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 469337272
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4eda0e89aa4d3d282525d77c55d3bb3bc455baed6788b7932726886a4fec8d9d
|
| 3 |
size 469337272
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 938825803
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1edb7194df3a9589c4165f828399d05a5b3aae13f4977bb578f5509f2695427b
|
| 3 |
size 938825803
|
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 sha256:2c47bf8207ce24fd1d44b017f106d799e41cb97bfb17f06383eccd30d2f40350
|
| 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 sha256:54283825bf988fc504a674e83415482fb216062ac68ed73b527e8f8eb54d9eec
|
| 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": 84.533,
|
| 633 |
"eval_steps_per_second": 21.133,
|
| 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": 0.10909090909090909,
|
| 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": 84.533,
|
| 633 |
"eval_steps_per_second": 21.133,
|
| 634 |
"step": 8000
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.07363636363636364,
|
| 638 |
+
"grad_norm": 0.18711890280246735,
|
| 639 |
+
"learning_rate": 0.0009871354840820543,
|
| 640 |
+
"loss": 3.0751129150390626,
|
| 641 |
+
"step": 8100
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.07454545454545454,
|
| 645 |
+
"grad_norm": 0.19081872701644897,
|
| 646 |
+
"learning_rate": 0.0009868112112252953,
|
| 647 |
+
"loss": 3.069129638671875,
|
| 648 |
+
"step": 8200
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.07545454545454545,
|
| 652 |
+
"grad_norm": 0.18380340933799744,
|
| 653 |
+
"learning_rate": 0.0009864829567477196,
|
| 654 |
+
"loss": 3.0967727661132813,
|
| 655 |
+
"step": 8300
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.07636363636363637,
|
| 659 |
+
"grad_norm": 0.1662234514951706,
|
| 660 |
+
"learning_rate": 0.0009861507233341154,
|
| 661 |
+
"loss": 3.0465274047851563,
|
| 662 |
+
"step": 8400
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.07727272727272727,
|
| 666 |
+
"grad_norm": 0.1769150197505951,
|
| 667 |
+
"learning_rate": 0.0009858145137018137,
|
| 668 |
+
"loss": 3.05833251953125,
|
| 669 |
+
"step": 8500
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.07818181818181819,
|
| 673 |
+
"grad_norm": 0.18805448710918427,
|
| 674 |
+
"learning_rate": 0.0009854743306006682,
|
| 675 |
+
"loss": 3.0252114868164064,
|
| 676 |
+
"step": 8600
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.07909090909090909,
|
| 680 |
+
"grad_norm": 0.18553867936134338,
|
| 681 |
+
"learning_rate": 0.0009851301768130304,
|
| 682 |
+
"loss": 3.0619546508789064,
|
| 683 |
+
"step": 8700
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.08,
|
| 687 |
+
"grad_norm": 0.18448372185230255,
|
| 688 |
+
"learning_rate": 0.0009847820551537288,
|
| 689 |
+
"loss": 3.076944580078125,
|
| 690 |
+
"step": 8800
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.0809090909090909,
|
| 694 |
+
"grad_norm": 0.18073825538158417,
|
| 695 |
+
"learning_rate": 0.0009844299684700442,
|
| 696 |
+
"loss": 3.04953857421875,
|
| 697 |
+
"step": 8900
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.08181818181818182,
|
| 701 |
+
"grad_norm": 0.18676605820655823,
|
| 702 |
+
"learning_rate": 0.000984073919641688,
|
| 703 |
+
"loss": 3.052662658691406,
|
| 704 |
+
"step": 9000
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.08181818181818182,
|
| 708 |
+
"eval_loss": 3.390735626220703,
|
| 709 |
+
"eval_runtime": 6.8573,
|
| 710 |
+
"eval_samples_per_second": 83.999,
|
| 711 |
+
"eval_steps_per_second": 21.0,
|
| 712 |
+
"step": 9000
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 0.08272727272727273,
|
| 716 |
+
"grad_norm": 0.1843118667602539,
|
| 717 |
+
"learning_rate": 0.0009837139115807777,
|
| 718 |
+
"loss": 3.0578955078125,
|
| 719 |
+
"step": 9100
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 0.08363636363636363,
|
| 723 |
+
"grad_norm": 0.1908266246318817,
|
| 724 |
+
"learning_rate": 0.0009833499472318129,
|
| 725 |
+
"loss": 3.0461907958984376,
|
| 726 |
+
"step": 9200
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 0.08454545454545455,
|
| 730 |
+
"grad_norm": 0.17415334284305573,
|
| 731 |
+
"learning_rate": 0.0009829820295716525,
|
| 732 |
+
"loss": 3.0242233276367188,
|
| 733 |
+
"step": 9300
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.08545454545454545,
|
| 737 |
+
"grad_norm": 0.161512091755867,
|
| 738 |
+
"learning_rate": 0.0009826101616094885,
|
| 739 |
+
"loss": 3.06851806640625,
|
| 740 |
+
"step": 9400
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.08636363636363636,
|
| 744 |
+
"grad_norm": 0.17435242235660553,
|
| 745 |
+
"learning_rate": 0.000982234346386823,
|
| 746 |
+
"loss": 3.04041015625,
|
| 747 |
+
"step": 9500
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.08727272727272728,
|
| 751 |
+
"grad_norm": 0.17635726928710938,
|
| 752 |
+
"learning_rate": 0.0009818545869774427,
|
| 753 |
+
"loss": 3.0322161865234376,
|
| 754 |
+
"step": 9600
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.08818181818181818,
|
| 758 |
+
"grad_norm": 0.19083574414253235,
|
| 759 |
+
"learning_rate": 0.000981470886487393,
|
| 760 |
+
"loss": 3.0362371826171874,
|
| 761 |
+
"step": 9700
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.0890909090909091,
|
| 765 |
+
"grad_norm": 0.1669977903366089,
|
| 766 |
+
"learning_rate": 0.000981083248054954,
|
| 767 |
+
"loss": 3.0415472412109374,
|
| 768 |
+
"step": 9800
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.09,
|
| 772 |
+
"grad_norm": 0.1624830961227417,
|
| 773 |
+
"learning_rate": 0.000980691674850614,
|
| 774 |
+
"loss": 3.03228271484375,
|
| 775 |
+
"step": 9900
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.09090909090909091,
|
| 779 |
+
"grad_norm": 0.20320835709571838,
|
| 780 |
+
"learning_rate": 0.000980296170077044,
|
| 781 |
+
"loss": 3.0213031005859374,
|
| 782 |
+
"step": 10000
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.09090909090909091,
|
| 786 |
+
"eval_loss": 3.3655972480773926,
|
| 787 |
+
"eval_runtime": 6.8194,
|
| 788 |
+
"eval_samples_per_second": 84.465,
|
| 789 |
+
"eval_steps_per_second": 21.116,
|
| 790 |
+
"step": 10000
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.09181818181818181,
|
| 794 |
+
"grad_norm": 0.1716221123933792,
|
| 795 |
+
"learning_rate": 0.000979896736969071,
|
| 796 |
+
"loss": 3.018829345703125,
|
| 797 |
+
"step": 10100
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.09272727272727273,
|
| 801 |
+
"grad_norm": 0.18420584499835968,
|
| 802 |
+
"learning_rate": 0.0009794933787936513,
|
| 803 |
+
"loss": 3.0364111328125,
|
| 804 |
+
"step": 10200
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.09363636363636364,
|
| 808 |
+
"grad_norm": 0.16853921115398407,
|
| 809 |
+
"learning_rate": 0.000979086098849845,
|
| 810 |
+
"loss": 2.9975177001953126,
|
| 811 |
+
"step": 10300
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.09454545454545454,
|
| 815 |
+
"grad_norm": 0.17749086022377014,
|
| 816 |
+
"learning_rate": 0.000978674900468788,
|
| 817 |
+
"loss": 3.025662536621094,
|
| 818 |
+
"step": 10400
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.09545454545454546,
|
| 822 |
+
"grad_norm": 0.17817527055740356,
|
| 823 |
+
"learning_rate": 0.0009782597870136652,
|
| 824 |
+
"loss": 3.0068899536132814,
|
| 825 |
+
"step": 10500
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.09636363636363636,
|
| 829 |
+
"grad_norm": 0.16383598744869232,
|
| 830 |
+
"learning_rate": 0.0009778407618796824,
|
| 831 |
+
"loss": 2.9598651123046875,
|
| 832 |
+
"step": 10600
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 0.09727272727272727,
|
| 836 |
+
"grad_norm": 0.18420074880123138,
|
| 837 |
+
"learning_rate": 0.0009774178284940392,
|
| 838 |
+
"loss": 2.9876394653320313,
|
| 839 |
+
"step": 10700
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 0.09818181818181818,
|
| 843 |
+
"grad_norm": 0.16747510433197021,
|
| 844 |
+
"learning_rate": 0.0009769909903159007,
|
| 845 |
+
"loss": 3.0132855224609374,
|
| 846 |
+
"step": 10800
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 0.09909090909090909,
|
| 850 |
+
"grad_norm": 0.15621648728847504,
|
| 851 |
+
"learning_rate": 0.0009765602508363697,
|
| 852 |
+
"loss": 3.0095565795898436,
|
| 853 |
+
"step": 10900
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 0.1,
|
| 857 |
+
"grad_norm": 0.1697891354560852,
|
| 858 |
+
"learning_rate": 0.0009761256135784568,
|
| 859 |
+
"loss": 3.0590411376953126,
|
| 860 |
+
"step": 11000
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 0.1,
|
| 864 |
+
"eval_loss": 3.3478543758392334,
|
| 865 |
+
"eval_runtime": 6.8379,
|
| 866 |
+
"eval_samples_per_second": 84.236,
|
| 867 |
+
"eval_steps_per_second": 21.059,
|
| 868 |
+
"step": 11000
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 0.1009090909090909,
|
| 872 |
+
"grad_norm": 0.15818284451961517,
|
| 873 |
+
"learning_rate": 0.0009756870820970532,
|
| 874 |
+
"loss": 3.015447692871094,
|
| 875 |
+
"step": 11100
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 0.10181818181818182,
|
| 879 |
+
"grad_norm": 0.16059984266757965,
|
| 880 |
+
"learning_rate": 0.0009752446599789003,
|
| 881 |
+
"loss": 2.9939862060546876,
|
| 882 |
+
"step": 11200
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.10272727272727272,
|
| 886 |
+
"grad_norm": 0.16179029643535614,
|
| 887 |
+
"learning_rate": 0.0009747983508425615,
|
| 888 |
+
"loss": 2.989024963378906,
|
| 889 |
+
"step": 11300
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 0.10363636363636364,
|
| 893 |
+
"grad_norm": 0.16419965028762817,
|
| 894 |
+
"learning_rate": 0.0009743481583383919,
|
| 895 |
+
"loss": 2.9855859375,
|
| 896 |
+
"step": 11400
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 0.10454545454545454,
|
| 900 |
+
"grad_norm": 0.17154866456985474,
|
| 901 |
+
"learning_rate": 0.0009738940861485082,
|
| 902 |
+
"loss": 2.9723300170898437,
|
| 903 |
+
"step": 11500
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.10545454545454545,
|
| 907 |
+
"grad_norm": 0.16613702476024628,
|
| 908 |
+
"learning_rate": 0.0009734361379867597,
|
| 909 |
+
"loss": 3.022707214355469,
|
| 910 |
+
"step": 11600
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 0.10636363636363637,
|
| 914 |
+
"grad_norm": 0.16711774468421936,
|
| 915 |
+
"learning_rate": 0.0009729743175986965,
|
| 916 |
+
"loss": 2.99096923828125,
|
| 917 |
+
"step": 11700
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 0.10727272727272727,
|
| 921 |
+
"grad_norm": 0.16586251556873322,
|
| 922 |
+
"learning_rate": 0.00097250862876154,
|
| 923 |
+
"loss": 2.977761535644531,
|
| 924 |
+
"step": 11800
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 0.10818181818181818,
|
| 928 |
+
"grad_norm": 0.1719771921634674,
|
| 929 |
+
"learning_rate": 0.0009720390752841515,
|
| 930 |
+
"loss": 2.97351318359375,
|
| 931 |
+
"step": 11900
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 0.10909090909090909,
|
| 935 |
+
"grad_norm": 0.17710699141025543,
|
| 936 |
+
"learning_rate": 0.000971565661007001,
|
| 937 |
+
"loss": 2.976995849609375,
|
| 938 |
+
"step": 12000
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 0.10909090909090909,
|
| 942 |
+
"eval_loss": 3.324172019958496,
|
| 943 |
+
"eval_runtime": 6.855,
|
| 944 |
+
"eval_samples_per_second": 84.026,
|
| 945 |
+
"eval_steps_per_second": 21.006,
|
| 946 |
+
"step": 12000
|
| 947 |
}
|
| 948 |
],
|
| 949 |
"logging_steps": 100,
|
|
|
|
| 963 |
"attributes": {}
|
| 964 |
}
|
| 965 |
},
|
| 966 |
+
"total_flos": 2.98974971953152e+17,
|
| 967 |
"train_batch_size": 22,
|
| 968 |
"trial_name": null,
|
| 969 |
"trial_params": null
|