Training in progress, epoch 3
Browse files- last-checkpoint/optimizer.pt +2 -2
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +288 -3
- pytorch_model.bin +1 -1
- runs/Feb20_18-29-06_ubuntu-2004/events.out.tfevents.1676885357.ubuntu-2004.887393.0 +2 -2
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ad3d537ea4fd7d6ad4fa6cf73b1b40dd110b483d065f2705e6949affdc6cf17
|
| 3 |
+
size 236491269
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 118253458
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2906e434c2be5553d8ba690fa00f38995006c684a8b4fbef8476c7418f239877
|
| 3 |
size 118253458
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15597
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fddd988ead107be498ca0838e5d6931249bb674b40ce6296875748270d271cc4
|
| 3 |
size 15597
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 557
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45ac1a1a1f98b3964d76c33e861170daff6e880017ea91dcfeb6f1af152554e5
|
| 3 |
size 557
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29cf36739c6a6691ce7e0e701bc722960d20ddd1e069bdfc942253c223daa611
|
| 3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -570,11 +570,296 @@
|
|
| 570 |
"eval_samples_per_second": 604.475,
|
| 571 |
"eval_steps_per_second": 37.78,
|
| 572 |
"step": 45880
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 573 |
}
|
| 574 |
],
|
| 575 |
"max_steps": 321160,
|
| 576 |
"num_train_epochs": 14,
|
| 577 |
-
"total_flos":
|
| 578 |
"trial_name": null,
|
| 579 |
"trial_params": null
|
| 580 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 68820,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 570 |
"eval_samples_per_second": 604.475,
|
| 571 |
"eval_steps_per_second": 37.78,
|
| 572 |
"step": 45880
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 2.01,
|
| 576 |
+
"learning_rate": 8.654780026922643e-05,
|
| 577 |
+
"loss": 1.9157,
|
| 578 |
+
"step": 46000
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.03,
|
| 582 |
+
"learning_rate": 8.639054184961062e-05,
|
| 583 |
+
"loss": 1.9106,
|
| 584 |
+
"step": 46500
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 2.05,
|
| 588 |
+
"learning_rate": 8.623328342999485e-05,
|
| 589 |
+
"loss": 1.9071,
|
| 590 |
+
"step": 47000
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 2.07,
|
| 594 |
+
"learning_rate": 8.607602501037906e-05,
|
| 595 |
+
"loss": 1.9029,
|
| 596 |
+
"step": 47500
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 2.09,
|
| 600 |
+
"learning_rate": 8.59190811076025e-05,
|
| 601 |
+
"loss": 1.9037,
|
| 602 |
+
"step": 48000
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 2.11,
|
| 606 |
+
"learning_rate": 8.576182268798671e-05,
|
| 607 |
+
"loss": 1.9035,
|
| 608 |
+
"step": 48500
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 2.14,
|
| 612 |
+
"learning_rate": 8.560456426837094e-05,
|
| 613 |
+
"loss": 1.8995,
|
| 614 |
+
"step": 49000
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 2.16,
|
| 618 |
+
"learning_rate": 8.544730584875515e-05,
|
| 619 |
+
"loss": 1.8955,
|
| 620 |
+
"step": 49500
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.18,
|
| 624 |
+
"learning_rate": 8.529036194597859e-05,
|
| 625 |
+
"loss": 1.894,
|
| 626 |
+
"step": 50000
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 2.2,
|
| 630 |
+
"learning_rate": 8.51331035263628e-05,
|
| 631 |
+
"loss": 1.8871,
|
| 632 |
+
"step": 50500
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 2.22,
|
| 636 |
+
"learning_rate": 8.497584510674703e-05,
|
| 637 |
+
"loss": 1.8897,
|
| 638 |
+
"step": 51000
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 2.24,
|
| 642 |
+
"learning_rate": 8.481858668713124e-05,
|
| 643 |
+
"loss": 1.888,
|
| 644 |
+
"step": 51500
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 2.27,
|
| 648 |
+
"learning_rate": 8.466164278435468e-05,
|
| 649 |
+
"loss": 1.8866,
|
| 650 |
+
"step": 52000
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 2.29,
|
| 654 |
+
"learning_rate": 8.450438436473889e-05,
|
| 655 |
+
"loss": 1.8829,
|
| 656 |
+
"step": 52500
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 2.31,
|
| 660 |
+
"learning_rate": 8.43471259451231e-05,
|
| 661 |
+
"loss": 1.8787,
|
| 662 |
+
"step": 53000
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.33,
|
| 666 |
+
"learning_rate": 8.418986752550731e-05,
|
| 667 |
+
"loss": 1.8743,
|
| 668 |
+
"step": 53500
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 2.35,
|
| 672 |
+
"learning_rate": 8.403260910589154e-05,
|
| 673 |
+
"loss": 1.8758,
|
| 674 |
+
"step": 54000
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 2.38,
|
| 678 |
+
"learning_rate": 8.387566520311498e-05,
|
| 679 |
+
"loss": 1.8728,
|
| 680 |
+
"step": 54500
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 2.4,
|
| 684 |
+
"learning_rate": 8.371840678349919e-05,
|
| 685 |
+
"loss": 1.8713,
|
| 686 |
+
"step": 55000
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 2.42,
|
| 690 |
+
"learning_rate": 8.35611483638834e-05,
|
| 691 |
+
"loss": 1.8675,
|
| 692 |
+
"step": 55500
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 2.44,
|
| 696 |
+
"learning_rate": 8.340388994426763e-05,
|
| 697 |
+
"loss": 1.8653,
|
| 698 |
+
"step": 56000
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 2.46,
|
| 702 |
+
"learning_rate": 8.324694604149107e-05,
|
| 703 |
+
"loss": 1.8635,
|
| 704 |
+
"step": 56500
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.48,
|
| 708 |
+
"learning_rate": 8.308968762187528e-05,
|
| 709 |
+
"loss": 1.8589,
|
| 710 |
+
"step": 57000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 2.51,
|
| 714 |
+
"learning_rate": 8.293242920225949e-05,
|
| 715 |
+
"loss": 1.8585,
|
| 716 |
+
"step": 57500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 2.53,
|
| 720 |
+
"learning_rate": 8.27751707826437e-05,
|
| 721 |
+
"loss": 1.8592,
|
| 722 |
+
"step": 58000
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 2.55,
|
| 726 |
+
"learning_rate": 8.261822687986716e-05,
|
| 727 |
+
"loss": 1.8551,
|
| 728 |
+
"step": 58500
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 2.57,
|
| 732 |
+
"learning_rate": 8.246096846025136e-05,
|
| 733 |
+
"loss": 1.8564,
|
| 734 |
+
"step": 59000
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 2.59,
|
| 738 |
+
"learning_rate": 8.230371004063558e-05,
|
| 739 |
+
"loss": 1.851,
|
| 740 |
+
"step": 59500
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 2.62,
|
| 744 |
+
"learning_rate": 8.214645162101979e-05,
|
| 745 |
+
"loss": 1.8469,
|
| 746 |
+
"step": 60000
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 2.64,
|
| 750 |
+
"learning_rate": 8.198950771824324e-05,
|
| 751 |
+
"loss": 1.8461,
|
| 752 |
+
"step": 60500
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 2.66,
|
| 756 |
+
"learning_rate": 8.183224929862745e-05,
|
| 757 |
+
"loss": 1.8487,
|
| 758 |
+
"step": 61000
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 2.68,
|
| 762 |
+
"learning_rate": 8.167499087901167e-05,
|
| 763 |
+
"loss": 1.8435,
|
| 764 |
+
"step": 61500
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 2.7,
|
| 768 |
+
"learning_rate": 8.151773245939588e-05,
|
| 769 |
+
"loss": 1.8403,
|
| 770 |
+
"step": 62000
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 2.72,
|
| 774 |
+
"learning_rate": 8.136078855661933e-05,
|
| 775 |
+
"loss": 1.8435,
|
| 776 |
+
"step": 62500
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 2.75,
|
| 780 |
+
"learning_rate": 8.120353013700354e-05,
|
| 781 |
+
"loss": 1.8409,
|
| 782 |
+
"step": 63000
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 2.77,
|
| 786 |
+
"learning_rate": 8.104627171738776e-05,
|
| 787 |
+
"loss": 1.8359,
|
| 788 |
+
"step": 63500
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 2.79,
|
| 792 |
+
"learning_rate": 8.088901329777196e-05,
|
| 793 |
+
"loss": 1.833,
|
| 794 |
+
"step": 64000
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 2.81,
|
| 798 |
+
"learning_rate": 8.073206939499542e-05,
|
| 799 |
+
"loss": 1.8336,
|
| 800 |
+
"step": 64500
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 2.83,
|
| 804 |
+
"learning_rate": 8.057481097537963e-05,
|
| 805 |
+
"loss": 1.8348,
|
| 806 |
+
"step": 65000
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 2.86,
|
| 810 |
+
"learning_rate": 8.041755255576384e-05,
|
| 811 |
+
"loss": 1.8302,
|
| 812 |
+
"step": 65500
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 2.88,
|
| 816 |
+
"learning_rate": 8.026029413614805e-05,
|
| 817 |
+
"loss": 1.8253,
|
| 818 |
+
"step": 66000
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 2.9,
|
| 822 |
+
"learning_rate": 8.01033502333715e-05,
|
| 823 |
+
"loss": 1.8225,
|
| 824 |
+
"step": 66500
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 2.92,
|
| 828 |
+
"learning_rate": 7.99460918137557e-05,
|
| 829 |
+
"loss": 1.8245,
|
| 830 |
+
"step": 67000
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 2.94,
|
| 834 |
+
"learning_rate": 7.978883339413993e-05,
|
| 835 |
+
"loss": 1.8246,
|
| 836 |
+
"step": 67500
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 2.96,
|
| 840 |
+
"learning_rate": 7.963157497452414e-05,
|
| 841 |
+
"loss": 1.8203,
|
| 842 |
+
"step": 68000
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 2.99,
|
| 846 |
+
"learning_rate": 7.947463107174758e-05,
|
| 847 |
+
"loss": 1.8178,
|
| 848 |
+
"step": 68500
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 3.0,
|
| 852 |
+
"eval_accuracy": 0.6562844667040338,
|
| 853 |
+
"eval_loss": 1.6895612478256226,
|
| 854 |
+
"eval_runtime": 294.9578,
|
| 855 |
+
"eval_samples_per_second": 603.314,
|
| 856 |
+
"eval_steps_per_second": 37.707,
|
| 857 |
+
"step": 68820
|
| 858 |
}
|
| 859 |
],
|
| 860 |
"max_steps": 321160,
|
| 861 |
"num_train_epochs": 14,
|
| 862 |
+
"total_flos": 5.2328760513448845e+17,
|
| 863 |
"trial_name": null,
|
| 864 |
"trial_params": null
|
| 865 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 118253458
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2906e434c2be5553d8ba690fa00f38995006c684a8b4fbef8476c7418f239877
|
| 3 |
size 118253458
|
runs/Feb20_18-29-06_ubuntu-2004/events.out.tfevents.1676885357.ubuntu-2004.887393.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7bf4c282d434ce5ba540303c16207d3c8f5d389184c1a3bbf4dd4df23675b929
|
| 3 |
+
size 26579
|