Training in progress, step 12000, 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 541154336
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc4995194ae24360d283af7c87f66b06313c421ad3237dea5a676ea17582d264
|
| 3 |
size 541154336
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1082379659
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9134638ae868d7f042875926428ccfe72229e1aaba471b09bd4a42524bf529c7
|
| 3 |
size 1082379659
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:236304ae89e49aae8260113165ee63419b9b745f79120014328a7fa31ed79b42
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da9eb59c8b73626afc5a8c951a30627f32f26248a9fe83d71a280178d617963d
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 1000,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -632,6 +632,318 @@
|
|
| 632 |
"eval_samples_per_second": 45.514,
|
| 633 |
"eval_steps_per_second": 11.378,
|
| 634 |
"step": 8000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 635 |
}
|
| 636 |
],
|
| 637 |
"logging_steps": 100,
|
|
@@ -651,7 +963,7 @@
|
|
| 651 |
"attributes": {}
|
| 652 |
}
|
| 653 |
},
|
| 654 |
-
"total_flos":
|
| 655 |
"train_batch_size": 22,
|
| 656 |
"trial_name": null,
|
| 657 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.15584415584415584,
|
| 6 |
"eval_steps": 1000,
|
| 7 |
+
"global_step": 12000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 632 |
"eval_samples_per_second": 45.514,
|
| 633 |
"eval_steps_per_second": 11.378,
|
| 634 |
"step": 8000
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.10519480519480519,
|
| 638 |
+
"grad_norm": 0.19026321172714233,
|
| 639 |
+
"learning_rate": 0.000989706938281085,
|
| 640 |
+
"loss": 3.0792,
|
| 641 |
+
"step": 8100
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.10649350649350649,
|
| 645 |
+
"grad_norm": 0.22636525332927704,
|
| 646 |
+
"learning_rate": 0.0009894138657894054,
|
| 647 |
+
"loss": 3.0808,
|
| 648 |
+
"step": 8200
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.10779220779220779,
|
| 652 |
+
"grad_norm": 0.1759577989578247,
|
| 653 |
+
"learning_rate": 0.0009891167239833311,
|
| 654 |
+
"loss": 3.0651,
|
| 655 |
+
"step": 8300
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.10909090909090909,
|
| 659 |
+
"grad_norm": 0.19504410028457642,
|
| 660 |
+
"learning_rate": 0.0009888155153334984,
|
| 661 |
+
"loss": 3.0701,
|
| 662 |
+
"step": 8400
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.11038961038961038,
|
| 666 |
+
"grad_norm": 0.20704291760921478,
|
| 667 |
+
"learning_rate": 0.000988510242344357,
|
| 668 |
+
"loss": 3.072,
|
| 669 |
+
"step": 8500
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.11168831168831168,
|
| 673 |
+
"grad_norm": 0.19917143881320953,
|
| 674 |
+
"learning_rate": 0.000988200907554151,
|
| 675 |
+
"loss": 3.0716,
|
| 676 |
+
"step": 8600
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.11298701298701298,
|
| 680 |
+
"grad_norm": 0.1709250509738922,
|
| 681 |
+
"learning_rate": 0.000987887513534897,
|
| 682 |
+
"loss": 3.0622,
|
| 683 |
+
"step": 8700
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.11428571428571428,
|
| 687 |
+
"grad_norm": 0.2797200381755829,
|
| 688 |
+
"learning_rate": 0.0009875700628923622,
|
| 689 |
+
"loss": 3.0743,
|
| 690 |
+
"step": 8800
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.11558441558441558,
|
| 694 |
+
"grad_norm": 0.172173872590065,
|
| 695 |
+
"learning_rate": 0.000987248558266044,
|
| 696 |
+
"loss": 3.0676,
|
| 697 |
+
"step": 8900
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.11688311688311688,
|
| 701 |
+
"grad_norm": 0.1997879594564438,
|
| 702 |
+
"learning_rate": 0.000986923002329147,
|
| 703 |
+
"loss": 3.0591,
|
| 704 |
+
"step": 9000
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.11688311688311688,
|
| 708 |
+
"eval_loss": 3.424792766571045,
|
| 709 |
+
"eval_runtime": 15.3808,
|
| 710 |
+
"eval_samples_per_second": 37.449,
|
| 711 |
+
"eval_steps_per_second": 9.362,
|
| 712 |
+
"step": 9000
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 0.11818181818181818,
|
| 716 |
+
"grad_norm": 0.16804350912570953,
|
| 717 |
+
"learning_rate": 0.0009865933977885612,
|
| 718 |
+
"loss": 3.0642,
|
| 719 |
+
"step": 9100
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 0.11948051948051948,
|
| 723 |
+
"grad_norm": 0.1866862177848816,
|
| 724 |
+
"learning_rate": 0.0009862597473848393,
|
| 725 |
+
"loss": 3.0378,
|
| 726 |
+
"step": 9200
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 0.12077922077922078,
|
| 730 |
+
"grad_norm": 0.2142857313156128,
|
| 731 |
+
"learning_rate": 0.000985922053892174,
|
| 732 |
+
"loss": 3.057,
|
| 733 |
+
"step": 9300
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.12207792207792208,
|
| 737 |
+
"grad_norm": 0.1772162914276123,
|
| 738 |
+
"learning_rate": 0.0009855803201183743,
|
| 739 |
+
"loss": 3.0585,
|
| 740 |
+
"step": 9400
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.12337662337662338,
|
| 744 |
+
"grad_norm": 0.1796869933605194,
|
| 745 |
+
"learning_rate": 0.0009852345489048447,
|
| 746 |
+
"loss": 3.0228,
|
| 747 |
+
"step": 9500
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.12467532467532468,
|
| 751 |
+
"grad_norm": 0.19519853591918945,
|
| 752 |
+
"learning_rate": 0.0009848847431265576,
|
| 753 |
+
"loss": 3.0493,
|
| 754 |
+
"step": 9600
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.12597402597402596,
|
| 758 |
+
"grad_norm": 0.1866455227136612,
|
| 759 |
+
"learning_rate": 0.0009845309056920326,
|
| 760 |
+
"loss": 3.0369,
|
| 761 |
+
"step": 9700
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.12727272727272726,
|
| 765 |
+
"grad_norm": 0.1888640969991684,
|
| 766 |
+
"learning_rate": 0.000984173039543311,
|
| 767 |
+
"loss": 3.0388,
|
| 768 |
+
"step": 9800
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.12857142857142856,
|
| 772 |
+
"grad_norm": 0.1753017008304596,
|
| 773 |
+
"learning_rate": 0.0009838111476559313,
|
| 774 |
+
"loss": 3.0533,
|
| 775 |
+
"step": 9900
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.12987012987012986,
|
| 779 |
+
"grad_norm": 0.17457301914691925,
|
| 780 |
+
"learning_rate": 0.000983445233038905,
|
| 781 |
+
"loss": 3.0569,
|
| 782 |
+
"step": 10000
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.12987012987012986,
|
| 786 |
+
"eval_loss": 3.401273012161255,
|
| 787 |
+
"eval_runtime": 14.6757,
|
| 788 |
+
"eval_samples_per_second": 39.248,
|
| 789 |
+
"eval_steps_per_second": 9.812,
|
| 790 |
+
"step": 10000
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.13116883116883116,
|
| 794 |
+
"grad_norm": 0.17421157658100128,
|
| 795 |
+
"learning_rate": 0.0009830752987346908,
|
| 796 |
+
"loss": 3.0596,
|
| 797 |
+
"step": 10100
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.13246753246753246,
|
| 801 |
+
"grad_norm": 0.1772899180650711,
|
| 802 |
+
"learning_rate": 0.0009827013478191703,
|
| 803 |
+
"loss": 3.016,
|
| 804 |
+
"step": 10200
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.13376623376623376,
|
| 808 |
+
"grad_norm": 0.169020414352417,
|
| 809 |
+
"learning_rate": 0.0009823233834016214,
|
| 810 |
+
"loss": 3.0173,
|
| 811 |
+
"step": 10300
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.13506493506493505,
|
| 815 |
+
"grad_norm": 0.34023940563201904,
|
| 816 |
+
"learning_rate": 0.0009819414086246938,
|
| 817 |
+
"loss": 3.0004,
|
| 818 |
+
"step": 10400
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.13636363636363635,
|
| 822 |
+
"grad_norm": 0.19924494624137878,
|
| 823 |
+
"learning_rate": 0.0009815554266643808,
|
| 824 |
+
"loss": 3.003,
|
| 825 |
+
"step": 10500
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.13766233766233765,
|
| 829 |
+
"grad_norm": 0.1713639199733734,
|
| 830 |
+
"learning_rate": 0.0009811654407299948,
|
| 831 |
+
"loss": 2.9895,
|
| 832 |
+
"step": 10600
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 0.13896103896103895,
|
| 836 |
+
"grad_norm": 0.16809602081775665,
|
| 837 |
+
"learning_rate": 0.00098077145406414,
|
| 838 |
+
"loss": 3.0078,
|
| 839 |
+
"step": 10700
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 0.14025974025974025,
|
| 843 |
+
"grad_norm": 0.18249379098415375,
|
| 844 |
+
"learning_rate": 0.0009803734699426853,
|
| 845 |
+
"loss": 3.0379,
|
| 846 |
+
"step": 10800
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 0.14155844155844155,
|
| 850 |
+
"grad_norm": 0.19280089437961578,
|
| 851 |
+
"learning_rate": 0.0009799714916747368,
|
| 852 |
+
"loss": 2.9917,
|
| 853 |
+
"step": 10900
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 0.14285714285714285,
|
| 857 |
+
"grad_norm": 0.18399550020694733,
|
| 858 |
+
"learning_rate": 0.000979565522602611,
|
| 859 |
+
"loss": 3.0597,
|
| 860 |
+
"step": 11000
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 0.14285714285714285,
|
| 864 |
+
"eval_loss": 3.4125261306762695,
|
| 865 |
+
"eval_runtime": 15.5875,
|
| 866 |
+
"eval_samples_per_second": 36.953,
|
| 867 |
+
"eval_steps_per_second": 9.238,
|
| 868 |
+
"step": 11000
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 0.14415584415584415,
|
| 872 |
+
"grad_norm": 0.17574363946914673,
|
| 873 |
+
"learning_rate": 0.000979155566101806,
|
| 874 |
+
"loss": 3.0168,
|
| 875 |
+
"step": 11100
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 0.14545454545454545,
|
| 879 |
+
"grad_norm": 0.17517109215259552,
|
| 880 |
+
"learning_rate": 0.0009787416255809752,
|
| 881 |
+
"loss": 2.9817,
|
| 882 |
+
"step": 11200
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.14675324675324675,
|
| 886 |
+
"grad_norm": 0.18359977006912231,
|
| 887 |
+
"learning_rate": 0.0009783237044818968,
|
| 888 |
+
"loss": 2.9916,
|
| 889 |
+
"step": 11300
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 0.14805194805194805,
|
| 893 |
+
"grad_norm": 0.17518875002861023,
|
| 894 |
+
"learning_rate": 0.000977901806279446,
|
| 895 |
+
"loss": 2.9567,
|
| 896 |
+
"step": 11400
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 0.14935064935064934,
|
| 900 |
+
"grad_norm": 0.19247221946716309,
|
| 901 |
+
"learning_rate": 0.0009774759344815674,
|
| 902 |
+
"loss": 2.9901,
|
| 903 |
+
"step": 11500
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.15064935064935064,
|
| 907 |
+
"grad_norm": 0.18513117730617523,
|
| 908 |
+
"learning_rate": 0.000977046092629244,
|
| 909 |
+
"loss": 2.992,
|
| 910 |
+
"step": 11600
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 0.15194805194805194,
|
| 914 |
+
"grad_norm": 0.18412470817565918,
|
| 915 |
+
"learning_rate": 0.0009766122842964683,
|
| 916 |
+
"loss": 2.9985,
|
| 917 |
+
"step": 11700
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 0.15324675324675324,
|
| 921 |
+
"grad_norm": 0.19853200018405914,
|
| 922 |
+
"learning_rate": 0.0009761745130902134,
|
| 923 |
+
"loss": 2.978,
|
| 924 |
+
"step": 11800
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 0.15454545454545454,
|
| 928 |
+
"grad_norm": 0.19611628353595734,
|
| 929 |
+
"learning_rate": 0.0009757327826504022,
|
| 930 |
+
"loss": 2.9771,
|
| 931 |
+
"step": 11900
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 0.15584415584415584,
|
| 935 |
+
"grad_norm": 0.17522920668125153,
|
| 936 |
+
"learning_rate": 0.0009752870966498766,
|
| 937 |
+
"loss": 2.9641,
|
| 938 |
+
"step": 12000
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 0.15584415584415584,
|
| 942 |
+
"eval_loss": 3.3487231731414795,
|
| 943 |
+
"eval_runtime": 13.9045,
|
| 944 |
+
"eval_samples_per_second": 41.425,
|
| 945 |
+
"eval_steps_per_second": 10.356,
|
| 946 |
+
"step": 12000
|
| 947 |
}
|
| 948 |
],
|
| 949 |
"logging_steps": 100,
|
|
|
|
| 963 |
"attributes": {}
|
| 964 |
}
|
| 965 |
},
|
| 966 |
+
"total_flos": 3.5723176574976e+17,
|
| 967 |
"train_batch_size": 22,
|
| 968 |
"trial_name": null,
|
| 969 |
"trial_params": null
|