Training in progress, step 1200, 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 723674912
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bad5e660c2681bf513edd8d9c80ea4ffe1dbe06a8eb2430490fcd914238944a6
|
| 3 |
size 723674912
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 735625626
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f69a85f7d27ed1c6d319c12454c4c516fc2be3c9e582716f2cfdb5b74a2524ea
|
| 3 |
size 735625626
|
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:a85b7ee4e3e06f8b21d4d23e7eb8bbe5510e7f25d23cfc2ffc16d97845a1be25
|
| 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 sha256:427276ae77d918ee2b880ea4152618640d39ea76588856ca2cd62fe2ab8b83d7
|
| 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": 200,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -607,6 +607,302 @@
|
|
| 607 |
"eval_samples_per_second": 39.558,
|
| 608 |
"eval_steps_per_second": 9.903,
|
| 609 |
"step": 800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 610 |
}
|
| 611 |
],
|
| 612 |
"logging_steps": 10,
|
|
@@ -626,7 +922,7 @@
|
|
| 626 |
"attributes": {}
|
| 627 |
}
|
| 628 |
},
|
| 629 |
-
"total_flos": 1.
|
| 630 |
"train_batch_size": 4,
|
| 631 |
"trial_name": null,
|
| 632 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.3551346552234389,
|
| 5 |
"eval_steps": 200,
|
| 6 |
+
"global_step": 1200,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 607 |
"eval_samples_per_second": 39.558,
|
| 608 |
"eval_steps_per_second": 9.903,
|
| 609 |
"step": 800
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.23971589227582124,
|
| 613 |
+
"grad_norm": 2.3125,
|
| 614 |
+
"learning_rate": 0.0001616818989495711,
|
| 615 |
+
"loss": 2.385,
|
| 616 |
+
"step": 810
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 0.24267534773601657,
|
| 620 |
+
"grad_norm": 3.203125,
|
| 621 |
+
"learning_rate": 0.00016063536950548826,
|
| 622 |
+
"loss": 2.0597,
|
| 623 |
+
"step": 820
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 0.2456348031962119,
|
| 627 |
+
"grad_norm": 2.8125,
|
| 628 |
+
"learning_rate": 0.0001595782306274553,
|
| 629 |
+
"loss": 1.9741,
|
| 630 |
+
"step": 830
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 0.24859425865640722,
|
| 634 |
+
"grad_norm": 6.5,
|
| 635 |
+
"learning_rate": 0.00015851066728416618,
|
| 636 |
+
"loss": 2.0407,
|
| 637 |
+
"step": 840
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 0.25155371411660254,
|
| 641 |
+
"grad_norm": 21.0,
|
| 642 |
+
"learning_rate": 0.00015743286626829437,
|
| 643 |
+
"loss": 1.9952,
|
| 644 |
+
"step": 850
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 0.25451316957679787,
|
| 648 |
+
"grad_norm": 2.03125,
|
| 649 |
+
"learning_rate": 0.00015634501616380967,
|
| 650 |
+
"loss": 2.2178,
|
| 651 |
+
"step": 860
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.2574726250369932,
|
| 655 |
+
"grad_norm": 2.765625,
|
| 656 |
+
"learning_rate": 0.00015524730731298134,
|
| 657 |
+
"loss": 2.0677,
|
| 658 |
+
"step": 870
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 0.2604320804971885,
|
| 662 |
+
"grad_norm": 4.53125,
|
| 663 |
+
"learning_rate": 0.0001541399317830738,
|
| 664 |
+
"loss": 2.2565,
|
| 665 |
+
"step": 880
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 0.26339153595738385,
|
| 669 |
+
"grad_norm": 5.0,
|
| 670 |
+
"learning_rate": 0.0001530230833327405,
|
| 671 |
+
"loss": 1.9119,
|
| 672 |
+
"step": 890
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 0.2663509914175792,
|
| 676 |
+
"grad_norm": 8.5625,
|
| 677 |
+
"learning_rate": 0.00015189695737812152,
|
| 678 |
+
"loss": 1.8892,
|
| 679 |
+
"step": 900
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 0.2693104468777745,
|
| 683 |
+
"grad_norm": 2.578125,
|
| 684 |
+
"learning_rate": 0.0001507617509586517,
|
| 685 |
+
"loss": 2.1497,
|
| 686 |
+
"step": 910
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.2722699023379698,
|
| 690 |
+
"grad_norm": 2.421875,
|
| 691 |
+
"learning_rate": 0.00014961766270258422,
|
| 692 |
+
"loss": 2.1354,
|
| 693 |
+
"step": 920
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.27522935779816515,
|
| 697 |
+
"grad_norm": 3.015625,
|
| 698 |
+
"learning_rate": 0.00014846489279223652,
|
| 699 |
+
"loss": 1.7865,
|
| 700 |
+
"step": 930
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 0.2781888132583605,
|
| 704 |
+
"grad_norm": 5.03125,
|
| 705 |
+
"learning_rate": 0.0001473036429289641,
|
| 706 |
+
"loss": 2.1861,
|
| 707 |
+
"step": 940
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 0.2811482687185558,
|
| 711 |
+
"grad_norm": 16.5,
|
| 712 |
+
"learning_rate": 0.0001461341162978688,
|
| 713 |
+
"loss": 1.8348,
|
| 714 |
+
"step": 950
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.28410772417875113,
|
| 718 |
+
"grad_norm": 2.3125,
|
| 719 |
+
"learning_rate": 0.00014495651753224705,
|
| 720 |
+
"loss": 2.1879,
|
| 721 |
+
"step": 960
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 0.28706717963894646,
|
| 725 |
+
"grad_norm": 2.296875,
|
| 726 |
+
"learning_rate": 0.00014377105267778518,
|
| 727 |
+
"loss": 2.2375,
|
| 728 |
+
"step": 970
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 0.2900266350991418,
|
| 732 |
+
"grad_norm": 2.875,
|
| 733 |
+
"learning_rate": 0.00014257792915650728,
|
| 734 |
+
"loss": 2.1182,
|
| 735 |
+
"step": 980
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.2929860905593371,
|
| 739 |
+
"grad_norm": 5.21875,
|
| 740 |
+
"learning_rate": 0.00014137735573048233,
|
| 741 |
+
"loss": 2.178,
|
| 742 |
+
"step": 990
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 0.2959455460195324,
|
| 746 |
+
"grad_norm": 21.75,
|
| 747 |
+
"learning_rate": 0.00014016954246529696,
|
| 748 |
+
"loss": 1.7343,
|
| 749 |
+
"step": 1000
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 0.2959455460195324,
|
| 753 |
+
"eval_loss": 2.05126953125,
|
| 754 |
+
"eval_runtime": 37.8219,
|
| 755 |
+
"eval_samples_per_second": 39.712,
|
| 756 |
+
"eval_steps_per_second": 9.941,
|
| 757 |
+
"step": 1000
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 0.2989050014797277,
|
| 761 |
+
"grad_norm": 2.28125,
|
| 762 |
+
"learning_rate": 0.00013895470069330004,
|
| 763 |
+
"loss": 2.3846,
|
| 764 |
+
"step": 1010
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 0.30186445693992303,
|
| 768 |
+
"grad_norm": 3.328125,
|
| 769 |
+
"learning_rate": 0.00013773304297662559,
|
| 770 |
+
"loss": 1.9283,
|
| 771 |
+
"step": 1020
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.30482391240011836,
|
| 775 |
+
"grad_norm": 3.5,
|
| 776 |
+
"learning_rate": 0.00013650478307000057,
|
| 777 |
+
"loss": 2.0405,
|
| 778 |
+
"step": 1030
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 0.3077833678603137,
|
| 782 |
+
"grad_norm": 6.5,
|
| 783 |
+
"learning_rate": 0.00013527013588334415,
|
| 784 |
+
"loss": 2.0844,
|
| 785 |
+
"step": 1040
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 0.310742823320509,
|
| 789 |
+
"grad_norm": 13.75,
|
| 790 |
+
"learning_rate": 0.00013402931744416433,
|
| 791 |
+
"loss": 1.8831,
|
| 792 |
+
"step": 1050
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 0.31370227878070434,
|
| 796 |
+
"grad_norm": 1.9765625,
|
| 797 |
+
"learning_rate": 0.00013278254485975976,
|
| 798 |
+
"loss": 2.1649,
|
| 799 |
+
"step": 1060
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 0.31666173424089966,
|
| 803 |
+
"grad_norm": 2.828125,
|
| 804 |
+
"learning_rate": 0.00013153003627923218,
|
| 805 |
+
"loss": 2.2713,
|
| 806 |
+
"step": 1070
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 0.319621189701095,
|
| 810 |
+
"grad_norm": 3.90625,
|
| 811 |
+
"learning_rate": 0.00013027201085531634,
|
| 812 |
+
"loss": 2.286,
|
| 813 |
+
"step": 1080
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.3225806451612903,
|
| 817 |
+
"grad_norm": 3.71875,
|
| 818 |
+
"learning_rate": 0.00012900868870603503,
|
| 819 |
+
"loss": 1.9544,
|
| 820 |
+
"step": 1090
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 0.32554010062148564,
|
| 824 |
+
"grad_norm": 14.125,
|
| 825 |
+
"learning_rate": 0.00012774029087618446,
|
| 826 |
+
"loss": 2.2556,
|
| 827 |
+
"step": 1100
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 0.32849955608168097,
|
| 831 |
+
"grad_norm": 1.96875,
|
| 832 |
+
"learning_rate": 0.00012646703929865817,
|
| 833 |
+
"loss": 2.0874,
|
| 834 |
+
"step": 1110
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 0.3314590115418763,
|
| 838 |
+
"grad_norm": 2.765625,
|
| 839 |
+
"learning_rate": 0.00012518915675561483,
|
| 840 |
+
"loss": 2.255,
|
| 841 |
+
"step": 1120
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.3344184670020716,
|
| 845 |
+
"grad_norm": 3.5625,
|
| 846 |
+
"learning_rate": 0.00012390686683949798,
|
| 847 |
+
"loss": 1.9591,
|
| 848 |
+
"step": 1130
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 0.33737792246226694,
|
| 852 |
+
"grad_norm": 6.6875,
|
| 853 |
+
"learning_rate": 0.00012262039391391404,
|
| 854 |
+
"loss": 1.949,
|
| 855 |
+
"step": 1140
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.34033737792246227,
|
| 859 |
+
"grad_norm": 21.0,
|
| 860 |
+
"learning_rate": 0.0001213299630743747,
|
| 861 |
+
"loss": 1.9946,
|
| 862 |
+
"step": 1150
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 0.3432968333826576,
|
| 866 |
+
"grad_norm": 2.65625,
|
| 867 |
+
"learning_rate": 0.00012003580010891213,
|
| 868 |
+
"loss": 2.4143,
|
| 869 |
+
"step": 1160
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 0.3462562888428529,
|
| 873 |
+
"grad_norm": 2.609375,
|
| 874 |
+
"learning_rate": 0.00011873813145857249,
|
| 875 |
+
"loss": 2.1089,
|
| 876 |
+
"step": 1170
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 0.34921574430304825,
|
| 880 |
+
"grad_norm": 4.28125,
|
| 881 |
+
"learning_rate": 0.00011743718417779517,
|
| 882 |
+
"loss": 2.227,
|
| 883 |
+
"step": 1180
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 0.3521751997632436,
|
| 887 |
+
"grad_norm": 5.0,
|
| 888 |
+
"learning_rate": 0.00011613318589468511,
|
| 889 |
+
"loss": 1.8928,
|
| 890 |
+
"step": 1190
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 0.3551346552234389,
|
| 894 |
+
"grad_norm": 7.78125,
|
| 895 |
+
"learning_rate": 0.0001148263647711842,
|
| 896 |
+
"loss": 1.4467,
|
| 897 |
+
"step": 1200
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.3551346552234389,
|
| 901 |
+
"eval_loss": 2.0554354190826416,
|
| 902 |
+
"eval_runtime": 37.6327,
|
| 903 |
+
"eval_samples_per_second": 39.912,
|
| 904 |
+
"eval_steps_per_second": 9.991,
|
| 905 |
+
"step": 1200
|
| 906 |
}
|
| 907 |
],
|
| 908 |
"logging_steps": 10,
|
|
|
|
| 922 |
"attributes": {}
|
| 923 |
}
|
| 924 |
},
|
| 925 |
+
"total_flos": 1.85888691191808e+16,
|
| 926 |
"train_batch_size": 4,
|
| 927 |
"trial_name": null,
|
| 928 |
"trial_params": null
|