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 671149168
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb1b16447e2a058b959ca4c13d61d8d251d8786a4683fe785c55200bb73838fc
|
| 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 sha256:0b906ad1a41b7e9971bb0de895b25db2907de19810da5368d298b976d30765d6
|
| 3 |
size 1342555602
|
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 sha256:21ef774aef58f76fd627dbed5fbe2347c56b19bc9fd058490751e4be971883ee
|
| 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 sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
|
| 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": 12.806,
|
| 374 |
"eval_steps_per_second": 1.605,
|
| 375 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 376 |
}
|
| 377 |
],
|
| 378 |
"logging_steps": 1,
|
|
@@ -396,12 +754,12 @@
|
|
| 396 |
"should_evaluate": false,
|
| 397 |
"should_log": false,
|
| 398 |
"should_save": true,
|
| 399 |
-
"should_training_stop":
|
| 400 |
},
|
| 401 |
"attributes": {}
|
| 402 |
}
|
| 403 |
},
|
| 404 |
-
"total_flos":
|
| 405 |
"train_batch_size": 8,
|
| 406 |
"trial_name": null,
|
| 407 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.13168495893478394,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 0.081799591002045,
|
| 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": 12.806,
|
| 374 |
"eval_steps_per_second": 1.605,
|
| 375 |
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.04171779141104295,
|
| 379 |
+
"grad_norm": 0.011765269562602043,
|
| 380 |
+
"learning_rate": 5.695865504800327e-05,
|
| 381 |
+
"loss": 0.0758,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.0425357873210634,
|
| 386 |
+
"grad_norm": 0.08227711915969849,
|
| 387 |
+
"learning_rate": 5.522642316338268e-05,
|
| 388 |
+
"loss": 0.0783,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.043353783231083846,
|
| 393 |
+
"grad_norm": 0.0031160374637693167,
|
| 394 |
+
"learning_rate": 5.348782368720626e-05,
|
| 395 |
+
"loss": 0.0788,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.044171779141104296,
|
| 400 |
+
"grad_norm": 0.011308848857879639,
|
| 401 |
+
"learning_rate": 5.174497483512506e-05,
|
| 402 |
+
"loss": 0.0795,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.044989775051124746,
|
| 407 |
+
"grad_norm": 0.13721175491809845,
|
| 408 |
+
"learning_rate": 5e-05,
|
| 409 |
+
"loss": 0.0819,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.045807770961145196,
|
| 414 |
+
"grad_norm": 0.006852192338556051,
|
| 415 |
+
"learning_rate": 4.825502516487497e-05,
|
| 416 |
+
"loss": 0.082,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.046625766871165646,
|
| 421 |
+
"grad_norm": 0.29579928517341614,
|
| 422 |
+
"learning_rate": 4.6512176312793736e-05,
|
| 423 |
+
"loss": 0.083,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.047443762781186095,
|
| 428 |
+
"grad_norm": 0.007515231147408485,
|
| 429 |
+
"learning_rate": 4.477357683661734e-05,
|
| 430 |
+
"loss": 0.0834,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.048261758691206545,
|
| 435 |
+
"grad_norm": 0.004428052809089422,
|
| 436 |
+
"learning_rate": 4.3041344951996746e-05,
|
| 437 |
+
"loss": 0.0852,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.049079754601226995,
|
| 442 |
+
"grad_norm": 0.8864473104476929,
|
| 443 |
+
"learning_rate": 4.131759111665349e-05,
|
| 444 |
+
"loss": 0.0947,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.049897750511247445,
|
| 449 |
+
"grad_norm": 0.05357252061367035,
|
| 450 |
+
"learning_rate": 3.960441545911204e-05,
|
| 451 |
+
"loss": 0.0993,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.050715746421267895,
|
| 456 |
+
"grad_norm": 1.1230288743972778,
|
| 457 |
+
"learning_rate": 3.790390522001662e-05,
|
| 458 |
+
"loss": 0.1072,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.051533742331288344,
|
| 463 |
+
"grad_norm": 0.11107894033193588,
|
| 464 |
+
"learning_rate": 3.6218132209150045e-05,
|
| 465 |
+
"loss": 0.1049,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.052351738241308794,
|
| 470 |
+
"grad_norm": 0.0049737924709916115,
|
| 471 |
+
"learning_rate": 3.4549150281252636e-05,
|
| 472 |
+
"loss": 0.1022,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.053169734151329244,
|
| 477 |
+
"grad_norm": 0.0029193395748734474,
|
| 478 |
+
"learning_rate": 3.289899283371657e-05,
|
| 479 |
+
"loss": 0.1035,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.053987730061349694,
|
| 484 |
+
"grad_norm": 0.011156219989061356,
|
| 485 |
+
"learning_rate": 3.12696703292044e-05,
|
| 486 |
+
"loss": 0.1053,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.054805725971370144,
|
| 491 |
+
"grad_norm": 0.003020926844328642,
|
| 492 |
+
"learning_rate": 2.9663167846209998e-05,
|
| 493 |
+
"loss": 0.1056,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.05562372188139059,
|
| 498 |
+
"grad_norm": 0.01634683832526207,
|
| 499 |
+
"learning_rate": 2.8081442660546125e-05,
|
| 500 |
+
"loss": 0.1065,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.05644171779141104,
|
| 505 |
+
"grad_norm": 0.006313734222203493,
|
| 506 |
+
"learning_rate": 2.6526421860705473e-05,
|
| 507 |
+
"loss": 0.1064,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.05725971370143149,
|
| 512 |
+
"grad_norm": 0.005186033435165882,
|
| 513 |
+
"learning_rate": 2.500000000000001e-05,
|
| 514 |
+
"loss": 0.1072,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.05807770961145194,
|
| 519 |
+
"grad_norm": 0.04070008173584938,
|
| 520 |
+
"learning_rate": 2.350403678833976e-05,
|
| 521 |
+
"loss": 0.1088,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.05889570552147239,
|
| 526 |
+
"grad_norm": 0.01637279987335205,
|
| 527 |
+
"learning_rate": 2.2040354826462668e-05,
|
| 528 |
+
"loss": 0.1092,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.05971370143149284,
|
| 533 |
+
"grad_norm": 0.17546702921390533,
|
| 534 |
+
"learning_rate": 2.061073738537635e-05,
|
| 535 |
+
"loss": 0.1141,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.06053169734151329,
|
| 540 |
+
"grad_norm": 0.12339083105325699,
|
| 541 |
+
"learning_rate": 1.9216926233717085e-05,
|
| 542 |
+
"loss": 0.1127,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.06134969325153374,
|
| 547 |
+
"grad_norm": 0.005719954613596201,
|
| 548 |
+
"learning_rate": 1.7860619515673033e-05,
|
| 549 |
+
"loss": 0.112,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.06216768916155419,
|
| 554 |
+
"grad_norm": 0.005668998695909977,
|
| 555 |
+
"learning_rate": 1.6543469682057106e-05,
|
| 556 |
+
"loss": 0.1128,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.06298568507157465,
|
| 561 |
+
"grad_norm": 0.007494923193007708,
|
| 562 |
+
"learning_rate": 1.526708147705013e-05,
|
| 563 |
+
"loss": 0.1139,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.0638036809815951,
|
| 568 |
+
"grad_norm": 0.9686630368232727,
|
| 569 |
+
"learning_rate": 1.4033009983067452e-05,
|
| 570 |
+
"loss": 0.1185,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.06462167689161555,
|
| 575 |
+
"grad_norm": 0.005378738045692444,
|
| 576 |
+
"learning_rate": 1.2842758726130283e-05,
|
| 577 |
+
"loss": 0.1269,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.065439672801636,
|
| 582 |
+
"grad_norm": 0.008375857956707478,
|
| 583 |
+
"learning_rate": 1.1697777844051105e-05,
|
| 584 |
+
"loss": 0.1394,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.06625766871165645,
|
| 589 |
+
"grad_norm": 0.0262595321983099,
|
| 590 |
+
"learning_rate": 1.0599462319663905e-05,
|
| 591 |
+
"loss": 0.1466,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.0670756646216769,
|
| 596 |
+
"grad_norm": 0.004784999880939722,
|
| 597 |
+
"learning_rate": 9.549150281252633e-06,
|
| 598 |
+
"loss": 0.1518,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.06789366053169735,
|
| 603 |
+
"grad_norm": 0.541429877281189,
|
| 604 |
+
"learning_rate": 8.548121372247918e-06,
|
| 605 |
+
"loss": 0.158,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.0687116564417178,
|
| 610 |
+
"grad_norm": 0.17787200212478638,
|
| 611 |
+
"learning_rate": 7.597595192178702e-06,
|
| 612 |
+
"loss": 0.1617,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.06952965235173825,
|
| 617 |
+
"grad_norm": 0.7806742787361145,
|
| 618 |
+
"learning_rate": 6.698729810778065e-06,
|
| 619 |
+
"loss": 0.1635,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.0703476482617587,
|
| 624 |
+
"grad_norm": 0.004796426277607679,
|
| 625 |
+
"learning_rate": 5.852620357053651e-06,
|
| 626 |
+
"loss": 0.1595,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.07116564417177915,
|
| 631 |
+
"grad_norm": 1.1767271757125854,
|
| 632 |
+
"learning_rate": 5.060297685041659e-06,
|
| 633 |
+
"loss": 0.1716,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.0719836400817996,
|
| 638 |
+
"grad_norm": 0.8248836994171143,
|
| 639 |
+
"learning_rate": 4.322727117869951e-06,
|
| 640 |
+
"loss": 0.1651,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.07280163599182005,
|
| 645 |
+
"grad_norm": 0.005601507145911455,
|
| 646 |
+
"learning_rate": 3.6408072716606346e-06,
|
| 647 |
+
"loss": 0.165,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.0736196319018405,
|
| 652 |
+
"grad_norm": 0.20898360013961792,
|
| 653 |
+
"learning_rate": 3.0153689607045845e-06,
|
| 654 |
+
"loss": 0.1697,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.07443762781186095,
|
| 659 |
+
"grad_norm": 0.00812277290970087,
|
| 660 |
+
"learning_rate": 2.4471741852423237e-06,
|
| 661 |
+
"loss": 0.1666,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.0752556237218814,
|
| 666 |
+
"grad_norm": 0.005786346737295389,
|
| 667 |
+
"learning_rate": 1.9369152030840556e-06,
|
| 668 |
+
"loss": 0.1707,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.07607361963190185,
|
| 673 |
+
"grad_norm": 0.004848749376833439,
|
| 674 |
+
"learning_rate": 1.4852136862001764e-06,
|
| 675 |
+
"loss": 0.1748,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.0768916155419223,
|
| 680 |
+
"grad_norm": 0.7034335732460022,
|
| 681 |
+
"learning_rate": 1.0926199633097157e-06,
|
| 682 |
+
"loss": 0.1838,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.07770961145194274,
|
| 687 |
+
"grad_norm": 0.721812903881073,
|
| 688 |
+
"learning_rate": 7.596123493895991e-07,
|
| 689 |
+
"loss": 0.202,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.0785276073619632,
|
| 694 |
+
"grad_norm": 0.6704414486885071,
|
| 695 |
+
"learning_rate": 4.865965629214819e-07,
|
| 696 |
+
"loss": 0.2159,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.07934560327198364,
|
| 701 |
+
"grad_norm": 1.4202635288238525,
|
| 702 |
+
"learning_rate": 2.7390523158633554e-07,
|
| 703 |
+
"loss": 0.2141,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.0801635991820041,
|
| 708 |
+
"grad_norm": 0.36247241497039795,
|
| 709 |
+
"learning_rate": 1.2179748700879012e-07,
|
| 710 |
+
"loss": 0.2182,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.08098159509202454,
|
| 715 |
+
"grad_norm": 0.008243364281952381,
|
| 716 |
+
"learning_rate": 3.04586490452119e-08,
|
| 717 |
+
"loss": 0.2288,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.081799591002045,
|
| 722 |
+
"grad_norm": 1.1368809938430786,
|
| 723 |
+
"learning_rate": 0.0,
|
| 724 |
+
"loss": 0.2542,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.081799591002045,
|
| 729 |
+
"eval_loss": 0.13168495893478394,
|
| 730 |
+
"eval_runtime": 160.7443,
|
| 731 |
+
"eval_samples_per_second": 12.809,
|
| 732 |
+
"eval_steps_per_second": 1.605,
|
| 733 |
+
"step": 100
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
|
|
| 754 |
"should_evaluate": false,
|
| 755 |
"should_log": false,
|
| 756 |
"should_save": true,
|
| 757 |
+
"should_training_stop": true
|
| 758 |
},
|
| 759 |
"attributes": {}
|
| 760 |
}
|
| 761 |
},
|
| 762 |
+
"total_flos": 1.508513578745856e+17,
|
| 763 |
"train_batch_size": 8,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|