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 50503544
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e014bafd26aa060f607da8eef483b6e7e82be9550547c1d471fd7b3ab0e10947
|
| 3 |
size 50503544
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 101184122
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d8acbf7d94fd8f2b136a5c18026b3b053386588e0323db70d945c591b1f9139
|
| 3 |
size 101184122
|
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 sha256:70fe1072043eb74154c0f5a2511bc78205c8ae7abae96348cc35ee1cc6003593
|
| 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": 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 +405,404 @@
|
|
| 405 |
"learning_rate": 5.868240888334653e-05,
|
| 406 |
"loss": 0.0647,
|
| 407 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 408 |
}
|
| 409 |
],
|
| 410 |
"logging_steps": 1,
|
|
@@ -419,12 +817,12 @@
|
|
| 419 |
"should_evaluate": false,
|
| 420 |
"should_log": false,
|
| 421 |
"should_save": true,
|
| 422 |
-
"should_training_stop":
|
| 423 |
},
|
| 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": 0.04627487274409996,
|
| 5 |
"eval_steps": 9,
|
| 6 |
+
"global_step": 100,
|
| 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": 0.0647,
|
| 407 |
"step": 50
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.023600185099490977,
|
| 411 |
+
"grad_norm": 2.2488627433776855,
|
| 412 |
+
"learning_rate": 5.695865504800327e-05,
|
| 413 |
+
"loss": 0.1892,
|
| 414 |
+
"step": 51
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.024062933826931976,
|
| 418 |
+
"grad_norm": 3.109647750854492,
|
| 419 |
+
"learning_rate": 5.522642316338268e-05,
|
| 420 |
+
"loss": 0.2971,
|
| 421 |
+
"step": 52
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.024525682554372975,
|
| 425 |
+
"grad_norm": 2.9143030643463135,
|
| 426 |
+
"learning_rate": 5.348782368720626e-05,
|
| 427 |
+
"loss": 0.4799,
|
| 428 |
+
"step": 53
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.024988431281813973,
|
| 432 |
+
"grad_norm": 3.5207865238189697,
|
| 433 |
+
"learning_rate": 5.174497483512506e-05,
|
| 434 |
+
"loss": 0.232,
|
| 435 |
+
"step": 54
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.024988431281813973,
|
| 439 |
+
"eval_loss": 0.19303588569164276,
|
| 440 |
+
"eval_runtime": 108.8496,
|
| 441 |
+
"eval_samples_per_second": 16.72,
|
| 442 |
+
"eval_steps_per_second": 2.095,
|
| 443 |
+
"step": 54
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.025451180009254976,
|
| 447 |
+
"grad_norm": 2.1500442028045654,
|
| 448 |
+
"learning_rate": 5e-05,
|
| 449 |
+
"loss": 0.2456,
|
| 450 |
+
"step": 55
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.025913928736695974,
|
| 454 |
+
"grad_norm": 5.131832122802734,
|
| 455 |
+
"learning_rate": 4.825502516487497e-05,
|
| 456 |
+
"loss": 0.6216,
|
| 457 |
+
"step": 56
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.026376677464136973,
|
| 461 |
+
"grad_norm": 1.655394434928894,
|
| 462 |
+
"learning_rate": 4.6512176312793736e-05,
|
| 463 |
+
"loss": 0.3206,
|
| 464 |
+
"step": 57
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.026839426191577972,
|
| 468 |
+
"grad_norm": 2.8779218196868896,
|
| 469 |
+
"learning_rate": 4.477357683661734e-05,
|
| 470 |
+
"loss": 0.3797,
|
| 471 |
+
"step": 58
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.027302174919018974,
|
| 475 |
+
"grad_norm": 1.5078076124191284,
|
| 476 |
+
"learning_rate": 4.3041344951996746e-05,
|
| 477 |
+
"loss": 0.0985,
|
| 478 |
+
"step": 59
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.027764923646459973,
|
| 482 |
+
"grad_norm": 1.3938862085342407,
|
| 483 |
+
"learning_rate": 4.131759111665349e-05,
|
| 484 |
+
"loss": 0.0939,
|
| 485 |
+
"step": 60
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.02822767237390097,
|
| 489 |
+
"grad_norm": 3.5782883167266846,
|
| 490 |
+
"learning_rate": 3.960441545911204e-05,
|
| 491 |
+
"loss": 0.2676,
|
| 492 |
+
"step": 61
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.02869042110134197,
|
| 496 |
+
"grad_norm": 1.3503000736236572,
|
| 497 |
+
"learning_rate": 3.790390522001662e-05,
|
| 498 |
+
"loss": 0.1315,
|
| 499 |
+
"step": 62
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.029153169828782972,
|
| 503 |
+
"grad_norm": 5.648515701293945,
|
| 504 |
+
"learning_rate": 3.6218132209150045e-05,
|
| 505 |
+
"loss": 0.1448,
|
| 506 |
+
"step": 63
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.029153169828782972,
|
| 510 |
+
"eval_loss": 0.17772692441940308,
|
| 511 |
+
"eval_runtime": 109.2089,
|
| 512 |
+
"eval_samples_per_second": 16.665,
|
| 513 |
+
"eval_steps_per_second": 2.088,
|
| 514 |
+
"step": 63
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.02961591855622397,
|
| 518 |
+
"grad_norm": 0.6387403011322021,
|
| 519 |
+
"learning_rate": 3.4549150281252636e-05,
|
| 520 |
+
"loss": 0.0981,
|
| 521 |
+
"step": 64
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.03007866728366497,
|
| 525 |
+
"grad_norm": 5.184665679931641,
|
| 526 |
+
"learning_rate": 3.289899283371657e-05,
|
| 527 |
+
"loss": 0.3126,
|
| 528 |
+
"step": 65
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.03054141601110597,
|
| 532 |
+
"grad_norm": 1.2718273401260376,
|
| 533 |
+
"learning_rate": 3.12696703292044e-05,
|
| 534 |
+
"loss": 0.2393,
|
| 535 |
+
"step": 66
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.031004164738546967,
|
| 539 |
+
"grad_norm": 0.9245361685752869,
|
| 540 |
+
"learning_rate": 2.9663167846209998e-05,
|
| 541 |
+
"loss": 0.2016,
|
| 542 |
+
"step": 67
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.03146691346598797,
|
| 546 |
+
"grad_norm": 3.493025541305542,
|
| 547 |
+
"learning_rate": 2.8081442660546125e-05,
|
| 548 |
+
"loss": 0.21,
|
| 549 |
+
"step": 68
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.031929662193428965,
|
| 553 |
+
"grad_norm": 3.8758113384246826,
|
| 554 |
+
"learning_rate": 2.6526421860705473e-05,
|
| 555 |
+
"loss": 0.2169,
|
| 556 |
+
"step": 69
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.03239241092086997,
|
| 560 |
+
"grad_norm": 4.775798797607422,
|
| 561 |
+
"learning_rate": 2.500000000000001e-05,
|
| 562 |
+
"loss": 0.3688,
|
| 563 |
+
"step": 70
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.03285515964831097,
|
| 567 |
+
"grad_norm": 1.524680495262146,
|
| 568 |
+
"learning_rate": 2.350403678833976e-05,
|
| 569 |
+
"loss": 0.1639,
|
| 570 |
+
"step": 71
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.033317908375751965,
|
| 574 |
+
"grad_norm": 1.8387486934661865,
|
| 575 |
+
"learning_rate": 2.2040354826462668e-05,
|
| 576 |
+
"loss": 0.224,
|
| 577 |
+
"step": 72
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.033317908375751965,
|
| 581 |
+
"eval_loss": 0.18191145360469818,
|
| 582 |
+
"eval_runtime": 108.8432,
|
| 583 |
+
"eval_samples_per_second": 16.721,
|
| 584 |
+
"eval_steps_per_second": 2.095,
|
| 585 |
+
"step": 72
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.03378065710319297,
|
| 589 |
+
"grad_norm": 0.8230963945388794,
|
| 590 |
+
"learning_rate": 2.061073738537635e-05,
|
| 591 |
+
"loss": 0.1038,
|
| 592 |
+
"step": 73
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.03424340583063397,
|
| 596 |
+
"grad_norm": 4.8260722160339355,
|
| 597 |
+
"learning_rate": 1.9216926233717085e-05,
|
| 598 |
+
"loss": 0.2824,
|
| 599 |
+
"step": 74
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.034706154558074964,
|
| 603 |
+
"grad_norm": 2.352128267288208,
|
| 604 |
+
"learning_rate": 1.7860619515673033e-05,
|
| 605 |
+
"loss": 0.2273,
|
| 606 |
+
"step": 75
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.035168903285515966,
|
| 610 |
+
"grad_norm": 1.7466846704483032,
|
| 611 |
+
"learning_rate": 1.6543469682057106e-05,
|
| 612 |
+
"loss": 0.2123,
|
| 613 |
+
"step": 76
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.03563165201295696,
|
| 617 |
+
"grad_norm": 1.6248657703399658,
|
| 618 |
+
"learning_rate": 1.526708147705013e-05,
|
| 619 |
+
"loss": 0.1353,
|
| 620 |
+
"step": 77
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.036094400740397964,
|
| 624 |
+
"grad_norm": 1.3933769464492798,
|
| 625 |
+
"learning_rate": 1.4033009983067452e-05,
|
| 626 |
+
"loss": 0.2277,
|
| 627 |
+
"step": 78
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.036557149467838966,
|
| 631 |
+
"grad_norm": 1.7838780879974365,
|
| 632 |
+
"learning_rate": 1.2842758726130283e-05,
|
| 633 |
+
"loss": 0.2165,
|
| 634 |
+
"step": 79
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.03701989819527996,
|
| 638 |
+
"grad_norm": 1.778045415878296,
|
| 639 |
+
"learning_rate": 1.1697777844051105e-05,
|
| 640 |
+
"loss": 0.1446,
|
| 641 |
+
"step": 80
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.037482646922720964,
|
| 645 |
+
"grad_norm": 2.422689199447632,
|
| 646 |
+
"learning_rate": 1.0599462319663905e-05,
|
| 647 |
+
"loss": 0.1707,
|
| 648 |
+
"step": 81
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.037482646922720964,
|
| 652 |
+
"eval_loss": 0.1773979812860489,
|
| 653 |
+
"eval_runtime": 108.8294,
|
| 654 |
+
"eval_samples_per_second": 16.723,
|
| 655 |
+
"eval_steps_per_second": 2.095,
|
| 656 |
+
"step": 81
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 0.03794539565016196,
|
| 660 |
+
"grad_norm": 2.397000312805176,
|
| 661 |
+
"learning_rate": 9.549150281252633e-06,
|
| 662 |
+
"loss": 0.2127,
|
| 663 |
+
"step": 82
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.03840814437760296,
|
| 667 |
+
"grad_norm": 2.0644094944000244,
|
| 668 |
+
"learning_rate": 8.548121372247918e-06,
|
| 669 |
+
"loss": 0.2302,
|
| 670 |
+
"step": 83
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 0.03887089310504396,
|
| 674 |
+
"grad_norm": 1.9861756563186646,
|
| 675 |
+
"learning_rate": 7.597595192178702e-06,
|
| 676 |
+
"loss": 0.2531,
|
| 677 |
+
"step": 84
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 0.03933364183248496,
|
| 681 |
+
"grad_norm": 1.7267298698425293,
|
| 682 |
+
"learning_rate": 6.698729810778065e-06,
|
| 683 |
+
"loss": 0.2176,
|
| 684 |
+
"step": 85
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 0.03979639055992596,
|
| 688 |
+
"grad_norm": 0.7792419791221619,
|
| 689 |
+
"learning_rate": 5.852620357053651e-06,
|
| 690 |
+
"loss": 0.0763,
|
| 691 |
+
"step": 86
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 0.04025913928736696,
|
| 695 |
+
"grad_norm": 1.2674682140350342,
|
| 696 |
+
"learning_rate": 5.060297685041659e-06,
|
| 697 |
+
"loss": 0.1173,
|
| 698 |
+
"step": 87
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.04072188801480796,
|
| 702 |
+
"grad_norm": 1.3142675161361694,
|
| 703 |
+
"learning_rate": 4.322727117869951e-06,
|
| 704 |
+
"loss": 0.1326,
|
| 705 |
+
"step": 88
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.04118463674224896,
|
| 709 |
+
"grad_norm": 3.0400171279907227,
|
| 710 |
+
"learning_rate": 3.6408072716606346e-06,
|
| 711 |
+
"loss": 0.3707,
|
| 712 |
+
"step": 89
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 0.041647385469689956,
|
| 716 |
+
"grad_norm": 1.8144176006317139,
|
| 717 |
+
"learning_rate": 3.0153689607045845e-06,
|
| 718 |
+
"loss": 0.1973,
|
| 719 |
+
"step": 90
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 0.041647385469689956,
|
| 723 |
+
"eval_loss": 0.1692516952753067,
|
| 724 |
+
"eval_runtime": 108.9085,
|
| 725 |
+
"eval_samples_per_second": 16.711,
|
| 726 |
+
"eval_steps_per_second": 2.094,
|
| 727 |
+
"step": 90
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.04211013419713096,
|
| 731 |
+
"grad_norm": 0.7678631544113159,
|
| 732 |
+
"learning_rate": 2.4471741852423237e-06,
|
| 733 |
+
"loss": 0.0723,
|
| 734 |
+
"step": 91
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.04257288292457196,
|
| 738 |
+
"grad_norm": 7.679274559020996,
|
| 739 |
+
"learning_rate": 1.9369152030840556e-06,
|
| 740 |
+
"loss": 0.385,
|
| 741 |
+
"step": 92
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.043035631652012955,
|
| 745 |
+
"grad_norm": 1.0919711589813232,
|
| 746 |
+
"learning_rate": 1.4852136862001764e-06,
|
| 747 |
+
"loss": 0.2062,
|
| 748 |
+
"step": 93
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 0.04349838037945396,
|
| 752 |
+
"grad_norm": 0.8858644366264343,
|
| 753 |
+
"learning_rate": 1.0926199633097157e-06,
|
| 754 |
+
"loss": 0.0903,
|
| 755 |
+
"step": 94
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 0.04396112910689495,
|
| 759 |
+
"grad_norm": 1.427178978919983,
|
| 760 |
+
"learning_rate": 7.596123493895991e-07,
|
| 761 |
+
"loss": 0.2173,
|
| 762 |
+
"step": 95
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.044423877834335955,
|
| 766 |
+
"grad_norm": 2.144537925720215,
|
| 767 |
+
"learning_rate": 4.865965629214819e-07,
|
| 768 |
+
"loss": 0.221,
|
| 769 |
+
"step": 96
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 0.04488662656177696,
|
| 773 |
+
"grad_norm": 2.2111377716064453,
|
| 774 |
+
"learning_rate": 2.7390523158633554e-07,
|
| 775 |
+
"loss": 0.1411,
|
| 776 |
+
"step": 97
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 0.04534937528921795,
|
| 780 |
+
"grad_norm": 1.809673547744751,
|
| 781 |
+
"learning_rate": 1.2179748700879012e-07,
|
| 782 |
+
"loss": 0.1562,
|
| 783 |
+
"step": 98
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.045812124016658955,
|
| 787 |
+
"grad_norm": 1.1327333450317383,
|
| 788 |
+
"learning_rate": 3.04586490452119e-08,
|
| 789 |
+
"loss": 0.0806,
|
| 790 |
+
"step": 99
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.045812124016658955,
|
| 794 |
+
"eval_loss": 0.16798387467861176,
|
| 795 |
+
"eval_runtime": 109.2031,
|
| 796 |
+
"eval_samples_per_second": 16.666,
|
| 797 |
+
"eval_steps_per_second": 2.088,
|
| 798 |
+
"step": 99
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 0.04627487274409996,
|
| 802 |
+
"grad_norm": 2.2550415992736816,
|
| 803 |
+
"learning_rate": 0.0,
|
| 804 |
+
"loss": 0.4077,
|
| 805 |
+
"step": 100
|
| 806 |
}
|
| 807 |
],
|
| 808 |
"logging_steps": 1,
|
|
|
|
| 817 |
"should_evaluate": false,
|
| 818 |
"should_log": false,
|
| 819 |
"should_save": true,
|
| 820 |
+
"should_training_stop": true
|
| 821 |
},
|
| 822 |
"attributes": {}
|
| 823 |
}
|
| 824 |
},
|
| 825 |
+
"total_flos": 1.9969754177470464e+16,
|
| 826 |
"train_batch_size": 8,
|
| 827 |
"trial_name": null,
|
| 828 |
"trial_params": null
|