Training in progress, step 152, 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 200068512
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a47bdc1f52e9687f1b2065118ba5ed67f0e7ddf452b628d16653fe52dd7f3c5a
|
| 3 |
size 200068512
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 400361770
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3c67139bafbd6e7779c67dd433ab463e343894e27d0d229c7eb363ec450984e
|
| 3 |
size 400361770
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14512
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:502476aa04a593c704ac84967b6f43b1590a9e6c3672e589c240c6f9d4b929a7
|
| 3 |
size 14512
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14512
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71dbabef39979f13d0c4a4aefe6ca255e0c18d780788adac8fb329d89525cd7a
|
| 3 |
size 14512
|
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 sha256:8a18cea3621f9dc2789cea415c39b96c4e45945922514433b7b11735bf5d8256
|
| 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": 76,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -555,6 +555,546 @@
|
|
| 555 |
"eval_samples_per_second": 3.664,
|
| 556 |
"eval_steps_per_second": 0.916,
|
| 557 |
"step": 76
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 558 |
}
|
| 559 |
],
|
| 560 |
"logging_steps": 1,
|
|
@@ -574,7 +1114,7 @@
|
|
| 574 |
"attributes": {}
|
| 575 |
}
|
| 576 |
},
|
| 577 |
-
"total_flos":
|
| 578 |
"train_batch_size": 2,
|
| 579 |
"trial_name": null,
|
| 580 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.09924910218739798,
|
| 5 |
"eval_steps": 76,
|
| 6 |
+
"global_step": 152,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 555 |
"eval_samples_per_second": 3.664,
|
| 556 |
"eval_steps_per_second": 0.916,
|
| 557 |
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.05027750571335292,
|
| 561 |
+
"grad_norm": 3.9176759719848633,
|
| 562 |
+
"learning_rate": 0.0001944321908543708,
|
| 563 |
+
"loss": 1.9556,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.050930460333006855,
|
| 568 |
+
"grad_norm": 3.578507423400879,
|
| 569 |
+
"learning_rate": 0.00019401636137990816,
|
| 570 |
+
"loss": 2.025,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.05158341495266079,
|
| 575 |
+
"grad_norm": 3.641873598098755,
|
| 576 |
+
"learning_rate": 0.00019358603562568416,
|
| 577 |
+
"loss": 1.667,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.05223636957231472,
|
| 582 |
+
"grad_norm": 4.218084335327148,
|
| 583 |
+
"learning_rate": 0.0001931412799431554,
|
| 584 |
+
"loss": 1.797,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.05288932419196866,
|
| 589 |
+
"grad_norm": 3.496741533279419,
|
| 590 |
+
"learning_rate": 0.0001926821629087133,
|
| 591 |
+
"loss": 1.5076,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.053542278811622594,
|
| 596 |
+
"grad_norm": 5.606319427490234,
|
| 597 |
+
"learning_rate": 0.00019220875531311045,
|
| 598 |
+
"loss": 1.5796,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.054195233431276524,
|
| 603 |
+
"grad_norm": 3.143007516860962,
|
| 604 |
+
"learning_rate": 0.00019172113015054532,
|
| 605 |
+
"loss": 1.4222,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.05484818805093046,
|
| 610 |
+
"grad_norm": 3.359457015991211,
|
| 611 |
+
"learning_rate": 0.00019121936260740752,
|
| 612 |
+
"loss": 0.9389,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.0555011426705844,
|
| 617 |
+
"grad_norm": 3.911376476287842,
|
| 618 |
+
"learning_rate": 0.00019070353005068484,
|
| 619 |
+
"loss": 1.8963,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.056154097290238326,
|
| 624 |
+
"grad_norm": 3.542954444885254,
|
| 625 |
+
"learning_rate": 0.00019017371201603407,
|
| 626 |
+
"loss": 1.4677,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.05680705190989226,
|
| 631 |
+
"grad_norm": 3.1694722175598145,
|
| 632 |
+
"learning_rate": 0.00018962999019551754,
|
| 633 |
+
"loss": 1.4803,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.0574600065295462,
|
| 638 |
+
"grad_norm": 2.960282564163208,
|
| 639 |
+
"learning_rate": 0.00018907244842500704,
|
| 640 |
+
"loss": 1.8923,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.05811296114920013,
|
| 645 |
+
"grad_norm": 2.6101479530334473,
|
| 646 |
+
"learning_rate": 0.00018850117267125738,
|
| 647 |
+
"loss": 1.9243,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.058765915768854066,
|
| 652 |
+
"grad_norm": 3.0619993209838867,
|
| 653 |
+
"learning_rate": 0.00018791625101865117,
|
| 654 |
+
"loss": 2.1384,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.059418870388507995,
|
| 659 |
+
"grad_norm": 2.6776371002197266,
|
| 660 |
+
"learning_rate": 0.0001873177736556172,
|
| 661 |
+
"loss": 1.7285,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.06007182500816193,
|
| 666 |
+
"grad_norm": 3.687798023223877,
|
| 667 |
+
"learning_rate": 0.00018670583286072443,
|
| 668 |
+
"loss": 1.8332,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.06072477962781587,
|
| 673 |
+
"grad_norm": 2.632847547531128,
|
| 674 |
+
"learning_rate": 0.0001860805229884536,
|
| 675 |
+
"loss": 1.8342,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.0613777342474698,
|
| 680 |
+
"grad_norm": 3.5173568725585938,
|
| 681 |
+
"learning_rate": 0.00018544194045464886,
|
| 682 |
+
"loss": 2.004,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.062030688867123734,
|
| 687 |
+
"grad_norm": 3.2944045066833496,
|
| 688 |
+
"learning_rate": 0.0001847901837216515,
|
| 689 |
+
"loss": 1.8861,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.06268364348677767,
|
| 694 |
+
"grad_norm": 3.5300235748291016,
|
| 695 |
+
"learning_rate": 0.00018412535328311814,
|
| 696 |
+
"loss": 1.7608,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.06333659810643161,
|
| 701 |
+
"grad_norm": 3.253826856613159,
|
| 702 |
+
"learning_rate": 0.0001834475516485257,
|
| 703 |
+
"loss": 1.9151,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.06398955272608553,
|
| 708 |
+
"grad_norm": 3.243023633956909,
|
| 709 |
+
"learning_rate": 0.00018275688332736577,
|
| 710 |
+
"loss": 1.5671,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.06464250734573947,
|
| 715 |
+
"grad_norm": 3.3818089962005615,
|
| 716 |
+
"learning_rate": 0.00018205345481302998,
|
| 717 |
+
"loss": 1.4077,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.0652954619653934,
|
| 722 |
+
"grad_norm": 3.632511615753174,
|
| 723 |
+
"learning_rate": 0.00018133737456639044,
|
| 724 |
+
"loss": 1.0454,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.06594841658504734,
|
| 729 |
+
"grad_norm": 3.6621978282928467,
|
| 730 |
+
"learning_rate": 0.0001806087529990758,
|
| 731 |
+
"loss": 2.0844,
|
| 732 |
+
"step": 101
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.06660137120470128,
|
| 736 |
+
"grad_norm": 5.99480676651001,
|
| 737 |
+
"learning_rate": 0.0001798677024564473,
|
| 738 |
+
"loss": 1.8015,
|
| 739 |
+
"step": 102
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 0.06725432582435521,
|
| 743 |
+
"grad_norm": 3.063887357711792,
|
| 744 |
+
"learning_rate": 0.00017911433720027624,
|
| 745 |
+
"loss": 1.7182,
|
| 746 |
+
"step": 103
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.06790728044400914,
|
| 750 |
+
"grad_norm": 3.2303333282470703,
|
| 751 |
+
"learning_rate": 0.00017834877339112612,
|
| 752 |
+
"loss": 1.6701,
|
| 753 |
+
"step": 104
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.06856023506366307,
|
| 757 |
+
"grad_norm": 7.370791435241699,
|
| 758 |
+
"learning_rate": 0.000177571129070442,
|
| 759 |
+
"loss": 1.6819,
|
| 760 |
+
"step": 105
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 0.06921318968331701,
|
| 764 |
+
"grad_norm": 3.4059948921203613,
|
| 765 |
+
"learning_rate": 0.00017678152414234968,
|
| 766 |
+
"loss": 1.3683,
|
| 767 |
+
"step": 106
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.06986614430297095,
|
| 771 |
+
"grad_norm": 4.130568504333496,
|
| 772 |
+
"learning_rate": 0.000175980080355168,
|
| 773 |
+
"loss": 1.6074,
|
| 774 |
+
"step": 107
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.07051909892262488,
|
| 778 |
+
"grad_norm": 4.288647651672363,
|
| 779 |
+
"learning_rate": 0.00017516692128263648,
|
| 780 |
+
"loss": 1.2521,
|
| 781 |
+
"step": 108
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 0.07117205354227882,
|
| 785 |
+
"grad_norm": 3.245211362838745,
|
| 786 |
+
"learning_rate": 0.00017434217230486164,
|
| 787 |
+
"loss": 1.3333,
|
| 788 |
+
"step": 109
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.07182500816193274,
|
| 792 |
+
"grad_norm": 3.7068018913269043,
|
| 793 |
+
"learning_rate": 0.00017350596058898483,
|
| 794 |
+
"loss": 1.287,
|
| 795 |
+
"step": 110
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.07247796278158668,
|
| 799 |
+
"grad_norm": 3.418928623199463,
|
| 800 |
+
"learning_rate": 0.0001726584150695744,
|
| 801 |
+
"loss": 1.3896,
|
| 802 |
+
"step": 111
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 0.07313091740124061,
|
| 806 |
+
"grad_norm": 3.3947291374206543,
|
| 807 |
+
"learning_rate": 0.00017179966642874543,
|
| 808 |
+
"loss": 1.7948,
|
| 809 |
+
"step": 112
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.07378387202089455,
|
| 813 |
+
"grad_norm": 2.770167589187622,
|
| 814 |
+
"learning_rate": 0.0001709298470760101,
|
| 815 |
+
"loss": 1.8008,
|
| 816 |
+
"step": 113
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 0.07443682664054849,
|
| 820 |
+
"grad_norm": 2.841723918914795,
|
| 821 |
+
"learning_rate": 0.00017004909112786144,
|
| 822 |
+
"loss": 1.7773,
|
| 823 |
+
"step": 114
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 0.07508978126020241,
|
| 827 |
+
"grad_norm": 3.010446071624756,
|
| 828 |
+
"learning_rate": 0.00016915753438709417,
|
| 829 |
+
"loss": 1.9485,
|
| 830 |
+
"step": 115
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.07574273587985635,
|
| 834 |
+
"grad_norm": 2.804893970489502,
|
| 835 |
+
"learning_rate": 0.00016825531432186543,
|
| 836 |
+
"loss": 1.8283,
|
| 837 |
+
"step": 116
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.07639569049951028,
|
| 841 |
+
"grad_norm": 2.607825517654419,
|
| 842 |
+
"learning_rate": 0.00016734257004449862,
|
| 843 |
+
"loss": 1.5881,
|
| 844 |
+
"step": 117
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 0.07704864511916422,
|
| 848 |
+
"grad_norm": 3.1926357746124268,
|
| 849 |
+
"learning_rate": 0.00016641944229003395,
|
| 850 |
+
"loss": 1.9909,
|
| 851 |
+
"step": 118
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 0.07770159973881816,
|
| 855 |
+
"grad_norm": 2.6762239933013916,
|
| 856 |
+
"learning_rate": 0.00016548607339452853,
|
| 857 |
+
"loss": 1.7493,
|
| 858 |
+
"step": 119
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.07835455435847209,
|
| 862 |
+
"grad_norm": 2.9282002449035645,
|
| 863 |
+
"learning_rate": 0.00016454260727310978,
|
| 864 |
+
"loss": 1.6987,
|
| 865 |
+
"step": 120
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 0.07900750897812601,
|
| 869 |
+
"grad_norm": 3.6605136394500732,
|
| 870 |
+
"learning_rate": 0.00016358918939778536,
|
| 871 |
+
"loss": 2.1916,
|
| 872 |
+
"step": 121
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 0.07966046359777995,
|
| 876 |
+
"grad_norm": 3.031012535095215,
|
| 877 |
+
"learning_rate": 0.00016262596677501297,
|
| 878 |
+
"loss": 1.9056,
|
| 879 |
+
"step": 122
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.08031341821743389,
|
| 883 |
+
"grad_norm": 3.2578601837158203,
|
| 884 |
+
"learning_rate": 0.0001616530879230335,
|
| 885 |
+
"loss": 1.5707,
|
| 886 |
+
"step": 123
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 0.08096637283708782,
|
| 890 |
+
"grad_norm": 3.2448766231536865,
|
| 891 |
+
"learning_rate": 0.00016067070284897137,
|
| 892 |
+
"loss": 1.43,
|
| 893 |
+
"step": 124
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 0.08161932745674176,
|
| 897 |
+
"grad_norm": 3.2631771564483643,
|
| 898 |
+
"learning_rate": 0.00015967896302570485,
|
| 899 |
+
"loss": 1.0851,
|
| 900 |
+
"step": 125
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 0.08227228207639568,
|
| 904 |
+
"grad_norm": 3.316664457321167,
|
| 905 |
+
"learning_rate": 0.0001586780213685108,
|
| 906 |
+
"loss": 1.9519,
|
| 907 |
+
"step": 126
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 0.08292523669604962,
|
| 911 |
+
"grad_norm": 2.7955403327941895,
|
| 912 |
+
"learning_rate": 0.00015766803221148673,
|
| 913 |
+
"loss": 1.6003,
|
| 914 |
+
"step": 127
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 0.08357819131570356,
|
| 918 |
+
"grad_norm": 3.2884178161621094,
|
| 919 |
+
"learning_rate": 0.0001566491512837543,
|
| 920 |
+
"loss": 1.7108,
|
| 921 |
+
"step": 128
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.0842311459353575,
|
| 925 |
+
"grad_norm": 3.472278356552124,
|
| 926 |
+
"learning_rate": 0.00015562153568544752,
|
| 927 |
+
"loss": 1.8399,
|
| 928 |
+
"step": 129
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 0.08488410055501143,
|
| 932 |
+
"grad_norm": 2.900644302368164,
|
| 933 |
+
"learning_rate": 0.00015458534386348966,
|
| 934 |
+
"loss": 1.6259,
|
| 935 |
+
"step": 130
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 0.08553705517466537,
|
| 939 |
+
"grad_norm": 3.018883228302002,
|
| 940 |
+
"learning_rate": 0.0001535407355871626,
|
| 941 |
+
"loss": 1.5246,
|
| 942 |
+
"step": 131
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 0.08619000979431929,
|
| 946 |
+
"grad_norm": 3.375364303588867,
|
| 947 |
+
"learning_rate": 0.00015248787192347196,
|
| 948 |
+
"loss": 1.6209,
|
| 949 |
+
"step": 132
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 0.08684296441397323,
|
| 953 |
+
"grad_norm": 2.9012420177459717,
|
| 954 |
+
"learning_rate": 0.00015142691521231267,
|
| 955 |
+
"loss": 1.2602,
|
| 956 |
+
"step": 133
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 0.08749591903362716,
|
| 960 |
+
"grad_norm": 4.421230316162109,
|
| 961 |
+
"learning_rate": 0.00015035802904143762,
|
| 962 |
+
"loss": 1.5445,
|
| 963 |
+
"step": 134
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.0881488736532811,
|
| 967 |
+
"grad_norm": 3.3842790126800537,
|
| 968 |
+
"learning_rate": 0.00014928137822123452,
|
| 969 |
+
"loss": 1.2163,
|
| 970 |
+
"step": 135
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 0.08880182827293504,
|
| 974 |
+
"grad_norm": 3.1379024982452393,
|
| 975 |
+
"learning_rate": 0.0001481971287593138,
|
| 976 |
+
"loss": 1.6229,
|
| 977 |
+
"step": 136
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 0.08945478289258897,
|
| 981 |
+
"grad_norm": 3.0401148796081543,
|
| 982 |
+
"learning_rate": 0.00014710544783491208,
|
| 983 |
+
"loss": 2.1325,
|
| 984 |
+
"step": 137
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 0.0901077375122429,
|
| 988 |
+
"grad_norm": 3.1100378036499023,
|
| 989 |
+
"learning_rate": 0.00014600650377311522,
|
| 990 |
+
"loss": 1.8436,
|
| 991 |
+
"step": 138
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 0.09076069213189683,
|
| 995 |
+
"grad_norm": 2.646742105484009,
|
| 996 |
+
"learning_rate": 0.00014490046601890405,
|
| 997 |
+
"loss": 2.0225,
|
| 998 |
+
"step": 139
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 0.09141364675155077,
|
| 1002 |
+
"grad_norm": 2.7213666439056396,
|
| 1003 |
+
"learning_rate": 0.00014378750511102826,
|
| 1004 |
+
"loss": 1.9278,
|
| 1005 |
+
"step": 140
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.0920666013712047,
|
| 1009 |
+
"grad_norm": 2.6186165809631348,
|
| 1010 |
+
"learning_rate": 0.00014266779265571087,
|
| 1011 |
+
"loss": 2.1003,
|
| 1012 |
+
"step": 141
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 0.09271955599085864,
|
| 1016 |
+
"grad_norm": 2.469266653060913,
|
| 1017 |
+
"learning_rate": 0.00014154150130018866,
|
| 1018 |
+
"loss": 2.1259,
|
| 1019 |
+
"step": 142
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 0.09337251061051256,
|
| 1023 |
+
"grad_norm": 2.95566725730896,
|
| 1024 |
+
"learning_rate": 0.00014040880470609187,
|
| 1025 |
+
"loss": 2.0982,
|
| 1026 |
+
"step": 143
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 0.0940254652301665,
|
| 1030 |
+
"grad_norm": 3.408046007156372,
|
| 1031 |
+
"learning_rate": 0.00013926987752266735,
|
| 1032 |
+
"loss": 2.1553,
|
| 1033 |
+
"step": 144
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 0.09467841984982044,
|
| 1037 |
+
"grad_norm": 2.5797595977783203,
|
| 1038 |
+
"learning_rate": 0.00013812489535984981,
|
| 1039 |
+
"loss": 1.9652,
|
| 1040 |
+
"step": 145
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 0.09533137446947437,
|
| 1044 |
+
"grad_norm": 3.9302403926849365,
|
| 1045 |
+
"learning_rate": 0.00013697403476118454,
|
| 1046 |
+
"loss": 1.916,
|
| 1047 |
+
"step": 146
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 0.09598432908912831,
|
| 1051 |
+
"grad_norm": 3.0103251934051514,
|
| 1052 |
+
"learning_rate": 0.0001358174731766064,
|
| 1053 |
+
"loss": 1.5778,
|
| 1054 |
+
"step": 147
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 0.09663728370878225,
|
| 1058 |
+
"grad_norm": 3.0252418518066406,
|
| 1059 |
+
"learning_rate": 0.00013465538893507907,
|
| 1060 |
+
"loss": 1.862,
|
| 1061 |
+
"step": 148
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 0.09729023832843617,
|
| 1065 |
+
"grad_norm": 3.1504366397857666,
|
| 1066 |
+
"learning_rate": 0.00013348796121709862,
|
| 1067 |
+
"loss": 1.7159,
|
| 1068 |
+
"step": 149
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 0.0979431929480901,
|
| 1072 |
+
"grad_norm": 2.718940019607544,
|
| 1073 |
+
"learning_rate": 0.00013231537002706594,
|
| 1074 |
+
"loss": 1.1477,
|
| 1075 |
+
"step": 150
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 0.09859614756774404,
|
| 1079 |
+
"grad_norm": 3.6509456634521484,
|
| 1080 |
+
"learning_rate": 0.0001311377961655319,
|
| 1081 |
+
"loss": 1.6706,
|
| 1082 |
+
"step": 151
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 0.09924910218739798,
|
| 1086 |
+
"grad_norm": 3.2815134525299072,
|
| 1087 |
+
"learning_rate": 0.00012995542120132017,
|
| 1088 |
+
"loss": 1.4804,
|
| 1089 |
+
"step": 152
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.09924910218739798,
|
| 1093 |
+
"eval_loss": NaN,
|
| 1094 |
+
"eval_runtime": 699.3675,
|
| 1095 |
+
"eval_samples_per_second": 3.689,
|
| 1096 |
+
"eval_steps_per_second": 0.922,
|
| 1097 |
+
"step": 152
|
| 1098 |
}
|
| 1099 |
],
|
| 1100 |
"logging_steps": 1,
|
|
|
|
| 1114 |
"attributes": {}
|
| 1115 |
}
|
| 1116 |
},
|
| 1117 |
+
"total_flos": 4.662717514168402e+17,
|
| 1118 |
"train_batch_size": 2,
|
| 1119 |
"trial_name": null,
|
| 1120 |
"trial_params": null
|