Training in progress, step 1000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1304192904
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50ca524f54edaad2efaf52b5094690e6a44a5385b9e7f53ef2c19f513752a265
|
| 3 |
size 1304192904
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2608620781
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eec4148b0f8e105171cc96f1d25b9ea52f1a3ccfeb7c98ad54edc804e3b3c50c
|
| 3 |
size 2608620781
|
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 sha256:6410f39a0e7c645ed67ec28686db1c7ce44af3a9fe7fbe74340514fa7e64b446
|
| 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:a73fd5a100d4ccdd00ffce46e090807f48fb5f542090f5c0a86653f3b6372be2
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.2986587882041931,
|
| 3 |
"best_model_checkpoint": "./results/checkpoint-180",
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 20,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -407,6 +407,406 @@
|
|
| 407 |
"eval_samples_per_second": 9.895,
|
| 408 |
"eval_steps_per_second": 2.522,
|
| 409 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 410 |
}
|
| 411 |
],
|
| 412 |
"logging_steps": 20,
|
|
@@ -426,7 +826,7 @@
|
|
| 426 |
"attributes": {}
|
| 427 |
}
|
| 428 |
},
|
| 429 |
-
"total_flos":
|
| 430 |
"train_batch_size": 4,
|
| 431 |
"trial_name": null,
|
| 432 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.2986587882041931,
|
| 3 |
"best_model_checkpoint": "./results/checkpoint-180",
|
| 4 |
+
"epoch": 3.0211480362537766,
|
| 5 |
"eval_steps": 20,
|
| 6 |
+
"global_step": 1000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 407 |
"eval_samples_per_second": 9.895,
|
| 408 |
"eval_steps_per_second": 2.522,
|
| 409 |
"step": 500
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.5709969788519638,
|
| 413 |
+
"grad_norm": 0.41706299781799316,
|
| 414 |
+
"learning_rate": 1.3716012084592145e-05,
|
| 415 |
+
"loss": 0.321,
|
| 416 |
+
"step": 520
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.5709969788519638,
|
| 420 |
+
"eval_accuracy": 0.8758169934640523,
|
| 421 |
+
"eval_loss": 0.4749080538749695,
|
| 422 |
+
"eval_runtime": 16.3975,
|
| 423 |
+
"eval_samples_per_second": 9.331,
|
| 424 |
+
"eval_steps_per_second": 2.378,
|
| 425 |
+
"step": 520
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 1.6314199395770392,
|
| 429 |
+
"grad_norm": 0.012226684018969536,
|
| 430 |
+
"learning_rate": 1.3474320241691845e-05,
|
| 431 |
+
"loss": 0.1871,
|
| 432 |
+
"step": 540
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 1.6314199395770392,
|
| 436 |
+
"eval_accuracy": 0.9084967320261438,
|
| 437 |
+
"eval_loss": 0.4391900300979614,
|
| 438 |
+
"eval_runtime": 15.3076,
|
| 439 |
+
"eval_samples_per_second": 9.995,
|
| 440 |
+
"eval_steps_per_second": 2.548,
|
| 441 |
+
"step": 540
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.691842900302115,
|
| 445 |
+
"grad_norm": 0.008862942457199097,
|
| 446 |
+
"learning_rate": 1.3232628398791542e-05,
|
| 447 |
+
"loss": 0.1654,
|
| 448 |
+
"step": 560
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 1.691842900302115,
|
| 452 |
+
"eval_accuracy": 0.9084967320261438,
|
| 453 |
+
"eval_loss": 0.46628066897392273,
|
| 454 |
+
"eval_runtime": 15.645,
|
| 455 |
+
"eval_samples_per_second": 9.779,
|
| 456 |
+
"eval_steps_per_second": 2.493,
|
| 457 |
+
"step": 560
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.7522658610271904,
|
| 461 |
+
"grad_norm": 0.03276165947318077,
|
| 462 |
+
"learning_rate": 1.299093655589124e-05,
|
| 463 |
+
"loss": 0.3166,
|
| 464 |
+
"step": 580
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.7522658610271904,
|
| 468 |
+
"eval_accuracy": 0.8888888888888888,
|
| 469 |
+
"eval_loss": 0.5047788619995117,
|
| 470 |
+
"eval_runtime": 15.5009,
|
| 471 |
+
"eval_samples_per_second": 9.87,
|
| 472 |
+
"eval_steps_per_second": 2.516,
|
| 473 |
+
"step": 580
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 1.8126888217522659,
|
| 477 |
+
"grad_norm": 0.23161815106868744,
|
| 478 |
+
"learning_rate": 1.2749244712990937e-05,
|
| 479 |
+
"loss": 0.222,
|
| 480 |
+
"step": 600
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 1.8126888217522659,
|
| 484 |
+
"eval_accuracy": 0.9084967320261438,
|
| 485 |
+
"eval_loss": 0.4549576938152313,
|
| 486 |
+
"eval_runtime": 15.4555,
|
| 487 |
+
"eval_samples_per_second": 9.899,
|
| 488 |
+
"eval_steps_per_second": 2.523,
|
| 489 |
+
"step": 600
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.8731117824773413,
|
| 493 |
+
"grad_norm": 343.22900390625,
|
| 494 |
+
"learning_rate": 1.2507552870090635e-05,
|
| 495 |
+
"loss": 0.4299,
|
| 496 |
+
"step": 620
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 1.8731117824773413,
|
| 500 |
+
"eval_accuracy": 0.9084967320261438,
|
| 501 |
+
"eval_loss": 0.3444612920284271,
|
| 502 |
+
"eval_runtime": 15.5061,
|
| 503 |
+
"eval_samples_per_second": 9.867,
|
| 504 |
+
"eval_steps_per_second": 2.515,
|
| 505 |
+
"step": 620
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 1.9335347432024168,
|
| 509 |
+
"grad_norm": 0.07708082348108292,
|
| 510 |
+
"learning_rate": 1.2265861027190334e-05,
|
| 511 |
+
"loss": 0.0942,
|
| 512 |
+
"step": 640
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 1.9335347432024168,
|
| 516 |
+
"eval_accuracy": 0.9281045751633987,
|
| 517 |
+
"eval_loss": 0.3734738230705261,
|
| 518 |
+
"eval_runtime": 15.5297,
|
| 519 |
+
"eval_samples_per_second": 9.852,
|
| 520 |
+
"eval_steps_per_second": 2.511,
|
| 521 |
+
"step": 640
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.9939577039274925,
|
| 525 |
+
"grad_norm": 0.010122493840754032,
|
| 526 |
+
"learning_rate": 1.2024169184290032e-05,
|
| 527 |
+
"loss": 0.3991,
|
| 528 |
+
"step": 660
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.9939577039274925,
|
| 532 |
+
"eval_accuracy": 0.9084967320261438,
|
| 533 |
+
"eval_loss": 0.3646344840526581,
|
| 534 |
+
"eval_runtime": 15.4716,
|
| 535 |
+
"eval_samples_per_second": 9.889,
|
| 536 |
+
"eval_steps_per_second": 2.521,
|
| 537 |
+
"step": 660
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 2.054380664652568,
|
| 541 |
+
"grad_norm": 0.750132143497467,
|
| 542 |
+
"learning_rate": 1.178247734138973e-05,
|
| 543 |
+
"loss": 0.0581,
|
| 544 |
+
"step": 680
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 2.054380664652568,
|
| 548 |
+
"eval_accuracy": 0.9084967320261438,
|
| 549 |
+
"eval_loss": 0.3526937961578369,
|
| 550 |
+
"eval_runtime": 15.4654,
|
| 551 |
+
"eval_samples_per_second": 9.893,
|
| 552 |
+
"eval_steps_per_second": 2.522,
|
| 553 |
+
"step": 680
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 2.1148036253776437,
|
| 557 |
+
"grad_norm": 25.176610946655273,
|
| 558 |
+
"learning_rate": 1.1540785498489427e-05,
|
| 559 |
+
"loss": 0.2712,
|
| 560 |
+
"step": 700
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 2.1148036253776437,
|
| 564 |
+
"eval_accuracy": 0.9019607843137255,
|
| 565 |
+
"eval_loss": 0.42697274684906006,
|
| 566 |
+
"eval_runtime": 15.4239,
|
| 567 |
+
"eval_samples_per_second": 9.92,
|
| 568 |
+
"eval_steps_per_second": 2.529,
|
| 569 |
+
"step": 700
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 2.175226586102719,
|
| 573 |
+
"grad_norm": 0.046931881457567215,
|
| 574 |
+
"learning_rate": 1.1299093655589124e-05,
|
| 575 |
+
"loss": 0.0443,
|
| 576 |
+
"step": 720
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 2.175226586102719,
|
| 580 |
+
"eval_accuracy": 0.8954248366013072,
|
| 581 |
+
"eval_loss": 0.5462331771850586,
|
| 582 |
+
"eval_runtime": 15.4688,
|
| 583 |
+
"eval_samples_per_second": 9.891,
|
| 584 |
+
"eval_steps_per_second": 2.521,
|
| 585 |
+
"step": 720
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.2356495468277946,
|
| 589 |
+
"grad_norm": 0.033700473606586456,
|
| 590 |
+
"learning_rate": 1.1057401812688822e-05,
|
| 591 |
+
"loss": 0.3831,
|
| 592 |
+
"step": 740
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 2.2356495468277946,
|
| 596 |
+
"eval_accuracy": 0.9215686274509803,
|
| 597 |
+
"eval_loss": 0.3418585956096649,
|
| 598 |
+
"eval_runtime": 15.5047,
|
| 599 |
+
"eval_samples_per_second": 9.868,
|
| 600 |
+
"eval_steps_per_second": 2.515,
|
| 601 |
+
"step": 740
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 2.29607250755287,
|
| 605 |
+
"grad_norm": 0.046377379447221756,
|
| 606 |
+
"learning_rate": 1.0815709969788521e-05,
|
| 607 |
+
"loss": 0.2267,
|
| 608 |
+
"step": 760
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 2.29607250755287,
|
| 612 |
+
"eval_accuracy": 0.8888888888888888,
|
| 613 |
+
"eval_loss": 0.4924568831920624,
|
| 614 |
+
"eval_runtime": 15.5047,
|
| 615 |
+
"eval_samples_per_second": 9.868,
|
| 616 |
+
"eval_steps_per_second": 2.515,
|
| 617 |
+
"step": 760
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 2.3564954682779455,
|
| 621 |
+
"grad_norm": 9.31714916229248,
|
| 622 |
+
"learning_rate": 1.0574018126888219e-05,
|
| 623 |
+
"loss": 0.1821,
|
| 624 |
+
"step": 780
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 2.3564954682779455,
|
| 628 |
+
"eval_accuracy": 0.9215686274509803,
|
| 629 |
+
"eval_loss": 0.3624768853187561,
|
| 630 |
+
"eval_runtime": 15.502,
|
| 631 |
+
"eval_samples_per_second": 9.87,
|
| 632 |
+
"eval_steps_per_second": 2.516,
|
| 633 |
+
"step": 780
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 2.416918429003021,
|
| 637 |
+
"grad_norm": 112.68130493164062,
|
| 638 |
+
"learning_rate": 1.0332326283987916e-05,
|
| 639 |
+
"loss": 0.2926,
|
| 640 |
+
"step": 800
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 2.416918429003021,
|
| 644 |
+
"eval_accuracy": 0.9019607843137255,
|
| 645 |
+
"eval_loss": 0.3670673370361328,
|
| 646 |
+
"eval_runtime": 15.4876,
|
| 647 |
+
"eval_samples_per_second": 9.879,
|
| 648 |
+
"eval_steps_per_second": 2.518,
|
| 649 |
+
"step": 800
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 2.477341389728097,
|
| 653 |
+
"grad_norm": 0.23612752556800842,
|
| 654 |
+
"learning_rate": 1.0090634441087614e-05,
|
| 655 |
+
"loss": 0.2507,
|
| 656 |
+
"step": 820
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 2.477341389728097,
|
| 660 |
+
"eval_accuracy": 0.9019607843137255,
|
| 661 |
+
"eval_loss": 0.3853074610233307,
|
| 662 |
+
"eval_runtime": 15.494,
|
| 663 |
+
"eval_samples_per_second": 9.875,
|
| 664 |
+
"eval_steps_per_second": 2.517,
|
| 665 |
+
"step": 820
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 2.5377643504531724,
|
| 669 |
+
"grad_norm": 0.00892715621739626,
|
| 670 |
+
"learning_rate": 9.848942598187312e-06,
|
| 671 |
+
"loss": 0.2446,
|
| 672 |
+
"step": 840
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 2.5377643504531724,
|
| 676 |
+
"eval_accuracy": 0.8954248366013072,
|
| 677 |
+
"eval_loss": 0.4570922255516052,
|
| 678 |
+
"eval_runtime": 15.4901,
|
| 679 |
+
"eval_samples_per_second": 9.877,
|
| 680 |
+
"eval_steps_per_second": 2.518,
|
| 681 |
+
"step": 840
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 2.598187311178248,
|
| 685 |
+
"grad_norm": 0.08465878665447235,
|
| 686 |
+
"learning_rate": 9.60725075528701e-06,
|
| 687 |
+
"loss": 0.1926,
|
| 688 |
+
"step": 860
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 2.598187311178248,
|
| 692 |
+
"eval_accuracy": 0.8496732026143791,
|
| 693 |
+
"eval_loss": 0.5435793399810791,
|
| 694 |
+
"eval_runtime": 15.4883,
|
| 695 |
+
"eval_samples_per_second": 9.878,
|
| 696 |
+
"eval_steps_per_second": 2.518,
|
| 697 |
+
"step": 860
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.6586102719033233,
|
| 701 |
+
"grad_norm": 65.41895294189453,
|
| 702 |
+
"learning_rate": 9.365558912386707e-06,
|
| 703 |
+
"loss": 0.1725,
|
| 704 |
+
"step": 880
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.6586102719033233,
|
| 708 |
+
"eval_accuracy": 0.8496732026143791,
|
| 709 |
+
"eval_loss": 0.6575973629951477,
|
| 710 |
+
"eval_runtime": 15.4811,
|
| 711 |
+
"eval_samples_per_second": 9.883,
|
| 712 |
+
"eval_steps_per_second": 2.519,
|
| 713 |
+
"step": 880
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 2.719033232628399,
|
| 717 |
+
"grad_norm": 0.19986489415168762,
|
| 718 |
+
"learning_rate": 9.123867069486404e-06,
|
| 719 |
+
"loss": 0.2033,
|
| 720 |
+
"step": 900
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 2.719033232628399,
|
| 724 |
+
"eval_accuracy": 0.9019607843137255,
|
| 725 |
+
"eval_loss": 0.4772132933139801,
|
| 726 |
+
"eval_runtime": 15.4823,
|
| 727 |
+
"eval_samples_per_second": 9.882,
|
| 728 |
+
"eval_steps_per_second": 2.519,
|
| 729 |
+
"step": 900
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 2.7794561933534743,
|
| 733 |
+
"grad_norm": 0.02453712560236454,
|
| 734 |
+
"learning_rate": 8.882175226586104e-06,
|
| 735 |
+
"loss": 0.0095,
|
| 736 |
+
"step": 920
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 2.7794561933534743,
|
| 740 |
+
"eval_accuracy": 0.9150326797385621,
|
| 741 |
+
"eval_loss": 0.41026702523231506,
|
| 742 |
+
"eval_runtime": 15.4862,
|
| 743 |
+
"eval_samples_per_second": 9.88,
|
| 744 |
+
"eval_steps_per_second": 2.518,
|
| 745 |
+
"step": 920
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 2.8398791540785497,
|
| 749 |
+
"grad_norm": 0.09184593707323074,
|
| 750 |
+
"learning_rate": 8.640483383685801e-06,
|
| 751 |
+
"loss": 0.2896,
|
| 752 |
+
"step": 940
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 2.8398791540785497,
|
| 756 |
+
"eval_accuracy": 0.9084967320261438,
|
| 757 |
+
"eval_loss": 0.4332799017429352,
|
| 758 |
+
"eval_runtime": 15.4949,
|
| 759 |
+
"eval_samples_per_second": 9.874,
|
| 760 |
+
"eval_steps_per_second": 2.517,
|
| 761 |
+
"step": 940
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 2.900302114803625,
|
| 765 |
+
"grad_norm": 88.6507339477539,
|
| 766 |
+
"learning_rate": 8.398791540785499e-06,
|
| 767 |
+
"loss": 0.2661,
|
| 768 |
+
"step": 960
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 2.900302114803625,
|
| 772 |
+
"eval_accuracy": 0.8888888888888888,
|
| 773 |
+
"eval_loss": 0.5792773962020874,
|
| 774 |
+
"eval_runtime": 15.4764,
|
| 775 |
+
"eval_samples_per_second": 9.886,
|
| 776 |
+
"eval_steps_per_second": 2.52,
|
| 777 |
+
"step": 960
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 2.9607250755287007,
|
| 781 |
+
"grad_norm": 0.015309321694076061,
|
| 782 |
+
"learning_rate": 8.157099697885196e-06,
|
| 783 |
+
"loss": 0.1338,
|
| 784 |
+
"step": 980
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 2.9607250755287007,
|
| 788 |
+
"eval_accuracy": 0.8954248366013072,
|
| 789 |
+
"eval_loss": 0.454254150390625,
|
| 790 |
+
"eval_runtime": 15.4888,
|
| 791 |
+
"eval_samples_per_second": 9.878,
|
| 792 |
+
"eval_steps_per_second": 2.518,
|
| 793 |
+
"step": 980
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 3.0211480362537766,
|
| 797 |
+
"grad_norm": 0.06863677501678467,
|
| 798 |
+
"learning_rate": 7.915407854984894e-06,
|
| 799 |
+
"loss": 0.0751,
|
| 800 |
+
"step": 1000
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 3.0211480362537766,
|
| 804 |
+
"eval_accuracy": 0.8954248366013072,
|
| 805 |
+
"eval_loss": 0.5028541684150696,
|
| 806 |
+
"eval_runtime": 15.4598,
|
| 807 |
+
"eval_samples_per_second": 9.897,
|
| 808 |
+
"eval_steps_per_second": 2.523,
|
| 809 |
+
"step": 1000
|
| 810 |
}
|
| 811 |
],
|
| 812 |
"logging_steps": 20,
|
|
|
|
| 826 |
"attributes": {}
|
| 827 |
}
|
| 828 |
},
|
| 829 |
+
"total_flos": 3235818588464112.0,
|
| 830 |
"train_batch_size": 4,
|
| 831 |
"trial_name": null,
|
| 832 |
"trial_params": null
|