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 871457448
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aff1d604b13cf3d048f8d189b71a1d8ce8ea10cab74dcaf50c59b3c1f3df5c8a
|
| 3 |
size 871457448
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 443280340
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be46889630b146664dfc93c687af054613b3dc6ca7eb79ba0698b74dccf43473
|
| 3 |
size 443280340
|
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 sha256:57dbc6bc3b7e05eaf28058684f07775f2067e75d8bbd851597ad0ef815321c41
|
| 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 sha256:99ca67f9a35cd1c50df3d93bedf5a6642db2c7847c021a0a8d3f44c1bf4993d3
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.44632911682128906,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 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": 7.041,
|
| 374 |
"eval_steps_per_second": 1.761,
|
| 375 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 376 |
}
|
| 377 |
],
|
| 378 |
"logging_steps": 1,
|
|
@@ -387,7 +745,7 @@
|
|
| 387 |
"early_stopping_threshold": 0.0
|
| 388 |
},
|
| 389 |
"attributes": {
|
| 390 |
-
"early_stopping_patience_counter":
|
| 391 |
}
|
| 392 |
},
|
| 393 |
"TrainerControl": {
|
|
@@ -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": 0.44632911682128906,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 4 |
+
"epoch": 0.0821186614658181,
|
| 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": 7.041,
|
| 374 |
"eval_steps_per_second": 1.761,
|
| 375 |
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.04188051734756724,
|
| 379 |
+
"grad_norm": 1.5864020586013794,
|
| 380 |
+
"learning_rate": 9.729774092143627e-05,
|
| 381 |
+
"loss": 0.4838,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.04270170396222542,
|
| 386 |
+
"grad_norm": 1.2497475147247314,
|
| 387 |
+
"learning_rate": 9.716559066288715e-05,
|
| 388 |
+
"loss": 0.4411,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.0435228905768836,
|
| 393 |
+
"grad_norm": 0.9487363696098328,
|
| 394 |
+
"learning_rate": 9.703037989675087e-05,
|
| 395 |
+
"loss": 0.3657,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.04434407719154178,
|
| 400 |
+
"grad_norm": 0.33357444405555725,
|
| 401 |
+
"learning_rate": 9.689211739666023e-05,
|
| 402 |
+
"loss": 0.2727,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.04516526380619996,
|
| 407 |
+
"grad_norm": 0.4681488573551178,
|
| 408 |
+
"learning_rate": 9.675081213427076e-05,
|
| 409 |
+
"loss": 0.315,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.04598645042085814,
|
| 414 |
+
"grad_norm": 0.4412896931171417,
|
| 415 |
+
"learning_rate": 9.66064732786784e-05,
|
| 416 |
+
"loss": 0.3051,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.04680763703551632,
|
| 421 |
+
"grad_norm": 0.42806002497673035,
|
| 422 |
+
"learning_rate": 9.645911019582467e-05,
|
| 423 |
+
"loss": 0.296,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.047628823650174505,
|
| 428 |
+
"grad_norm": 0.3795586824417114,
|
| 429 |
+
"learning_rate": 9.630873244788883e-05,
|
| 430 |
+
"loss": 0.3184,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.048450010264832685,
|
| 435 |
+
"grad_norm": 0.34351328015327454,
|
| 436 |
+
"learning_rate": 9.615534979266745e-05,
|
| 437 |
+
"loss": 0.2832,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.049271196879490865,
|
| 442 |
+
"grad_norm": 0.35215750336647034,
|
| 443 |
+
"learning_rate": 9.599897218294122e-05,
|
| 444 |
+
"loss": 0.3083,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.050092383494149045,
|
| 449 |
+
"grad_norm": 0.3156924843788147,
|
| 450 |
+
"learning_rate": 9.583960976582913e-05,
|
| 451 |
+
"loss": 0.2577,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.050913570108807225,
|
| 456 |
+
"grad_norm": 0.4058922231197357,
|
| 457 |
+
"learning_rate": 9.567727288213005e-05,
|
| 458 |
+
"loss": 0.3156,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.051734756723465405,
|
| 463 |
+
"grad_norm": 0.3673064410686493,
|
| 464 |
+
"learning_rate": 9.551197206565173e-05,
|
| 465 |
+
"loss": 0.2932,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.052555943338123585,
|
| 470 |
+
"grad_norm": 0.3226417601108551,
|
| 471 |
+
"learning_rate": 9.534371804252728e-05,
|
| 472 |
+
"loss": 0.2404,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.05337712995278177,
|
| 477 |
+
"grad_norm": 0.3365015685558319,
|
| 478 |
+
"learning_rate": 9.517252173051911e-05,
|
| 479 |
+
"loss": 0.263,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.05419831656743995,
|
| 484 |
+
"grad_norm": 0.38001781702041626,
|
| 485 |
+
"learning_rate": 9.49983942383106e-05,
|
| 486 |
+
"loss": 0.2973,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.05501950318209813,
|
| 491 |
+
"grad_norm": 0.5203686356544495,
|
| 492 |
+
"learning_rate": 9.482134686478519e-05,
|
| 493 |
+
"loss": 0.2693,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.05584068979675631,
|
| 498 |
+
"grad_norm": 0.32921281456947327,
|
| 499 |
+
"learning_rate": 9.464139109829321e-05,
|
| 500 |
+
"loss": 0.2742,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.05666187641141449,
|
| 505 |
+
"grad_norm": 0.43800121545791626,
|
| 506 |
+
"learning_rate": 9.445853861590647e-05,
|
| 507 |
+
"loss": 0.2915,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.05748306302607267,
|
| 512 |
+
"grad_norm": 0.32359007000923157,
|
| 513 |
+
"learning_rate": 9.42728012826605e-05,
|
| 514 |
+
"loss": 0.218,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.05830424964073085,
|
| 519 |
+
"grad_norm": 0.39324089884757996,
|
| 520 |
+
"learning_rate": 9.408419115078471e-05,
|
| 521 |
+
"loss": 0.2635,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.05912543625538904,
|
| 526 |
+
"grad_norm": 0.45099887251853943,
|
| 527 |
+
"learning_rate": 9.389272045892024e-05,
|
| 528 |
+
"loss": 0.2402,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.05994662287004722,
|
| 533 |
+
"grad_norm": 0.4052051603794098,
|
| 534 |
+
"learning_rate": 9.36984016313259e-05,
|
| 535 |
+
"loss": 0.2775,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.0607678094847054,
|
| 540 |
+
"grad_norm": 0.41129499673843384,
|
| 541 |
+
"learning_rate": 9.350124727707197e-05,
|
| 542 |
+
"loss": 0.2564,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.06158899609936358,
|
| 547 |
+
"grad_norm": 0.3723108470439911,
|
| 548 |
+
"learning_rate": 9.330127018922194e-05,
|
| 549 |
+
"loss": 0.2614,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.06241018271402176,
|
| 554 |
+
"grad_norm": 0.39635589718818665,
|
| 555 |
+
"learning_rate": 9.309848334400246e-05,
|
| 556 |
+
"loss": 0.2825,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.06323136932867994,
|
| 561 |
+
"grad_norm": 0.4818005859851837,
|
| 562 |
+
"learning_rate": 9.289289989996133e-05,
|
| 563 |
+
"loss": 0.2539,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.06405255594333813,
|
| 568 |
+
"grad_norm": 0.4484040439128876,
|
| 569 |
+
"learning_rate": 9.268453319711363e-05,
|
| 570 |
+
"loss": 0.2857,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.0648737425579963,
|
| 575 |
+
"grad_norm": 0.46060118079185486,
|
| 576 |
+
"learning_rate": 9.247339675607605e-05,
|
| 577 |
+
"loss": 0.2745,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.06569492917265449,
|
| 582 |
+
"grad_norm": 0.3952708840370178,
|
| 583 |
+
"learning_rate": 9.225950427718975e-05,
|
| 584 |
+
"loss": 0.2954,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.06651611578731266,
|
| 589 |
+
"grad_norm": 0.4594082534313202,
|
| 590 |
+
"learning_rate": 9.204286963963111e-05,
|
| 591 |
+
"loss": 0.2647,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.06733730240197085,
|
| 596 |
+
"grad_norm": 0.498677134513855,
|
| 597 |
+
"learning_rate": 9.182350690051133e-05,
|
| 598 |
+
"loss": 0.2741,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.06815848901662903,
|
| 603 |
+
"grad_norm": 0.48790332674980164,
|
| 604 |
+
"learning_rate": 9.160143029396422e-05,
|
| 605 |
+
"loss": 0.217,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.06897967563128721,
|
| 610 |
+
"grad_norm": 0.4500594437122345,
|
| 611 |
+
"learning_rate": 9.13766542302225e-05,
|
| 612 |
+
"loss": 0.2478,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.0698008622459454,
|
| 617 |
+
"grad_norm": 0.477200984954834,
|
| 618 |
+
"learning_rate": 9.114919329468282e-05,
|
| 619 |
+
"loss": 0.276,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.07062204886060357,
|
| 624 |
+
"grad_norm": 0.5421808362007141,
|
| 625 |
+
"learning_rate": 9.091906224695935e-05,
|
| 626 |
+
"loss": 0.3018,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.07144323547526175,
|
| 631 |
+
"grad_norm": 0.473712295293808,
|
| 632 |
+
"learning_rate": 9.068627601992598e-05,
|
| 633 |
+
"loss": 0.2687,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.07226442208991993,
|
| 638 |
+
"grad_norm": 0.5594393610954285,
|
| 639 |
+
"learning_rate": 9.045084971874738e-05,
|
| 640 |
+
"loss": 0.2515,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.07308560870457811,
|
| 645 |
+
"grad_norm": 0.6386433839797974,
|
| 646 |
+
"learning_rate": 9.021279861989885e-05,
|
| 647 |
+
"loss": 0.2529,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.0739067953192363,
|
| 652 |
+
"grad_norm": 0.5319457650184631,
|
| 653 |
+
"learning_rate": 8.997213817017507e-05,
|
| 654 |
+
"loss": 0.2646,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.07472798193389447,
|
| 659 |
+
"grad_norm": 0.595516562461853,
|
| 660 |
+
"learning_rate": 8.972888398568772e-05,
|
| 661 |
+
"loss": 0.2756,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.07554916854855266,
|
| 666 |
+
"grad_norm": 0.6601677536964417,
|
| 667 |
+
"learning_rate": 8.948305185085225e-05,
|
| 668 |
+
"loss": 0.2805,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.07637035516321083,
|
| 673 |
+
"grad_norm": 0.6162546873092651,
|
| 674 |
+
"learning_rate": 8.92346577173636e-05,
|
| 675 |
+
"loss": 0.2435,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.07719154177786902,
|
| 680 |
+
"grad_norm": 0.6918389797210693,
|
| 681 |
+
"learning_rate": 8.898371770316111e-05,
|
| 682 |
+
"loss": 0.3159,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.07801272839252721,
|
| 687 |
+
"grad_norm": 0.7181240916252136,
|
| 688 |
+
"learning_rate": 8.873024809138272e-05,
|
| 689 |
+
"loss": 0.2413,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.07883391500718538,
|
| 694 |
+
"grad_norm": 1.1472549438476562,
|
| 695 |
+
"learning_rate": 8.847426532930831e-05,
|
| 696 |
+
"loss": 0.2949,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.07965510162184357,
|
| 701 |
+
"grad_norm": 0.9359822273254395,
|
| 702 |
+
"learning_rate": 8.821578602729242e-05,
|
| 703 |
+
"loss": 0.316,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.08047628823650174,
|
| 708 |
+
"grad_norm": 0.7444966435432434,
|
| 709 |
+
"learning_rate": 8.795482695768658e-05,
|
| 710 |
+
"loss": 0.3119,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.08129747485115993,
|
| 715 |
+
"grad_norm": 1.2565944194793701,
|
| 716 |
+
"learning_rate": 8.769140505375085e-05,
|
| 717 |
+
"loss": 0.2877,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.0821186614658181,
|
| 722 |
+
"grad_norm": 0.9129545092582703,
|
| 723 |
+
"learning_rate": 8.742553740855506e-05,
|
| 724 |
+
"loss": 0.3209,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.0821186614658181,
|
| 729 |
+
"eval_loss": 0.4635893702507019,
|
| 730 |
+
"eval_runtime": 290.5387,
|
| 731 |
+
"eval_samples_per_second": 7.059,
|
| 732 |
+
"eval_steps_per_second": 1.766,
|
| 733 |
+
"step": 100
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
|
|
| 745 |
"early_stopping_threshold": 0.0
|
| 746 |
},
|
| 747 |
"attributes": {
|
| 748 |
+
"early_stopping_patience_counter": 1
|
| 749 |
}
|
| 750 |
},
|
| 751 |
"TrainerControl": {
|
|
|
|
| 759 |
"attributes": {}
|
| 760 |
}
|
| 761 |
},
|
| 762 |
+
"total_flos": 1.7401760676682138e+17,
|
| 763 |
"train_batch_size": 8,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|