
| 403 |
+
"loss": 0.3113,
|
| 404 |
+
"step": 53
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.026899128268991282,
|
| 408 |
+
"grad_norm": 1.7186627388000488,
|
| 409 |
+
"learning_rate": 0.0002620232215476231,
|
| 410 |
+
"loss": 0.2532,
|
| 411 |
+
"step": 54
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.0273972602739726,
|
| 415 |
+
"grad_norm": 1.5477849245071411,
|
| 416 |
+
"learning_rate": 0.0002603585866009697,
|
| 417 |
+
"loss": 0.3041,
|
| 418 |
+
"step": 55
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.027895392278953924,
|
| 422 |
+
"grad_norm": 1.3647983074188232,
|
| 423 |
+
"learning_rate": 0.00025866378071866334,
|
| 424 |
+
"loss": 0.2715,
|
| 425 |
+
"step": 56
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.028393524283935243,
|
| 429 |
+
"grad_norm": 1.3015156984329224,
|
| 430 |
+
"learning_rate": 0.00025693926724370956,
|
| 431 |
+
"loss": 0.2774,
|
| 432 |
+
"step": 57
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.028891656288916562,
|
| 436 |
+
"grad_norm": 1.343042254447937,
|
| 437 |
+
"learning_rate": 0.00025518551764087326,
|
| 438 |
+
"loss": 0.1843,
|
| 439 |
+
"step": 58
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.029389788293897882,
|
| 443 |
+
"grad_norm": 1.6829490661621094,
|
| 444 |
+
"learning_rate": 0.00025340301136778483,
|
| 445 |
+
"loss": 0.3086,
|
| 446 |
+
"step": 59
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.029887920298879204,
|
| 450 |
+
"grad_norm": 1.5559968948364258,
|
| 451 |
+
"learning_rate": 0.00025159223574386114,
|
| 452 |
+
"loss": 0.245,
|
| 453 |
+
"step": 60
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.030386052303860524,
|
| 457 |
+
"grad_norm": 1.6984091997146606,
|
| 458 |
+
"learning_rate": 0.0002497536858170772,
|
| 459 |
+
"loss": 0.2805,
|
| 460 |
+
"step": 61
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.030884184308841843,
|
| 464 |
+
"grad_norm": 1.6316205263137817,
|
| 465 |
+
"learning_rate": 0.00024788786422862526,
|
| 466 |
+
"loss": 0.2328,
|
| 467 |
+
"step": 62
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.03138231631382316,
|
| 471 |
+
"grad_norm": 1.7361657619476318,
|
| 472 |
+
"learning_rate": 0.00024599528107549745,
|
| 473 |
+
"loss": 0.358,
|
| 474 |
+
"step": 63
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.03188044831880448,
|
| 478 |
+
"grad_norm": 1.2437626123428345,
|
| 479 |
+
"learning_rate": 0.00024407645377103054,
|
| 480 |
+
"loss": 0.1992,
|
| 481 |
+
"step": 64
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.0323785803237858,
|
| 485 |
+
"grad_norm": 1.4107438325881958,
|
| 486 |
+
"learning_rate": 0.00024213190690345018,
|
| 487 |
+
"loss": 0.261,
|
| 488 |
+
"step": 65
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.03287671232876712,
|
| 492 |
+
"grad_norm": 1.0943936109542847,
|
| 493 |
+
"learning_rate": 0.00024016217209245374,
|
| 494 |
+
"loss": 0.1947,
|
| 495 |
+
"step": 66
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.033374844333748446,
|
| 499 |
+
"grad_norm": 1.371076226234436,
|
| 500 |
+
"learning_rate": 0.00023816778784387094,
|
| 501 |
+
"loss": 0.1723,
|
| 502 |
+
"step": 67
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.033872976338729766,
|
| 506 |
+
"grad_norm": 1.8774269819259644,
|
| 507 |
+
"learning_rate": 0.0002361492994024415,
|
| 508 |
+
"loss": 0.3099,
|
| 509 |
+
"step": 68
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.034371108343711085,
|
| 513 |
+
"grad_norm": 1.5689069032669067,
|
| 514 |
+
"learning_rate": 0.0002341072586027509,
|
| 515 |
+
"loss": 0.2458,
|
| 516 |
+
"step": 69
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.034869240348692404,
|
| 520 |
+
"grad_norm": 1.4060947895050049,
|
| 521 |
+
"learning_rate": 0.00023204222371836405,
|
| 522 |
+
"loss": 0.2045,
|
| 523 |
+
"step": 70
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 0.03536737235367372,
|
| 527 |
+
"grad_norm": 1.5080294609069824,
|
| 528 |
+
"learning_rate": 0.00022995475930919905,
|
| 529 |
+
"loss": 0.2674,
|
| 530 |
+
"step": 71
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.03586550435865504,
|
| 534 |
+
"grad_norm": 2.0735766887664795,
|
| 535 |
+
"learning_rate": 0.00022784543606718227,
|
| 536 |
+
"loss": 0.268,
|
| 537 |
+
"step": 72
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.03636363636363636,
|
| 541 |
+
"grad_norm": 1.7785519361495972,
|
| 542 |
+
"learning_rate": 0.00022571483066022657,
|
| 543 |
+
"loss": 0.4725,
|
| 544 |
+
"step": 73
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.03686176836861768,
|
| 548 |
+
"grad_norm": 1.6680009365081787,
|
| 549 |
+
"learning_rate": 0.0002235635255745762,
|
| 550 |
+
"loss": 0.1942,
|
| 551 |
+
"step": 74
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.037359900373599,
|
| 555 |
+
"grad_norm": 1.2794748544692993,
|
| 556 |
+
"learning_rate": 0.00022139210895556104,
|
| 557 |
+
"loss": 0.1952,
|
| 558 |
+
"step": 75
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 0.037359900373599,
|
| 562 |
+
"eval_loss": 0.24085499346256256,
|
| 563 |
+
"eval_runtime": 4.2231,
|
| 564 |
+
"eval_samples_per_second": 11.84,
|
| 565 |
+
"eval_steps_per_second": 1.658,
|
| 566 |
+
"step": 75
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.03785803237858033,
|
| 570 |
+
"grad_norm": 2.097665309906006,
|
| 571 |
+
"learning_rate": 0.00021920117444680317,
|
| 572 |
+
"loss": 0.2742,
|
| 573 |
+
"step": 76
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.038356164383561646,
|
| 577 |
+
"grad_norm": 2.0213897228240967,
|
| 578 |
+
"learning_rate": 0.00021699132102792097,
|
| 579 |
+
"loss": 0.3291,
|
| 580 |
+
"step": 77
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 0.038854296388542965,
|
| 584 |
+
"grad_norm": 1.8470332622528076,
|
| 585 |
+
"learning_rate": 0.0002147631528507739,
|
| 586 |
+
"loss": 0.3145,
|
| 587 |
+
"step": 78
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 0.039352428393524284,
|
| 591 |
+
"grad_norm": 1.370811104774475,
|
| 592 |
+
"learning_rate": 0.00021251727907429355,
|
| 593 |
+
"loss": 0.2163,
|
| 594 |
+
"step": 79
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.039850560398505604,
|
| 598 |
+
"grad_norm": 1.4120204448699951,
|
| 599 |
+
"learning_rate": 0.0002102543136979454,
|
| 600 |
+
"loss": 0.2512,
|
| 601 |
+
"step": 80
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.04034869240348692,
|
| 605 |
+
"grad_norm": 1.5628596544265747,
|
| 606 |
+
"learning_rate": 0.0002079748753938678,
|
| 607 |
+
"loss": 0.2742,
|
| 608 |
+
"step": 81
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.04084682440846824,
|
| 612 |
+
"grad_norm": 1.351811408996582,
|
| 613 |
+
"learning_rate": 0.0002056795873377331,
|
| 614 |
+
"loss": 0.2858,
|
| 615 |
+
"step": 82
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.04134495641344956,
|
| 619 |
+
"grad_norm": 1.495460033416748,
|
| 620 |
+
"learning_rate": 0.00020336907703837748,
|
| 621 |
+
"loss": 0.2085,
|
| 622 |
+
"step": 83
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 0.04184308841843088,
|
| 626 |
+
"grad_norm": 1.1618963479995728,
|
| 627 |
+
"learning_rate": 0.00020104397616624645,
|
| 628 |
+
"loss": 0.256,
|
| 629 |
+
"step": 84
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 0.04234122042341221,
|
| 633 |
+
"grad_norm": 1.481665015220642,
|
| 634 |
+
"learning_rate": 0.00019870492038070252,
|
| 635 |
+
"loss": 0.267,
|
| 636 |
+
"step": 85
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 0.042839352428393526,
|
| 640 |
+
"grad_norm": 0.9506065249443054,
|
| 641 |
+
"learning_rate": 0.0001963525491562421,
|
| 642 |
+
"loss": 0.1691,
|
| 643 |
+
"step": 86
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 0.043337484433374845,
|
| 647 |
+
"grad_norm": 1.7585303783416748,
|
| 648 |
+
"learning_rate": 0.0001939875056076697,
|
| 649 |
+
"loss": 0.2362,
|
| 650 |
+
"step": 87
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.043835616438356165,
|
| 654 |
+
"grad_norm": 1.6562221050262451,
|
| 655 |
+
"learning_rate": 0.00019161043631427666,
|
| 656 |
+
"loss": 0.2178,
|
| 657 |
+
"step": 88
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.044333748443337484,
|
| 661 |
+
"grad_norm": 1.6594310998916626,
|
| 662 |
+
"learning_rate": 0.00018922199114307294,
|
| 663 |
+
"loss": 0.2027,
|
| 664 |
+
"step": 89
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 0.0448318804483188,
|
| 668 |
+
"grad_norm": 2.217742443084717,
|
| 669 |
+
"learning_rate": 0.00018682282307111987,
|
| 670 |
+
"loss": 0.2966,
|
| 671 |
+
"step": 90
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 0.04533001245330012,
|
| 675 |
+
"grad_norm": 1.4910566806793213,
|
| 676 |
+
"learning_rate": 0.00018441358800701273,
|
| 677 |
+
"loss": 0.179,
|
| 678 |
+
"step": 91
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 0.04582814445828144,
|
| 682 |
+
"grad_norm": 2.0381054878234863,
|
| 683 |
+
"learning_rate": 0.00018199494461156203,
|
| 684 |
+
"loss": 0.3568,
|
| 685 |
+
"step": 92
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 0.04632627646326277,
|
| 689 |
+
"grad_norm": 1.7185461521148682,
|
| 690 |
+
"learning_rate": 0.000179567554117722,
|
| 691 |
+
"loss": 0.2823,
|
| 692 |
+
"step": 93
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.04682440846824409,
|
| 696 |
+
"grad_norm": 1.6253682374954224,
|
| 697 |
+
"learning_rate": 0.00017713208014981648,
|
| 698 |
+
"loss": 0.2248,
|
| 699 |
+
"step": 94
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.047322540473225407,
|
| 703 |
+
"grad_norm": 1.2121644020080566,
|
| 704 |
+
"learning_rate": 0.00017468918854211007,
|
| 705 |
+
"loss": 0.1926,
|
| 706 |
+
"step": 95
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.047820672478206726,
|
| 710 |
+
"grad_norm": 1.1331689357757568,
|
| 711 |
+
"learning_rate": 0.00017223954715677627,
|
| 712 |
+
"loss": 0.1632,
|
| 713 |
+
"step": 96
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.048318804483188045,
|
| 717 |
+
"grad_norm": 1.6569329500198364,
|
| 718 |
+
"learning_rate": 0.00016978382570131034,
|
| 719 |
+
"loss": 0.2536,
|
| 720 |
+
"step": 97
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.048816936488169364,
|
| 724 |
+
"grad_norm": 1.3067047595977783,
|
| 725 |
+
"learning_rate": 0.00016732269554543794,
|
| 726 |
+
"loss": 0.1937,
|
| 727 |
+
"step": 98
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.049315068493150684,
|
| 731 |
+
"grad_norm": 2.5061912536621094,
|
| 732 |
+
"learning_rate": 0.00016485682953756942,
|
| 733 |
+
"loss": 0.3301,
|
| 734 |
+
"step": 99
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.049813200498132,
|
| 738 |
+
"grad_norm": 1.3976527452468872,
|
| 739 |
+
"learning_rate": 0.00016238690182084986,
|
| 740 |
+
"loss": 0.2458,
|
| 741 |
+
"step": 100
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.049813200498132,
|
| 745 |
+
"eval_loss": 0.23561157286167145,
|
| 746 |
+
"eval_runtime": 4.2306,
|
| 747 |
+
"eval_samples_per_second": 11.819,
|
| 748 |
+
"eval_steps_per_second": 1.655,
|
| 749 |
+
"step": 100
|
| 750 |
}
|
| 751 |
],
|
| 752 |
"logging_steps": 1,
|
|
|
|
| 775 |
"attributes": {}
|
| 776 |
}
|
| 777 |
},
|
| 778 |
+
"total_flos": 1.576510477565952e+17,
|
| 779 |
"train_batch_size": 8,
|
| 780 |
"trial_name": null,
|
| 781 |
"trial_params": null
|