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 2269195160
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:107d672c18b8a62f5938a854dbb1b4aef7780b39f2889fe38f142b72df38458a
|
| 3 |
size 2269195160
|
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:d9d267eb13fafbb79e310d1608520391a110c5100b89224270b9ae67b19a9e8a
|
| 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 sha256:938f3c5b1e74025dea7f7ecdfc1c134ecd27894e7d032a9550d538ee63172b38
|
| 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": 0.2474,
|
| 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": 0.18165304268846502,
|
| 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": 0.2474,
|
| 407 |
"step": 50
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.09264305177111716,
|
| 411 |
+
"grad_norm": 0.31370481848716736,
|
| 412 |
+
"learning_rate": 5.695865504800327e-05,
|
| 413 |
+
"loss": 0.2895,
|
| 414 |
+
"step": 51
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.09445958219800181,
|
| 418 |
+
"grad_norm": 0.26035645604133606,
|
| 419 |
+
"learning_rate": 5.522642316338268e-05,
|
| 420 |
+
"loss": 0.2501,
|
| 421 |
+
"step": 52
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.09627611262488647,
|
| 425 |
+
"grad_norm": 0.3116852343082428,
|
| 426 |
+
"learning_rate": 5.348782368720626e-05,
|
| 427 |
+
"loss": 0.2527,
|
| 428 |
+
"step": 53
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.09809264305177112,
|
| 432 |
+
"grad_norm": 0.2944983243942261,
|
| 433 |
+
"learning_rate": 5.174497483512506e-05,
|
| 434 |
+
"loss": 0.2754,
|
| 435 |
+
"step": 54
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.09809264305177112,
|
| 439 |
+
"eval_loss": 0.27958133816719055,
|
| 440 |
+
"eval_runtime": 108.6945,
|
| 441 |
+
"eval_samples_per_second": 4.269,
|
| 442 |
+
"eval_steps_per_second": 0.534,
|
| 443 |
+
"step": 54
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.09990917347865577,
|
| 447 |
+
"grad_norm": 0.350281685590744,
|
| 448 |
+
"learning_rate": 5e-05,
|
| 449 |
+
"loss": 0.2596,
|
| 450 |
+
"step": 55
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.10172570390554042,
|
| 454 |
+
"grad_norm": 0.33483561873435974,
|
| 455 |
+
"learning_rate": 4.825502516487497e-05,
|
| 456 |
+
"loss": 0.3078,
|
| 457 |
+
"step": 56
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.10354223433242507,
|
| 461 |
+
"grad_norm": 0.28896334767341614,
|
| 462 |
+
"learning_rate": 4.6512176312793736e-05,
|
| 463 |
+
"loss": 0.2864,
|
| 464 |
+
"step": 57
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.10535876475930972,
|
| 468 |
+
"grad_norm": 0.27719321846961975,
|
| 469 |
+
"learning_rate": 4.477357683661734e-05,
|
| 470 |
+
"loss": 0.2958,
|
| 471 |
+
"step": 58
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.10717529518619437,
|
| 475 |
+
"grad_norm": 0.31106963753700256,
|
| 476 |
+
"learning_rate": 4.3041344951996746e-05,
|
| 477 |
+
"loss": 0.2851,
|
| 478 |
+
"step": 59
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.10899182561307902,
|
| 482 |
+
"grad_norm": 0.253791481256485,
|
| 483 |
+
"learning_rate": 4.131759111665349e-05,
|
| 484 |
+
"loss": 0.2168,
|
| 485 |
+
"step": 60
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.11080835603996367,
|
| 489 |
+
"grad_norm": 0.37355419993400574,
|
| 490 |
+
"learning_rate": 3.960441545911204e-05,
|
| 491 |
+
"loss": 0.3131,
|
| 492 |
+
"step": 61
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.11262488646684832,
|
| 496 |
+
"grad_norm": 0.40072622895240784,
|
| 497 |
+
"learning_rate": 3.790390522001662e-05,
|
| 498 |
+
"loss": 0.3205,
|
| 499 |
+
"step": 62
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.11444141689373297,
|
| 503 |
+
"grad_norm": 0.27985572814941406,
|
| 504 |
+
"learning_rate": 3.6218132209150045e-05,
|
| 505 |
+
"loss": 0.2427,
|
| 506 |
+
"step": 63
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.11444141689373297,
|
| 510 |
+
"eval_loss": 0.27756959199905396,
|
| 511 |
+
"eval_runtime": 108.6448,
|
| 512 |
+
"eval_samples_per_second": 4.271,
|
| 513 |
+
"eval_steps_per_second": 0.534,
|
| 514 |
+
"step": 63
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.11625794732061762,
|
| 518 |
+
"grad_norm": 0.28662416338920593,
|
| 519 |
+
"learning_rate": 3.4549150281252636e-05,
|
| 520 |
+
"loss": 0.3106,
|
| 521 |
+
"step": 64
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.11807447774750227,
|
| 525 |
+
"grad_norm": 0.29447686672210693,
|
| 526 |
+
"learning_rate": 3.289899283371657e-05,
|
| 527 |
+
"loss": 0.2368,
|
| 528 |
+
"step": 65
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.11989100817438691,
|
| 532 |
+
"grad_norm": 0.2652858793735504,
|
| 533 |
+
"learning_rate": 3.12696703292044e-05,
|
| 534 |
+
"loss": 0.2319,
|
| 535 |
+
"step": 66
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.12170753860127158,
|
| 539 |
+
"grad_norm": 0.29174622893333435,
|
| 540 |
+
"learning_rate": 2.9663167846209998e-05,
|
| 541 |
+
"loss": 0.3058,
|
| 542 |
+
"step": 67
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.12352406902815623,
|
| 546 |
+
"grad_norm": 0.30116814374923706,
|
| 547 |
+
"learning_rate": 2.8081442660546125e-05,
|
| 548 |
+
"loss": 0.2818,
|
| 549 |
+
"step": 68
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.12534059945504086,
|
| 553 |
+
"grad_norm": 0.30650588870048523,
|
| 554 |
+
"learning_rate": 2.6526421860705473e-05,
|
| 555 |
+
"loss": 0.2743,
|
| 556 |
+
"step": 69
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.1271571298819255,
|
| 560 |
+
"grad_norm": 0.27553582191467285,
|
| 561 |
+
"learning_rate": 2.500000000000001e-05,
|
| 562 |
+
"loss": 0.2155,
|
| 563 |
+
"step": 70
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.12897366030881016,
|
| 567 |
+
"grad_norm": 0.2803662121295929,
|
| 568 |
+
"learning_rate": 2.350403678833976e-05,
|
| 569 |
+
"loss": 0.2782,
|
| 570 |
+
"step": 71
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.1307901907356948,
|
| 574 |
+
"grad_norm": 0.26244497299194336,
|
| 575 |
+
"learning_rate": 2.2040354826462668e-05,
|
| 576 |
+
"loss": 0.1971,
|
| 577 |
+
"step": 72
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.1307901907356948,
|
| 581 |
+
"eval_loss": 0.2747555673122406,
|
| 582 |
+
"eval_runtime": 108.6235,
|
| 583 |
+
"eval_samples_per_second": 4.272,
|
| 584 |
+
"eval_steps_per_second": 0.534,
|
| 585 |
+
"step": 72
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.13260672116257946,
|
| 589 |
+
"grad_norm": 0.29561930894851685,
|
| 590 |
+
"learning_rate": 2.061073738537635e-05,
|
| 591 |
+
"loss": 0.3123,
|
| 592 |
+
"step": 73
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.1344232515894641,
|
| 596 |
+
"grad_norm": 0.3003482520580292,
|
| 597 |
+
"learning_rate": 1.9216926233717085e-05,
|
| 598 |
+
"loss": 0.3104,
|
| 599 |
+
"step": 74
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.1362397820163488,
|
| 603 |
+
"grad_norm": 0.2806616425514221,
|
| 604 |
+
"learning_rate": 1.7860619515673033e-05,
|
| 605 |
+
"loss": 0.2908,
|
| 606 |
+
"step": 75
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.13805631244323344,
|
| 610 |
+
"grad_norm": 0.331093430519104,
|
| 611 |
+
"learning_rate": 1.6543469682057106e-05,
|
| 612 |
+
"loss": 0.2559,
|
| 613 |
+
"step": 76
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.13987284287011809,
|
| 617 |
+
"grad_norm": 0.2987718880176544,
|
| 618 |
+
"learning_rate": 1.526708147705013e-05,
|
| 619 |
+
"loss": 0.2594,
|
| 620 |
+
"step": 77
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.14168937329700274,
|
| 624 |
+
"grad_norm": 0.2768915593624115,
|
| 625 |
+
"learning_rate": 1.4033009983067452e-05,
|
| 626 |
+
"loss": 0.274,
|
| 627 |
+
"step": 78
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.14350590372388738,
|
| 631 |
+
"grad_norm": 0.28360041975975037,
|
| 632 |
+
"learning_rate": 1.2842758726130283e-05,
|
| 633 |
+
"loss": 0.2638,
|
| 634 |
+
"step": 79
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.14532243415077203,
|
| 638 |
+
"grad_norm": 0.28000327944755554,
|
| 639 |
+
"learning_rate": 1.1697777844051105e-05,
|
| 640 |
+
"loss": 0.2937,
|
| 641 |
+
"step": 80
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.14713896457765668,
|
| 645 |
+
"grad_norm": 0.3231543004512787,
|
| 646 |
+
"learning_rate": 1.0599462319663905e-05,
|
| 647 |
+
"loss": 0.2612,
|
| 648 |
+
"step": 81
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.14713896457765668,
|
| 652 |
+
"eval_loss": 0.27281635999679565,
|
| 653 |
+
"eval_runtime": 108.6714,
|
| 654 |
+
"eval_samples_per_second": 4.27,
|
| 655 |
+
"eval_steps_per_second": 0.534,
|
| 656 |
+
"step": 81
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 0.14895549500454133,
|
| 660 |
+
"grad_norm": 0.352360337972641,
|
| 661 |
+
"learning_rate": 9.549150281252633e-06,
|
| 662 |
+
"loss": 0.2377,
|
| 663 |
+
"step": 82
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.15077202543142598,
|
| 667 |
+
"grad_norm": 0.29913556575775146,
|
| 668 |
+
"learning_rate": 8.548121372247918e-06,
|
| 669 |
+
"loss": 0.297,
|
| 670 |
+
"step": 83
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 0.15258855585831063,
|
| 674 |
+
"grad_norm": 0.3100139796733856,
|
| 675 |
+
"learning_rate": 7.597595192178702e-06,
|
| 676 |
+
"loss": 0.3254,
|
| 677 |
+
"step": 84
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 0.15440508628519528,
|
| 681 |
+
"grad_norm": 0.2626723051071167,
|
| 682 |
+
"learning_rate": 6.698729810778065e-06,
|
| 683 |
+
"loss": 0.2542,
|
| 684 |
+
"step": 85
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 0.15622161671207993,
|
| 688 |
+
"grad_norm": 0.2944123148918152,
|
| 689 |
+
"learning_rate": 5.852620357053651e-06,
|
| 690 |
+
"loss": 0.3606,
|
| 691 |
+
"step": 86
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 0.15803814713896458,
|
| 695 |
+
"grad_norm": 0.34874227643013,
|
| 696 |
+
"learning_rate": 5.060297685041659e-06,
|
| 697 |
+
"loss": 0.3298,
|
| 698 |
+
"step": 87
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.15985467756584923,
|
| 702 |
+
"grad_norm": 0.3021911680698395,
|
| 703 |
+
"learning_rate": 4.322727117869951e-06,
|
| 704 |
+
"loss": 0.356,
|
| 705 |
+
"step": 88
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.16167120799273388,
|
| 709 |
+
"grad_norm": 0.26396703720092773,
|
| 710 |
+
"learning_rate": 3.6408072716606346e-06,
|
| 711 |
+
"loss": 0.2144,
|
| 712 |
+
"step": 89
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 0.16348773841961853,
|
| 716 |
+
"grad_norm": 0.29361093044281006,
|
| 717 |
+
"learning_rate": 3.0153689607045845e-06,
|
| 718 |
+
"loss": 0.2807,
|
| 719 |
+
"step": 90
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 0.16348773841961853,
|
| 723 |
+
"eval_loss": 0.2723295986652374,
|
| 724 |
+
"eval_runtime": 108.6297,
|
| 725 |
+
"eval_samples_per_second": 4.271,
|
| 726 |
+
"eval_steps_per_second": 0.534,
|
| 727 |
+
"step": 90
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.16530426884650318,
|
| 731 |
+
"grad_norm": 0.2374623417854309,
|
| 732 |
+
"learning_rate": 2.4471741852423237e-06,
|
| 733 |
+
"loss": 0.2156,
|
| 734 |
+
"step": 91
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.16712079927338783,
|
| 738 |
+
"grad_norm": 0.26733702421188354,
|
| 739 |
+
"learning_rate": 1.9369152030840556e-06,
|
| 740 |
+
"loss": 0.2058,
|
| 741 |
+
"step": 92
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.16893732970027248,
|
| 745 |
+
"grad_norm": 0.2634991407394409,
|
| 746 |
+
"learning_rate": 1.4852136862001764e-06,
|
| 747 |
+
"loss": 0.2776,
|
| 748 |
+
"step": 93
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 0.17075386012715713,
|
| 752 |
+
"grad_norm": 0.2750228941440582,
|
| 753 |
+
"learning_rate": 1.0926199633097157e-06,
|
| 754 |
+
"loss": 0.2635,
|
| 755 |
+
"step": 94
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 0.17257039055404177,
|
| 759 |
+
"grad_norm": 0.2913649380207062,
|
| 760 |
+
"learning_rate": 7.596123493895991e-07,
|
| 761 |
+
"loss": 0.2466,
|
| 762 |
+
"step": 95
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.17438692098092642,
|
| 766 |
+
"grad_norm": 0.30093085765838623,
|
| 767 |
+
"learning_rate": 4.865965629214819e-07,
|
| 768 |
+
"loss": 0.2855,
|
| 769 |
+
"step": 96
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 0.17620345140781107,
|
| 773 |
+
"grad_norm": 0.32675302028656006,
|
| 774 |
+
"learning_rate": 2.7390523158633554e-07,
|
| 775 |
+
"loss": 0.2625,
|
| 776 |
+
"step": 97
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 0.17801998183469572,
|
| 780 |
+
"grad_norm": 0.2559075653553009,
|
| 781 |
+
"learning_rate": 1.2179748700879012e-07,
|
| 782 |
+
"loss": 0.26,
|
| 783 |
+
"step": 98
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.17983651226158037,
|
| 787 |
+
"grad_norm": 0.3088376224040985,
|
| 788 |
+
"learning_rate": 3.04586490452119e-08,
|
| 789 |
+
"loss": 0.298,
|
| 790 |
+
"step": 99
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.17983651226158037,
|
| 794 |
+
"eval_loss": 0.27232545614242554,
|
| 795 |
+
"eval_runtime": 108.5508,
|
| 796 |
+
"eval_samples_per_second": 4.274,
|
| 797 |
+
"eval_steps_per_second": 0.534,
|
| 798 |
+
"step": 99
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 0.18165304268846502,
|
| 802 |
+
"grad_norm": 0.28909745812416077,
|
| 803 |
+
"learning_rate": 0.0,
|
| 804 |
+
"loss": 0.2986,
|
| 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": 1.4281337959612416e+17,
|
| 826 |
"train_batch_size": 8,
|
| 827 |
"trial_name": null,
|
| 828 |
"trial_params": null
|