Training in progress, step 100, checkpoint
Browse files- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +363 -5
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:ffe08f68a44e9c53dceae362c1438e25bd33a50486d7e689fa5cfe717732086e
|
| 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 1342555602
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:075fec230b0bfb0d564ddf74e3ac10789012e76b69bb08c3b6f804754b03f3b7
|
| 3 |
size 1342555602
|
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 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64e3b7de560515cbc91a8044e0b3dd306699a3abb06e8a04986a88397035c819
|
| 3 |
size 14960
|
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 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fcccc4dfa28930ca21de6e14969ed225a9e22ddd15f63a8a9e3cdafd0643baac
|
| 3 |
size 15024
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:896ca407f4a8090d5c02fb67a520a48dfc67c2c022aa5bd805c104103995bbfe
|
| 3 |
size 15024
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e10fcbbbe7c2f37eee907ce9324e239ebd310a8e28d026302e6361d8ef25db5
|
| 3 |
size 15024
|
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 sha256:5c9fd70aa4cf68daad2242bc04a8a03f22adc681e42e4ebf5294902cea9d0a87
|
| 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": 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": 40.321,
|
| 374 |
"eval_steps_per_second": 5.05,
|
| 375 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 376 |
}
|
| 377 |
],
|
| 378 |
"logging_steps": 1,
|
|
@@ -401,7 +759,7 @@
|
|
| 401 |
"attributes": {}
|
| 402 |
}
|
| 403 |
},
|
| 404 |
-
"total_flos":
|
| 405 |
"train_batch_size": 8,
|
| 406 |
"trial_name": null,
|
| 407 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.2764929533004761,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 0.2588996763754045,
|
| 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": 40.321,
|
| 374 |
"eval_steps_per_second": 5.05,
|
| 375 |
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.13203883495145632,
|
| 379 |
+
"grad_norm": 12.063788414001465,
|
| 380 |
+
"learning_rate": 9.628188298907782e-05,
|
| 381 |
+
"loss": 1.4899,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.13462783171521037,
|
| 386 |
+
"grad_norm": 8.200540542602539,
|
| 387 |
+
"learning_rate": 9.592434928729616e-05,
|
| 388 |
+
"loss": 1.3093,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.1372168284789644,
|
| 393 |
+
"grad_norm": 3.508943796157837,
|
| 394 |
+
"learning_rate": 9.555113246230442e-05,
|
| 395 |
+
"loss": 1.1634,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.13980582524271845,
|
| 400 |
+
"grad_norm": 2.361328601837158,
|
| 401 |
+
"learning_rate": 9.516235996730645e-05,
|
| 402 |
+
"loss": 1.0916,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.1423948220064725,
|
| 407 |
+
"grad_norm": 2.5727005004882812,
|
| 408 |
+
"learning_rate": 9.475816456775313e-05,
|
| 409 |
+
"loss": 1.0954,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.14498381877022654,
|
| 414 |
+
"grad_norm": 3.032360792160034,
|
| 415 |
+
"learning_rate": 9.43386842960031e-05,
|
| 416 |
+
"loss": 1.175,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.14757281553398058,
|
| 421 |
+
"grad_norm": 2.9916622638702393,
|
| 422 |
+
"learning_rate": 9.39040624041849e-05,
|
| 423 |
+
"loss": 1.1121,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.15016181229773462,
|
| 428 |
+
"grad_norm": 3.048910140991211,
|
| 429 |
+
"learning_rate": 9.345444731527642e-05,
|
| 430 |
+
"loss": 1.0988,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.15275080906148866,
|
| 435 |
+
"grad_norm": 3.363703489303589,
|
| 436 |
+
"learning_rate": 9.298999257241863e-05,
|
| 437 |
+
"loss": 1.1841,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.1553398058252427,
|
| 442 |
+
"grad_norm": 3.3770105838775635,
|
| 443 |
+
"learning_rate": 9.251085678648072e-05,
|
| 444 |
+
"loss": 1.1814,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.15792880258899678,
|
| 449 |
+
"grad_norm": 4.700929641723633,
|
| 450 |
+
"learning_rate": 9.201720358189464e-05,
|
| 451 |
+
"loss": 1.2283,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.16051779935275082,
|
| 456 |
+
"grad_norm": 5.556697845458984,
|
| 457 |
+
"learning_rate": 9.150920154077754e-05,
|
| 458 |
+
"loss": 1.3271,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.16310679611650486,
|
| 463 |
+
"grad_norm": 5.743304252624512,
|
| 464 |
+
"learning_rate": 9.098702414536107e-05,
|
| 465 |
+
"loss": 1.2262,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.1656957928802589,
|
| 470 |
+
"grad_norm": 5.529282093048096,
|
| 471 |
+
"learning_rate": 9.045084971874738e-05,
|
| 472 |
+
"loss": 1.198,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.16828478964401294,
|
| 477 |
+
"grad_norm": 3.399848222732544,
|
| 478 |
+
"learning_rate": 8.9900861364012e-05,
|
| 479 |
+
"loss": 1.1249,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.170873786407767,
|
| 484 |
+
"grad_norm": 2.213207244873047,
|
| 485 |
+
"learning_rate": 8.933724690167417e-05,
|
| 486 |
+
"loss": 1.0662,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.17346278317152103,
|
| 491 |
+
"grad_norm": 2.491964101791382,
|
| 492 |
+
"learning_rate": 8.876019880555649e-05,
|
| 493 |
+
"loss": 1.0862,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.17605177993527507,
|
| 498 |
+
"grad_norm": 2.7167015075683594,
|
| 499 |
+
"learning_rate": 8.816991413705516e-05,
|
| 500 |
+
"loss": 1.1059,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.1786407766990291,
|
| 505 |
+
"grad_norm": 2.776489734649658,
|
| 506 |
+
"learning_rate": 8.756659447784368e-05,
|
| 507 |
+
"loss": 1.0858,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.18122977346278318,
|
| 512 |
+
"grad_norm": 2.965355396270752,
|
| 513 |
+
"learning_rate": 8.695044586103296e-05,
|
| 514 |
+
"loss": 1.125,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.18381877022653723,
|
| 519 |
+
"grad_norm": 2.7822370529174805,
|
| 520 |
+
"learning_rate": 8.632167870081121e-05,
|
| 521 |
+
"loss": 1.0688,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.18640776699029127,
|
| 526 |
+
"grad_norm": 4.001903533935547,
|
| 527 |
+
"learning_rate": 8.568050772058762e-05,
|
| 528 |
+
"loss": 1.1053,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.1889967637540453,
|
| 533 |
+
"grad_norm": 3.649930477142334,
|
| 534 |
+
"learning_rate": 8.502715187966455e-05,
|
| 535 |
+
"loss": 1.1806,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.19158576051779935,
|
| 540 |
+
"grad_norm": 4.8959550857543945,
|
| 541 |
+
"learning_rate": 8.436183429846313e-05,
|
| 542 |
+
"loss": 1.2705,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.1941747572815534,
|
| 547 |
+
"grad_norm": 7.251972198486328,
|
| 548 |
+
"learning_rate": 8.368478218232787e-05,
|
| 549 |
+
"loss": 1.3655,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.19676375404530744,
|
| 554 |
+
"grad_norm": 9.770423889160156,
|
| 555 |
+
"learning_rate": 8.299622674393614e-05,
|
| 556 |
+
"loss": 1.1064,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.19935275080906148,
|
| 561 |
+
"grad_norm": 8.65103530883789,
|
| 562 |
+
"learning_rate": 8.229640312433937e-05,
|
| 563 |
+
"loss": 1.1839,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.20194174757281552,
|
| 568 |
+
"grad_norm": 5.945736885070801,
|
| 569 |
+
"learning_rate": 8.158555031266254e-05,
|
| 570 |
+
"loss": 1.1019,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.2045307443365696,
|
| 575 |
+
"grad_norm": 3.460510730743408,
|
| 576 |
+
"learning_rate": 8.086391106448965e-05,
|
| 577 |
+
"loss": 1.0443,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.20711974110032363,
|
| 582 |
+
"grad_norm": 2.2635905742645264,
|
| 583 |
+
"learning_rate": 8.013173181896283e-05,
|
| 584 |
+
"loss": 1.0537,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.20970873786407768,
|
| 589 |
+
"grad_norm": 2.609692335128784,
|
| 590 |
+
"learning_rate": 7.938926261462366e-05,
|
| 591 |
+
"loss": 1.0779,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.21229773462783172,
|
| 596 |
+
"grad_norm": 2.645723819732666,
|
| 597 |
+
"learning_rate": 7.863675700402526e-05,
|
| 598 |
+
"loss": 1.0427,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.21488673139158576,
|
| 603 |
+
"grad_norm": 3.2835347652435303,
|
| 604 |
+
"learning_rate": 7.787447196714427e-05,
|
| 605 |
+
"loss": 1.1034,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.2174757281553398,
|
| 610 |
+
"grad_norm": 3.677543878555298,
|
| 611 |
+
"learning_rate": 7.710266782362247e-05,
|
| 612 |
+
"loss": 1.2105,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.22006472491909385,
|
| 617 |
+
"grad_norm": 3.5897769927978516,
|
| 618 |
+
"learning_rate": 7.63216081438678e-05,
|
| 619 |
+
"loss": 1.2181,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.2226537216828479,
|
| 624 |
+
"grad_norm": 3.5425643920898438,
|
| 625 |
+
"learning_rate": 7.553155965904535e-05,
|
| 626 |
+
"loss": 1.1825,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.22524271844660193,
|
| 631 |
+
"grad_norm": 4.001893997192383,
|
| 632 |
+
"learning_rate": 7.473279216998895e-05,
|
| 633 |
+
"loss": 1.2106,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.227831715210356,
|
| 638 |
+
"grad_norm": 3.9724557399749756,
|
| 639 |
+
"learning_rate": 7.392557845506432e-05,
|
| 640 |
+
"loss": 1.1139,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.23042071197411004,
|
| 645 |
+
"grad_norm": 4.996490955352783,
|
| 646 |
+
"learning_rate": 7.311019417701566e-05,
|
| 647 |
+
"loss": 1.1814,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.23300970873786409,
|
| 652 |
+
"grad_norm": 3.354581117630005,
|
| 653 |
+
"learning_rate": 7.228691778882693e-05,
|
| 654 |
+
"loss": 1.0731,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.23559870550161813,
|
| 659 |
+
"grad_norm": 1.9178783893585205,
|
| 660 |
+
"learning_rate": 7.145603043863045e-05,
|
| 661 |
+
"loss": 0.9357,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.23818770226537217,
|
| 666 |
+
"grad_norm": 2.0360922813415527,
|
| 667 |
+
"learning_rate": 7.061781587369519e-05,
|
| 668 |
+
"loss": 0.9789,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.2407766990291262,
|
| 673 |
+
"grad_norm": 2.401505470275879,
|
| 674 |
+
"learning_rate": 6.977256034352712e-05,
|
| 675 |
+
"loss": 1.0518,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.24336569579288025,
|
| 680 |
+
"grad_norm": 2.738330364227295,
|
| 681 |
+
"learning_rate": 6.892055250211552e-05,
|
| 682 |
+
"loss": 1.0681,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.2459546925566343,
|
| 687 |
+
"grad_norm": 3.1010687351226807,
|
| 688 |
+
"learning_rate": 6.806208330935766e-05,
|
| 689 |
+
"loss": 1.1431,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.24854368932038834,
|
| 694 |
+
"grad_norm": 3.6441831588745117,
|
| 695 |
+
"learning_rate": 6.719744593169641e-05,
|
| 696 |
+
"loss": 1.1438,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.2511326860841424,
|
| 701 |
+
"grad_norm": 3.7766201496124268,
|
| 702 |
+
"learning_rate": 6.632693564200416e-05,
|
| 703 |
+
"loss": 1.1669,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.2537216828478964,
|
| 708 |
+
"grad_norm": 4.321850299835205,
|
| 709 |
+
"learning_rate": 6.545084971874738e-05,
|
| 710 |
+
"loss": 1.1743,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.2563106796116505,
|
| 715 |
+
"grad_norm": 5.203691005706787,
|
| 716 |
+
"learning_rate": 6.456948734446624e-05,
|
| 717 |
+
"loss": 1.2916,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.2588996763754045,
|
| 722 |
+
"grad_norm": 6.3613057136535645,
|
| 723 |
+
"learning_rate": 6.368314950360415e-05,
|
| 724 |
+
"loss": 1.2034,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.2588996763754045,
|
| 729 |
+
"eval_loss": 0.2764929533004761,
|
| 730 |
+
"eval_runtime": 67.6851,
|
| 731 |
+
"eval_samples_per_second": 38.457,
|
| 732 |
+
"eval_steps_per_second": 4.816,
|
| 733 |
+
"step": 100
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
|
|
| 759 |
"attributes": {}
|
| 760 |
}
|
| 761 |
},
|
| 762 |
+
"total_flos": 5.802703442715607e+17,
|
| 763 |
"train_batch_size": 8,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|