Training in progress, step 75, 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 167832240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80c52138cf2c59d45e1831c51de681c4950b03a7a39d40a380c4ada227d37277
|
| 3 |
size 167832240
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 335922386
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cab4f46ba392e9fd9eedff9b9476dca93994426da8e8e1ae3021c4fb71dcf33c
|
| 3 |
size 335922386
|
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:d0c2aeb48c97bc17fc16027c087a1f2b9b14a3b5da40e726c4c4179d5382c495
|
| 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:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
|
| 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": 9,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -405,6 +405,205 @@
|
|
| 405 |
"learning_rate": 5.868240888334653e-05,
|
| 406 |
"loss": 0.0931,
|
| 407 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 408 |
}
|
| 409 |
],
|
| 410 |
"logging_steps": 1,
|
|
@@ -424,7 +623,7 @@
|
|
| 424 |
"attributes": {}
|
| 425 |
}
|
| 426 |
},
|
| 427 |
-
"total_flos":
|
| 428 |
"train_batch_size": 8,
|
| 429 |
"trial_name": null,
|
| 430 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.18404907975460122,
|
| 5 |
"eval_steps": 9,
|
| 6 |
+
"global_step": 75,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 405 |
"learning_rate": 5.868240888334653e-05,
|
| 406 |
"loss": 0.0931,
|
| 407 |
"step": 50
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.12515337423312883,
|
| 411 |
+
"grad_norm": 0.12616045773029327,
|
| 412 |
+
"learning_rate": 5.695865504800327e-05,
|
| 413 |
+
"loss": 0.0895,
|
| 414 |
+
"step": 51
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.1276073619631902,
|
| 418 |
+
"grad_norm": 0.133722722530365,
|
| 419 |
+
"learning_rate": 5.522642316338268e-05,
|
| 420 |
+
"loss": 0.0935,
|
| 421 |
+
"step": 52
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.13006134969325153,
|
| 425 |
+
"grad_norm": 0.2328999936580658,
|
| 426 |
+
"learning_rate": 5.348782368720626e-05,
|
| 427 |
+
"loss": 0.0983,
|
| 428 |
+
"step": 53
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.1325153374233129,
|
| 432 |
+
"grad_norm": 0.1427900344133377,
|
| 433 |
+
"learning_rate": 5.174497483512506e-05,
|
| 434 |
+
"loss": 0.0799,
|
| 435 |
+
"step": 54
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.1325153374233129,
|
| 439 |
+
"eval_loss": 0.08606944978237152,
|
| 440 |
+
"eval_runtime": 72.534,
|
| 441 |
+
"eval_samples_per_second": 4.729,
|
| 442 |
+
"eval_steps_per_second": 0.593,
|
| 443 |
+
"step": 54
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.13496932515337423,
|
| 447 |
+
"grad_norm": 0.16906791925430298,
|
| 448 |
+
"learning_rate": 5e-05,
|
| 449 |
+
"loss": 0.0607,
|
| 450 |
+
"step": 55
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.1374233128834356,
|
| 454 |
+
"grad_norm": 0.13459601998329163,
|
| 455 |
+
"learning_rate": 4.825502516487497e-05,
|
| 456 |
+
"loss": 0.0849,
|
| 457 |
+
"step": 56
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.13987730061349693,
|
| 461 |
+
"grad_norm": 0.17573149502277374,
|
| 462 |
+
"learning_rate": 4.6512176312793736e-05,
|
| 463 |
+
"loss": 0.0727,
|
| 464 |
+
"step": 57
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.1423312883435583,
|
| 468 |
+
"grad_norm": 0.14718861877918243,
|
| 469 |
+
"learning_rate": 4.477357683661734e-05,
|
| 470 |
+
"loss": 0.0842,
|
| 471 |
+
"step": 58
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.14478527607361963,
|
| 475 |
+
"grad_norm": 0.13461712002754211,
|
| 476 |
+
"learning_rate": 4.3041344951996746e-05,
|
| 477 |
+
"loss": 0.0713,
|
| 478 |
+
"step": 59
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.147239263803681,
|
| 482 |
+
"grad_norm": 0.14543554186820984,
|
| 483 |
+
"learning_rate": 4.131759111665349e-05,
|
| 484 |
+
"loss": 0.0835,
|
| 485 |
+
"step": 60
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.14969325153374233,
|
| 489 |
+
"grad_norm": 0.1449080854654312,
|
| 490 |
+
"learning_rate": 3.960441545911204e-05,
|
| 491 |
+
"loss": 0.076,
|
| 492 |
+
"step": 61
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.1521472392638037,
|
| 496 |
+
"grad_norm": 0.15544362366199493,
|
| 497 |
+
"learning_rate": 3.790390522001662e-05,
|
| 498 |
+
"loss": 0.0936,
|
| 499 |
+
"step": 62
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.15460122699386503,
|
| 503 |
+
"grad_norm": 0.1345524936914444,
|
| 504 |
+
"learning_rate": 3.6218132209150045e-05,
|
| 505 |
+
"loss": 0.0855,
|
| 506 |
+
"step": 63
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.15460122699386503,
|
| 510 |
+
"eval_loss": 0.08375449478626251,
|
| 511 |
+
"eval_runtime": 72.5986,
|
| 512 |
+
"eval_samples_per_second": 4.725,
|
| 513 |
+
"eval_steps_per_second": 0.592,
|
| 514 |
+
"step": 63
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.1570552147239264,
|
| 518 |
+
"grad_norm": 0.1138109564781189,
|
| 519 |
+
"learning_rate": 3.4549150281252636e-05,
|
| 520 |
+
"loss": 0.076,
|
| 521 |
+
"step": 64
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.15950920245398773,
|
| 525 |
+
"grad_norm": 0.14898569881916046,
|
| 526 |
+
"learning_rate": 3.289899283371657e-05,
|
| 527 |
+
"loss": 0.0799,
|
| 528 |
+
"step": 65
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.1619631901840491,
|
| 532 |
+
"grad_norm": 0.13991095125675201,
|
| 533 |
+
"learning_rate": 3.12696703292044e-05,
|
| 534 |
+
"loss": 0.0779,
|
| 535 |
+
"step": 66
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.16441717791411042,
|
| 539 |
+
"grad_norm": 0.2358105480670929,
|
| 540 |
+
"learning_rate": 2.9663167846209998e-05,
|
| 541 |
+
"loss": 0.1083,
|
| 542 |
+
"step": 67
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.1668711656441718,
|
| 546 |
+
"grad_norm": 0.1775648146867752,
|
| 547 |
+
"learning_rate": 2.8081442660546125e-05,
|
| 548 |
+
"loss": 0.0879,
|
| 549 |
+
"step": 68
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.16932515337423312,
|
| 553 |
+
"grad_norm": 0.1891743540763855,
|
| 554 |
+
"learning_rate": 2.6526421860705473e-05,
|
| 555 |
+
"loss": 0.102,
|
| 556 |
+
"step": 69
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.17177914110429449,
|
| 560 |
+
"grad_norm": 0.16097727417945862,
|
| 561 |
+
"learning_rate": 2.500000000000001e-05,
|
| 562 |
+
"loss": 0.0914,
|
| 563 |
+
"step": 70
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.17423312883435582,
|
| 567 |
+
"grad_norm": 0.09334325790405273,
|
| 568 |
+
"learning_rate": 2.350403678833976e-05,
|
| 569 |
+
"loss": 0.0564,
|
| 570 |
+
"step": 71
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.17668711656441718,
|
| 574 |
+
"grad_norm": 0.12249859422445297,
|
| 575 |
+
"learning_rate": 2.2040354826462668e-05,
|
| 576 |
+
"loss": 0.06,
|
| 577 |
+
"step": 72
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.17668711656441718,
|
| 581 |
+
"eval_loss": 0.08157961070537567,
|
| 582 |
+
"eval_runtime": 72.6132,
|
| 583 |
+
"eval_samples_per_second": 4.724,
|
| 584 |
+
"eval_steps_per_second": 0.592,
|
| 585 |
+
"step": 72
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.17914110429447852,
|
| 589 |
+
"grad_norm": 0.12387010455131531,
|
| 590 |
+
"learning_rate": 2.061073738537635e-05,
|
| 591 |
+
"loss": 0.0835,
|
| 592 |
+
"step": 73
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.18159509202453988,
|
| 596 |
+
"grad_norm": 0.1005992442369461,
|
| 597 |
+
"learning_rate": 1.9216926233717085e-05,
|
| 598 |
+
"loss": 0.0569,
|
| 599 |
+
"step": 74
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.18404907975460122,
|
| 603 |
+
"grad_norm": 0.1461544632911682,
|
| 604 |
+
"learning_rate": 1.7860619515673033e-05,
|
| 605 |
+
"loss": 0.0591,
|
| 606 |
+
"step": 75
|
| 607 |
}
|
| 608 |
],
|
| 609 |
"logging_steps": 1,
|
|
|
|
| 623 |
"attributes": {}
|
| 624 |
}
|
| 625 |
},
|
| 626 |
+
"total_flos": 9.57034595792978e+16,
|
| 627 |
"train_batch_size": 8,
|
| 628 |
"trial_name": null,
|
| 629 |
"trial_params": null
|