Training in progress, step 94, 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 50503544
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52a3b51954c721f4e0f1a70f69c82689a0d13a3cfd8545a9ff2347d07b1107e7
|
| 3 |
size 50503544
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 101184122
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:960d4c684267a7b67d6e53f747c2044cfbbd699f1e9a423e22ecc02c0a59fba2
|
| 3 |
size 101184122
|
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 sha256:1de59d07a68b3279e0fc3a797a6401f62f72e97ad97b47278800d6d6ffbb91e1
|
| 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 sha256:13281551d9d2bd9876ec10c3b51e9aaa8758f61508cf9259298bab8540ebb4ab
|
| 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 sha256:67273009a321cf39fd65d544bab368c783d106793a780845817d1f7f88ead9de
|
| 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": 47,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -352,6 +352,343 @@
|
|
| 352 |
"eval_samples_per_second": 19.509,
|
| 353 |
"eval_steps_per_second": 4.877,
|
| 354 |
"step": 47
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 355 |
}
|
| 356 |
],
|
| 357 |
"logging_steps": 1,
|
|
@@ -371,7 +708,7 @@
|
|
| 371 |
"attributes": {}
|
| 372 |
}
|
| 373 |
},
|
| 374 |
-
"total_flos":
|
| 375 |
"train_batch_size": 2,
|
| 376 |
"trial_name": null,
|
| 377 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.5023380093520374,
|
| 5 |
"eval_steps": 47,
|
| 6 |
+
"global_step": 94,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 352 |
"eval_samples_per_second": 19.509,
|
| 353 |
"eval_steps_per_second": 4.877,
|
| 354 |
"step": 47
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.2565130260521042,
|
| 358 |
+
"grad_norm": 6.551794052124023,
|
| 359 |
+
"learning_rate": 0.00018644534887309944,
|
| 360 |
+
"loss": 3.9149,
|
| 361 |
+
"step": 48
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.2618570474281897,
|
| 365 |
+
"grad_norm": 6.568101406097412,
|
| 366 |
+
"learning_rate": 0.00018548440916607453,
|
| 367 |
+
"loss": 3.0155,
|
| 368 |
+
"step": 49
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.26720106880427524,
|
| 372 |
+
"grad_norm": 5.584553241729736,
|
| 373 |
+
"learning_rate": 0.00018449321837726208,
|
| 374 |
+
"loss": 2.9737,
|
| 375 |
+
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.2725450901803607,
|
| 379 |
+
"grad_norm": 17.561307907104492,
|
| 380 |
+
"learning_rate": 0.00018347212726762437,
|
| 381 |
+
"loss": 5.1934,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.27788911155644624,
|
| 386 |
+
"grad_norm": 18.844377517700195,
|
| 387 |
+
"learning_rate": 0.00018242149717919993,
|
| 388 |
+
"loss": 5.1302,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.2832331329325317,
|
| 393 |
+
"grad_norm": 10.627951622009277,
|
| 394 |
+
"learning_rate": 0.00018134169990723247,
|
| 395 |
+
"loss": 4.5663,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.28857715430861725,
|
| 400 |
+
"grad_norm": 6.735750198364258,
|
| 401 |
+
"learning_rate": 0.00018023311756860038,
|
| 402 |
+
"loss": 3.7202,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.2939211756847027,
|
| 407 |
+
"grad_norm": 4.434415817260742,
|
| 408 |
+
"learning_rate": 0.00017909614246659409,
|
| 409 |
+
"loss": 4.1791,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.29926519706078825,
|
| 414 |
+
"grad_norm": 4.674170017242432,
|
| 415 |
+
"learning_rate": 0.00017793117695208828,
|
| 416 |
+
"loss": 3.8663,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.3046092184368738,
|
| 421 |
+
"grad_norm": 5.160229206085205,
|
| 422 |
+
"learning_rate": 0.0001767386332811587,
|
| 423 |
+
"loss": 3.8715,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.30995323981295925,
|
| 428 |
+
"grad_norm": 4.293652057647705,
|
| 429 |
+
"learning_rate": 0.00017551893346919362,
|
| 430 |
+
"loss": 2.5835,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.3152972611890448,
|
| 435 |
+
"grad_norm": 4.6995625495910645,
|
| 436 |
+
"learning_rate": 0.0001742725091415517,
|
| 437 |
+
"loss": 2.7618,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.32064128256513025,
|
| 442 |
+
"grad_norm": 5.258271217346191,
|
| 443 |
+
"learning_rate": 0.00017299980138081922,
|
| 444 |
+
"loss": 3.1181,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.3259853039412158,
|
| 449 |
+
"grad_norm": 3.5829501152038574,
|
| 450 |
+
"learning_rate": 0.00017170126057072032,
|
| 451 |
+
"loss": 3.3912,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.33132932531730125,
|
| 456 |
+
"grad_norm": 4.662436485290527,
|
| 457 |
+
"learning_rate": 0.00017037734623673615,
|
| 458 |
+
"loss": 3.1201,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.3366733466933868,
|
| 463 |
+
"grad_norm": 4.6757307052612305,
|
| 464 |
+
"learning_rate": 0.00016902852688348866,
|
| 465 |
+
"loss": 3.1055,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.3420173680694723,
|
| 470 |
+
"grad_norm": 3.675757884979248,
|
| 471 |
+
"learning_rate": 0.00016765527982894689,
|
| 472 |
+
"loss": 3.4294,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.3473613894455578,
|
| 477 |
+
"grad_norm": 3.7871510982513428,
|
| 478 |
+
"learning_rate": 0.00016625809103551462,
|
| 479 |
+
"loss": 3.1576,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.3527054108216433,
|
| 484 |
+
"grad_norm": 7.090997219085693,
|
| 485 |
+
"learning_rate": 0.0001648374549380587,
|
| 486 |
+
"loss": 1.9401,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.3580494321977288,
|
| 491 |
+
"grad_norm": 5.046462535858154,
|
| 492 |
+
"learning_rate": 0.00016339387426893918,
|
| 493 |
+
"loss": 1.7757,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.3633934535738143,
|
| 498 |
+
"grad_norm": 4.517994403839111,
|
| 499 |
+
"learning_rate": 0.00016192785988010353,
|
| 500 |
+
"loss": 1.3564,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.3687374749498998,
|
| 505 |
+
"grad_norm": 3.0163919925689697,
|
| 506 |
+
"learning_rate": 0.0001604399305623067,
|
| 507 |
+
"loss": 1.3458,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.3740814963259853,
|
| 512 |
+
"grad_norm": 4.087157249450684,
|
| 513 |
+
"learning_rate": 0.00015893061286152276,
|
| 514 |
+
"loss": 2.8926,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.37942551770207084,
|
| 519 |
+
"grad_norm": 4.707438945770264,
|
| 520 |
+
"learning_rate": 0.00015740044089261138,
|
| 521 |
+
"loss": 3.0473,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.3847695390781563,
|
| 526 |
+
"grad_norm": 8.234162330627441,
|
| 527 |
+
"learning_rate": 0.00015584995615030634,
|
| 528 |
+
"loss": 3.6788,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.39011356045424184,
|
| 533 |
+
"grad_norm": 7.497130870819092,
|
| 534 |
+
"learning_rate": 0.00015427970731759212,
|
| 535 |
+
"loss": 4.081,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.3954575818303273,
|
| 540 |
+
"grad_norm": 6.302802085876465,
|
| 541 |
+
"learning_rate": 0.000152690250071537,
|
| 542 |
+
"loss": 3.5992,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.40080160320641284,
|
| 547 |
+
"grad_norm": 7.252871036529541,
|
| 548 |
+
"learning_rate": 0.0001510821468866508,
|
| 549 |
+
"loss": 3.1878,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.4061456245824983,
|
| 554 |
+
"grad_norm": 4.067234516143799,
|
| 555 |
+
"learning_rate": 0.00014945596683583754,
|
| 556 |
+
"loss": 3.7711,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.41148964595858384,
|
| 561 |
+
"grad_norm": 3.713172435760498,
|
| 562 |
+
"learning_rate": 0.00014781228538901267,
|
| 563 |
+
"loss": 3.8432,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.4168336673346693,
|
| 568 |
+
"grad_norm": 3.5716781616210938,
|
| 569 |
+
"learning_rate": 0.00014615168420945688,
|
| 570 |
+
"loss": 3.6756,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.42217768871075484,
|
| 575 |
+
"grad_norm": 3.4458560943603516,
|
| 576 |
+
"learning_rate": 0.00014447475094797797,
|
| 577 |
+
"loss": 3.1908,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.42752171008684037,
|
| 582 |
+
"grad_norm": 2.959568500518799,
|
| 583 |
+
"learning_rate": 0.0001427820790349539,
|
| 584 |
+
"loss": 3.6547,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.43286573146292584,
|
| 589 |
+
"grad_norm": 3.844724178314209,
|
| 590 |
+
"learning_rate": 0.00014107426747033075,
|
| 591 |
+
"loss": 3.4797,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.43820975283901137,
|
| 596 |
+
"grad_norm": 3.2627336978912354,
|
| 597 |
+
"learning_rate": 0.00013935192061164956,
|
| 598 |
+
"loss": 3.4215,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.44355377421509684,
|
| 603 |
+
"grad_norm": 3.0022361278533936,
|
| 604 |
+
"learning_rate": 0.00013761564796017724,
|
| 605 |
+
"loss": 2.3842,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.44889779559118237,
|
| 610 |
+
"grad_norm": 2.4692890644073486,
|
| 611 |
+
"learning_rate": 0.0001358660639452173,
|
| 612 |
+
"loss": 2.2673,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.45424181696726784,
|
| 617 |
+
"grad_norm": 2.601637363433838,
|
| 618 |
+
"learning_rate": 0.0001341037877066766,
|
| 619 |
+
"loss": 2.8049,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.45958583834335337,
|
| 624 |
+
"grad_norm": 2.877810478210449,
|
| 625 |
+
"learning_rate": 0.00013232944287596522,
|
| 626 |
+
"loss": 2.9897,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.4649298597194389,
|
| 631 |
+
"grad_norm": 2.801961898803711,
|
| 632 |
+
"learning_rate": 0.00013054365735530664,
|
| 633 |
+
"loss": 2.969,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.47027388109552437,
|
| 638 |
+
"grad_norm": 3.4799296855926514,
|
| 639 |
+
"learning_rate": 0.00012874706309553698,
|
| 640 |
+
"loss": 2.7851,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.4756179024716099,
|
| 645 |
+
"grad_norm": 3.7868473529815674,
|
| 646 |
+
"learning_rate": 0.00012694029587247095,
|
| 647 |
+
"loss": 3.4085,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.48096192384769537,
|
| 652 |
+
"grad_norm": 3.071875810623169,
|
| 653 |
+
"learning_rate": 0.0001251239950619149,
|
| 654 |
+
"loss": 3.3867,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.4863059452237809,
|
| 659 |
+
"grad_norm": 8.204347610473633,
|
| 660 |
+
"learning_rate": 0.0001232988034134053,
|
| 661 |
+
"loss": 1.6884,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.4916499665998664,
|
| 666 |
+
"grad_norm": 5.938605785369873,
|
| 667 |
+
"learning_rate": 0.00012146536682275387,
|
| 668 |
+
"loss": 1.5711,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.4969939879759519,
|
| 673 |
+
"grad_norm": 3.6202452182769775,
|
| 674 |
+
"learning_rate": 0.0001196243341034786,
|
| 675 |
+
"loss": 1.7918,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.5023380093520374,
|
| 680 |
+
"grad_norm": 3.0969438552856445,
|
| 681 |
+
"learning_rate": 0.00011777635675720313,
|
| 682 |
+
"loss": 1.42,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.5023380093520374,
|
| 687 |
+
"eval_loss": 2.7997498512268066,
|
| 688 |
+
"eval_runtime": 16.1659,
|
| 689 |
+
"eval_samples_per_second": 19.547,
|
| 690 |
+
"eval_steps_per_second": 4.887,
|
| 691 |
+
"step": 94
|
| 692 |
}
|
| 693 |
],
|
| 694 |
"logging_steps": 1,
|
|
|
|
| 708 |
"attributes": {}
|
| 709 |
}
|
| 710 |
},
|
| 711 |
+
"total_flos": 7.740853165699891e+16,
|
| 712 |
"train_batch_size": 2,
|
| 713 |
"trial_name": null,
|
| 714 |
"trial_params": null
|