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 578859568
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:330ebf2fc78d7f6f8cb0c815f67bcae506da819a7aff7e37748efa931b16d910
|
| 3 |
size 578859568
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 294324372
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b00ebe9b91258a190a07ebaabacfcadcdf9d0e664ff19ed32400b152a5e4f7c
|
| 3 |
size 294324372
|
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 sha256:632841951b590cd1045c6936a248754bca8a52877d07e548317e1fb181970885
|
| 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:c9f081c44b322e29d9c3ab667f1f86bff894c62055bb3540dff4b22ee74b02c5
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.9230208396911621,
|
| 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": 11.549,
|
| 374 |
"eval_steps_per_second": 5.784,
|
| 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": 2,
|
| 406 |
"trial_name": null,
|
| 407 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.9230208396911621,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 4 |
+
"epoch": 0.0027796888138372907,
|
| 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": 11.549,
|
| 374 |
"eval_steps_per_second": 5.784,
|
| 375 |
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.0014176412950570184,
|
| 379 |
+
"grad_norm": 0.1536542773246765,
|
| 380 |
+
"learning_rate": 0.001965648708885559,
|
| 381 |
+
"loss": 1.0933,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.0014454381831953912,
|
| 386 |
+
"grad_norm": 0.1058596670627594,
|
| 387 |
+
"learning_rate": 0.001963962860695853,
|
| 388 |
+
"loss": 1.0704,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.0014732350713337642,
|
| 393 |
+
"grad_norm": 0.08224259316921234,
|
| 394 |
+
"learning_rate": 0.001962237387768529,
|
| 395 |
+
"loss": 1.1229,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.001501031959472137,
|
| 400 |
+
"grad_norm": 0.08697132021188736,
|
| 401 |
+
"learning_rate": 0.0019604723610310193,
|
| 402 |
+
"loss": 0.9118,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.00152882884761051,
|
| 407 |
+
"grad_norm": 0.08103405684232712,
|
| 408 |
+
"learning_rate": 0.0019586678530366607,
|
| 409 |
+
"loss": 0.946,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.0015566257357488829,
|
| 414 |
+
"grad_norm": 0.07975370436906815,
|
| 415 |
+
"learning_rate": 0.0019568239379617086,
|
| 416 |
+
"loss": 0.9038,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.001584422623887256,
|
| 421 |
+
"grad_norm": 0.07595320045948029,
|
| 422 |
+
"learning_rate": 0.0019549406916022907,
|
| 423 |
+
"loss": 0.8122,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.0016122195120256287,
|
| 428 |
+
"grad_norm": 0.08768190443515778,
|
| 429 |
+
"learning_rate": 0.0019530181913712872,
|
| 430 |
+
"loss": 0.8606,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.0016400164001640015,
|
| 435 |
+
"grad_norm": 0.09886912256479263,
|
| 436 |
+
"learning_rate": 0.0019510565162951536,
|
| 437 |
+
"loss": 0.8902,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.0016678132883023746,
|
| 442 |
+
"grad_norm": 0.08801861107349396,
|
| 443 |
+
"learning_rate": 0.0019490557470106687,
|
| 444 |
+
"loss": 0.9151,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.0016956101764407474,
|
| 449 |
+
"grad_norm": 0.08995132893323898,
|
| 450 |
+
"learning_rate": 0.0019470159657616214,
|
| 451 |
+
"loss": 0.7793,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.0017234070645791204,
|
| 456 |
+
"grad_norm": 0.08425740152597427,
|
| 457 |
+
"learning_rate": 0.0019449372563954293,
|
| 458 |
+
"loss": 0.7646,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.0017512039527174932,
|
| 463 |
+
"grad_norm": 0.11669428646564484,
|
| 464 |
+
"learning_rate": 0.001942819704359693,
|
| 465 |
+
"loss": 0.9056,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.0017790008408558663,
|
| 470 |
+
"grad_norm": 0.08303668349981308,
|
| 471 |
+
"learning_rate": 0.0019406633966986826,
|
| 472 |
+
"loss": 0.7583,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.001806797728994239,
|
| 477 |
+
"grad_norm": 0.08263064175844193,
|
| 478 |
+
"learning_rate": 0.0019384684220497604,
|
| 479 |
+
"loss": 0.9233,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.001834594617132612,
|
| 484 |
+
"grad_norm": 0.08262008428573608,
|
| 485 |
+
"learning_rate": 0.0019362348706397372,
|
| 486 |
+
"loss": 0.8359,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.001862391505270985,
|
| 491 |
+
"grad_norm": 0.10420376062393188,
|
| 492 |
+
"learning_rate": 0.0019339628342811633,
|
| 493 |
+
"loss": 0.9978,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.0018901883934093577,
|
| 498 |
+
"grad_norm": 0.0830477699637413,
|
| 499 |
+
"learning_rate": 0.001931652406368554,
|
| 500 |
+
"loss": 0.8834,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.0019179852815477307,
|
| 505 |
+
"grad_norm": 0.08504804968833923,
|
| 506 |
+
"learning_rate": 0.0019293036818745519,
|
| 507 |
+
"loss": 0.9164,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.0019457821696861036,
|
| 512 |
+
"grad_norm": 0.08910652250051498,
|
| 513 |
+
"learning_rate": 0.0019269167573460217,
|
| 514 |
+
"loss": 0.9095,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.0019735790578244766,
|
| 519 |
+
"grad_norm": 0.09257230162620544,
|
| 520 |
+
"learning_rate": 0.0019244917309000815,
|
| 521 |
+
"loss": 0.7138,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.0020013759459628494,
|
| 526 |
+
"grad_norm": 0.09553885459899902,
|
| 527 |
+
"learning_rate": 0.0019220287022200706,
|
| 528 |
+
"loss": 0.9544,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.002029172834101222,
|
| 533 |
+
"grad_norm": 0.08890817314386368,
|
| 534 |
+
"learning_rate": 0.0019195277725514508,
|
| 535 |
+
"loss": 0.7013,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.0020569697222395955,
|
| 540 |
+
"grad_norm": 0.10616549849510193,
|
| 541 |
+
"learning_rate": 0.0019169890446976451,
|
| 542 |
+
"loss": 0.7119,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.0020847666103779683,
|
| 547 |
+
"grad_norm": 0.09758912026882172,
|
| 548 |
+
"learning_rate": 0.0019144126230158124,
|
| 549 |
+
"loss": 0.811,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.002112563498516341,
|
| 554 |
+
"grad_norm": 0.09248580783605576,
|
| 555 |
+
"learning_rate": 0.001911798613412557,
|
| 556 |
+
"loss": 0.8025,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.002140360386654714,
|
| 561 |
+
"grad_norm": 0.09431200474500656,
|
| 562 |
+
"learning_rate": 0.001909147123339575,
|
| 563 |
+
"loss": 0.7038,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.0021681572747930867,
|
| 568 |
+
"grad_norm": 0.09258091449737549,
|
| 569 |
+
"learning_rate": 0.001906458261789238,
|
| 570 |
+
"loss": 0.7752,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.00219595416293146,
|
| 575 |
+
"grad_norm": 0.08860747516155243,
|
| 576 |
+
"learning_rate": 0.0019037321392901135,
|
| 577 |
+
"loss": 0.6832,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.0022237510510698328,
|
| 582 |
+
"grad_norm": 0.10791260004043579,
|
| 583 |
+
"learning_rate": 0.001900968867902419,
|
| 584 |
+
"loss": 0.7183,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.0022515479392082056,
|
| 589 |
+
"grad_norm": 0.0878261998295784,
|
| 590 |
+
"learning_rate": 0.001898168561213419,
|
| 591 |
+
"loss": 0.6677,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.0022793448273465784,
|
| 596 |
+
"grad_norm": 0.10915020108222961,
|
| 597 |
+
"learning_rate": 0.0018953313343327532,
|
| 598 |
+
"loss": 0.8602,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.0023071417154849516,
|
| 603 |
+
"grad_norm": 0.10625939816236496,
|
| 604 |
+
"learning_rate": 0.001892457303887706,
|
| 605 |
+
"loss": 0.8385,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.0023349386036233244,
|
| 610 |
+
"grad_norm": 0.10215223580598831,
|
| 611 |
+
"learning_rate": 0.001889546588018412,
|
| 612 |
+
"loss": 0.7723,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.0023627354917616973,
|
| 617 |
+
"grad_norm": 0.08778225630521774,
|
| 618 |
+
"learning_rate": 0.0018865993063730002,
|
| 619 |
+
"loss": 0.6503,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.00239053237990007,
|
| 624 |
+
"grad_norm": 0.10662350058555603,
|
| 625 |
+
"learning_rate": 0.0018836155801026753,
|
| 626 |
+
"loss": 0.6592,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.002418329268038443,
|
| 631 |
+
"grad_norm": 0.10347293317317963,
|
| 632 |
+
"learning_rate": 0.001880595531856738,
|
| 633 |
+
"loss": 0.602,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.002446126156176816,
|
| 638 |
+
"grad_norm": 0.11098446696996689,
|
| 639 |
+
"learning_rate": 0.001877539285777543,
|
| 640 |
+
"loss": 0.7291,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.002473923044315189,
|
| 645 |
+
"grad_norm": 0.10774262994527817,
|
| 646 |
+
"learning_rate": 0.0018744469674953957,
|
| 647 |
+
"loss": 0.6501,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.0025017199324535618,
|
| 652 |
+
"grad_norm": 0.10596223175525665,
|
| 653 |
+
"learning_rate": 0.0018713187041233894,
|
| 654 |
+
"loss": 0.7274,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.0025295168205919346,
|
| 659 |
+
"grad_norm": 0.11689383536577225,
|
| 660 |
+
"learning_rate": 0.0018681546242521785,
|
| 661 |
+
"loss": 0.6693,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.002557313708730308,
|
| 666 |
+
"grad_norm": 0.11212435364723206,
|
| 667 |
+
"learning_rate": 0.0018649548579446936,
|
| 668 |
+
"loss": 0.6218,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.0025851105968686806,
|
| 673 |
+
"grad_norm": 0.13619789481163025,
|
| 674 |
+
"learning_rate": 0.0018617195367307952,
|
| 675 |
+
"loss": 0.5839,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.0026129074850070534,
|
| 680 |
+
"grad_norm": 0.18084552884101868,
|
| 681 |
+
"learning_rate": 0.001858448793601866,
|
| 682 |
+
"loss": 0.6083,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.0026407043731454262,
|
| 687 |
+
"grad_norm": 0.14780890941619873,
|
| 688 |
+
"learning_rate": 0.0018551427630053464,
|
| 689 |
+
"loss": 0.6095,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.0026685012612837995,
|
| 694 |
+
"grad_norm": 0.12189039587974548,
|
| 695 |
+
"learning_rate": 0.0018518015808392043,
|
| 696 |
+
"loss": 0.6313,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.0026962981494221723,
|
| 701 |
+
"grad_norm": 0.2006332129240036,
|
| 702 |
+
"learning_rate": 0.0018484253844463525,
|
| 703 |
+
"loss": 0.6528,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.002724095037560545,
|
| 708 |
+
"grad_norm": 0.19439570605754852,
|
| 709 |
+
"learning_rate": 0.0018450143126090013,
|
| 710 |
+
"loss": 0.655,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.002751891925698918,
|
| 715 |
+
"grad_norm": 0.23627929389476776,
|
| 716 |
+
"learning_rate": 0.0018415685055429532,
|
| 717 |
+
"loss": 0.6663,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.0027796888138372907,
|
| 722 |
+
"grad_norm": 0.22060082852840424,
|
| 723 |
+
"learning_rate": 0.0018380881048918405,
|
| 724 |
+
"loss": 0.6549,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.0027796888138372907,
|
| 729 |
+
"eval_loss": 1.0665974617004395,
|
| 730 |
+
"eval_runtime": 49.9362,
|
| 731 |
+
"eval_samples_per_second": 11.555,
|
| 732 |
+
"eval_steps_per_second": 5.787,
|
| 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": 6589805739638784.0,
|
| 763 |
"train_batch_size": 2,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|