Training in progress, step 750, 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 527048968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c47a07760083ef95b3f53a94456e194f58abb165bc35349449ce5f4f1079c8b
|
| 3 |
size 527048968
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1054135994
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19ae14f87ac026dd5d955c968bd5d6ff348e00913a89c8c4e9a70143b8efbc89
|
| 3 |
size 1054135994
|
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 sha256:4ca9142fcbd976a2b9880762578e5776f18d9cad34016a627060f41ab78ec47d
|
| 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:e8974fc0327a603be8a90ee235d3ef81c4ee4af2818c873bdeb9bfb38f108e1a
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.7163676619529724,
|
| 3 |
"best_model_checkpoint": "./output/checkpoint-450",
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 150,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -442,6 +442,296 @@
|
|
| 442 |
"EMA_steps_per_second": 25.426,
|
| 443 |
"epoch": 19.565217391304348,
|
| 444 |
"step": 450
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 445 |
}
|
| 446 |
],
|
| 447 |
"logging_steps": 10,
|
|
@@ -461,7 +751,7 @@
|
|
| 461 |
"attributes": {}
|
| 462 |
}
|
| 463 |
},
|
| 464 |
-
"total_flos": 1.
|
| 465 |
"train_batch_size": 4,
|
| 466 |
"trial_name": null,
|
| 467 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.7163676619529724,
|
| 3 |
"best_model_checkpoint": "./output/checkpoint-450",
|
| 4 |
+
"epoch": 32.608695652173914,
|
| 5 |
"eval_steps": 150,
|
| 6 |
+
"global_step": 750,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 442 |
"EMA_steps_per_second": 25.426,
|
| 443 |
"epoch": 19.565217391304348,
|
| 444 |
"step": 450
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 20.0,
|
| 448 |
+
"grad_norm": 2.1196727752685547,
|
| 449 |
+
"learning_rate": 2.9996147467351856e-05,
|
| 450 |
+
"loss": 0.5146,
|
| 451 |
+
"step": 460
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 20.434782608695652,
|
| 455 |
+
"grad_norm": 1.276078701019287,
|
| 456 |
+
"learning_rate": 2.9995930474939773e-05,
|
| 457 |
+
"loss": 0.478,
|
| 458 |
+
"step": 470
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 20.869565217391305,
|
| 462 |
+
"grad_norm": 1.4759645462036133,
|
| 463 |
+
"learning_rate": 2.9995707538619975e-05,
|
| 464 |
+
"loss": 0.5704,
|
| 465 |
+
"step": 480
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 21.304347826086957,
|
| 469 |
+
"grad_norm": 1.3196395635604858,
|
| 470 |
+
"learning_rate": 2.9995478658480822e-05,
|
| 471 |
+
"loss": 0.5164,
|
| 472 |
+
"step": 490
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 21.73913043478261,
|
| 476 |
+
"grad_norm": 1.243372917175293,
|
| 477 |
+
"learning_rate": 2.9995243834613043e-05,
|
| 478 |
+
"loss": 0.5207,
|
| 479 |
+
"step": 500
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 22.17391304347826,
|
| 483 |
+
"grad_norm": 1.785915493965149,
|
| 484 |
+
"learning_rate": 2.9995003067109707e-05,
|
| 485 |
+
"loss": 0.4835,
|
| 486 |
+
"step": 510
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 22.608695652173914,
|
| 490 |
+
"grad_norm": 1.534149169921875,
|
| 491 |
+
"learning_rate": 2.9994756356066246e-05,
|
| 492 |
+
"loss": 0.5615,
|
| 493 |
+
"step": 520
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 23.043478260869566,
|
| 497 |
+
"grad_norm": 1.7393022775650024,
|
| 498 |
+
"learning_rate": 2.999450370158046e-05,
|
| 499 |
+
"loss": 0.4926,
|
| 500 |
+
"step": 530
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 23.47826086956522,
|
| 504 |
+
"grad_norm": 1.3098986148834229,
|
| 505 |
+
"learning_rate": 2.9994245103752478e-05,
|
| 506 |
+
"loss": 0.4386,
|
| 507 |
+
"step": 540
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 23.91304347826087,
|
| 511 |
+
"grad_norm": 1.2317270040512085,
|
| 512 |
+
"learning_rate": 2.999398056268481e-05,
|
| 513 |
+
"loss": 0.5265,
|
| 514 |
+
"step": 550
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 24.347826086956523,
|
| 518 |
+
"grad_norm": 1.4070038795471191,
|
| 519 |
+
"learning_rate": 2.9993710078482306e-05,
|
| 520 |
+
"loss": 0.5206,
|
| 521 |
+
"step": 560
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 24.782608695652176,
|
| 525 |
+
"grad_norm": 0.9481082558631897,
|
| 526 |
+
"learning_rate": 2.9993433651252185e-05,
|
| 527 |
+
"loss": 0.443,
|
| 528 |
+
"step": 570
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 25.217391304347824,
|
| 532 |
+
"grad_norm": 1.7193400859832764,
|
| 533 |
+
"learning_rate": 2.9993151281104006e-05,
|
| 534 |
+
"loss": 0.5326,
|
| 535 |
+
"step": 580
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 25.652173913043477,
|
| 539 |
+
"grad_norm": 1.1353116035461426,
|
| 540 |
+
"learning_rate": 2.9992862968149695e-05,
|
| 541 |
+
"loss": 0.4736,
|
| 542 |
+
"step": 590
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 26.08695652173913,
|
| 546 |
+
"grad_norm": 1.1752177476882935,
|
| 547 |
+
"learning_rate": 2.9992568712503533e-05,
|
| 548 |
+
"loss": 0.4607,
|
| 549 |
+
"step": 600
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 26.08695652173913,
|
| 553 |
+
"eval_loss": 0.7202690839767456,
|
| 554 |
+
"eval_runtime": 0.486,
|
| 555 |
+
"eval_samples_per_second": 20.576,
|
| 556 |
+
"eval_steps_per_second": 20.576,
|
| 557 |
+
"step": 600
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"Start_State_loss": 0.8603047132492065,
|
| 561 |
+
"Start_State_runtime": 0.5367,
|
| 562 |
+
"Start_State_samples_per_second": 18.634,
|
| 563 |
+
"Start_State_steps_per_second": 18.634,
|
| 564 |
+
"epoch": 26.08695652173913,
|
| 565 |
+
"step": 600
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"Raw_Model_loss": 0.7202690839767456,
|
| 569 |
+
"Raw_Model_runtime": 0.5363,
|
| 570 |
+
"Raw_Model_samples_per_second": 18.647,
|
| 571 |
+
"Raw_Model_steps_per_second": 18.647,
|
| 572 |
+
"epoch": 26.08695652173913,
|
| 573 |
+
"step": 600
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"SWA_loss": 0.7349081635475159,
|
| 577 |
+
"SWA_runtime": 0.5181,
|
| 578 |
+
"SWA_samples_per_second": 19.302,
|
| 579 |
+
"SWA_steps_per_second": 19.302,
|
| 580 |
+
"epoch": 26.08695652173913,
|
| 581 |
+
"step": 600
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"EMA_loss": 0.8603397607803345,
|
| 585 |
+
"EMA_runtime": 0.5673,
|
| 586 |
+
"EMA_samples_per_second": 17.628,
|
| 587 |
+
"EMA_steps_per_second": 17.628,
|
| 588 |
+
"epoch": 26.08695652173913,
|
| 589 |
+
"step": 600
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 26.52173913043478,
|
| 593 |
+
"grad_norm": 1.0985554456710815,
|
| 594 |
+
"learning_rate": 2.9992268514282142e-05,
|
| 595 |
+
"loss": 0.5119,
|
| 596 |
+
"step": 610
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 26.956521739130434,
|
| 600 |
+
"grad_norm": 1.3385064601898193,
|
| 601 |
+
"learning_rate": 2.999196237360452e-05,
|
| 602 |
+
"loss": 0.4318,
|
| 603 |
+
"step": 620
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 27.391304347826086,
|
| 607 |
+
"grad_norm": 1.2069611549377441,
|
| 608 |
+
"learning_rate": 2.9991650290592016e-05,
|
| 609 |
+
"loss": 0.4757,
|
| 610 |
+
"step": 630
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 27.82608695652174,
|
| 614 |
+
"grad_norm": 1.3943425416946411,
|
| 615 |
+
"learning_rate": 2.999133226536832e-05,
|
| 616 |
+
"loss": 0.5012,
|
| 617 |
+
"step": 640
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 28.26086956521739,
|
| 621 |
+
"grad_norm": 1.4118835926055908,
|
| 622 |
+
"learning_rate": 2.9991008298059493e-05,
|
| 623 |
+
"loss": 0.4107,
|
| 624 |
+
"step": 650
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 28.695652173913043,
|
| 628 |
+
"grad_norm": 1.5642292499542236,
|
| 629 |
+
"learning_rate": 2.9990678388793944e-05,
|
| 630 |
+
"loss": 0.5065,
|
| 631 |
+
"step": 660
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 29.130434782608695,
|
| 635 |
+
"grad_norm": 1.3201287984848022,
|
| 636 |
+
"learning_rate": 2.999034253770244e-05,
|
| 637 |
+
"loss": 0.4348,
|
| 638 |
+
"step": 670
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 29.565217391304348,
|
| 642 |
+
"grad_norm": 1.0674601793289185,
|
| 643 |
+
"learning_rate": 2.9990000744918097e-05,
|
| 644 |
+
"loss": 0.4704,
|
| 645 |
+
"step": 680
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 30.0,
|
| 649 |
+
"grad_norm": 2.4941728115081787,
|
| 650 |
+
"learning_rate": 2.9989653010576392e-05,
|
| 651 |
+
"loss": 0.414,
|
| 652 |
+
"step": 690
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 30.434782608695652,
|
| 656 |
+
"grad_norm": 1.3316413164138794,
|
| 657 |
+
"learning_rate": 2.9989299334815158e-05,
|
| 658 |
+
"loss": 0.4764,
|
| 659 |
+
"step": 700
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 30.869565217391305,
|
| 663 |
+
"grad_norm": 1.630299687385559,
|
| 664 |
+
"learning_rate": 2.9988939717774578e-05,
|
| 665 |
+
"loss": 0.4125,
|
| 666 |
+
"step": 710
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 31.304347826086957,
|
| 670 |
+
"grad_norm": 0.9058042168617249,
|
| 671 |
+
"learning_rate": 2.9988574159597194e-05,
|
| 672 |
+
"loss": 0.4246,
|
| 673 |
+
"step": 720
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 31.73913043478261,
|
| 677 |
+
"grad_norm": 1.6431688070297241,
|
| 678 |
+
"learning_rate": 2.9988202660427907e-05,
|
| 679 |
+
"loss": 0.4826,
|
| 680 |
+
"step": 730
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 32.17391304347826,
|
| 684 |
+
"grad_norm": 1.2037235498428345,
|
| 685 |
+
"learning_rate": 2.9987825220413958e-05,
|
| 686 |
+
"loss": 0.4386,
|
| 687 |
+
"step": 740
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 32.608695652173914,
|
| 691 |
+
"grad_norm": 1.7607014179229736,
|
| 692 |
+
"learning_rate": 2.998744183970496e-05,
|
| 693 |
+
"loss": 0.4732,
|
| 694 |
+
"step": 750
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 32.608695652173914,
|
| 698 |
+
"eval_loss": 0.730880856513977,
|
| 699 |
+
"eval_runtime": 0.4095,
|
| 700 |
+
"eval_samples_per_second": 24.421,
|
| 701 |
+
"eval_steps_per_second": 24.421,
|
| 702 |
+
"step": 750
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"Start_State_loss": 0.8603047132492065,
|
| 706 |
+
"Start_State_runtime": 0.3936,
|
| 707 |
+
"Start_State_samples_per_second": 25.405,
|
| 708 |
+
"Start_State_steps_per_second": 25.405,
|
| 709 |
+
"epoch": 32.608695652173914,
|
| 710 |
+
"step": 750
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"Raw_Model_loss": 0.730880856513977,
|
| 714 |
+
"Raw_Model_runtime": 0.3905,
|
| 715 |
+
"Raw_Model_samples_per_second": 25.607,
|
| 716 |
+
"Raw_Model_steps_per_second": 25.607,
|
| 717 |
+
"epoch": 32.608695652173914,
|
| 718 |
+
"step": 750
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"SWA_loss": 0.7291876077651978,
|
| 722 |
+
"SWA_runtime": 0.4034,
|
| 723 |
+
"SWA_samples_per_second": 24.789,
|
| 724 |
+
"SWA_steps_per_second": 24.789,
|
| 725 |
+
"epoch": 32.608695652173914,
|
| 726 |
+
"step": 750
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"EMA_loss": 0.8608433604240417,
|
| 730 |
+
"EMA_runtime": 0.4119,
|
| 731 |
+
"EMA_samples_per_second": 24.278,
|
| 732 |
+
"EMA_steps_per_second": 24.278,
|
| 733 |
+
"epoch": 32.608695652173914,
|
| 734 |
+
"step": 750
|
| 735 |
}
|
| 736 |
],
|
| 737 |
"logging_steps": 10,
|
|
|
|
| 751 |
"attributes": {}
|
| 752 |
}
|
| 753 |
},
|
| 754 |
+
"total_flos": 1.9231766387195904e+16,
|
| 755 |
"train_batch_size": 4,
|
| 756 |
"trial_name": null,
|
| 757 |
"trial_params": null
|