Training in progress, step 150, 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 59021064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e140581cf97c2ff49feded27279cbd08eace0495f5afd12562fa8c1906693ba4
|
| 3 |
size 59021064
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 30290452
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba59ea4e8eba7f0640208573e688cfef98d93f03d724499b344550aa047c5607
|
| 3 |
size 30290452
|
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 sha256:8abf2c3a2d675d09f86f31a4bbaac529a18147ee9c2568ece2b0294dff92a441
|
| 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:fe86356e82949734df1ffbf4ca1d6d4aad55d9e61b90271979f2d574e6a34d95
|
| 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":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -707,6 +707,356 @@
|
|
| 707 |
"learning_rate": 1.769911504424779e-05,
|
| 708 |
"loss": 2.72,
|
| 709 |
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 710 |
}
|
| 711 |
],
|
| 712 |
"logging_steps": 1,
|
|
@@ -726,7 +1076,7 @@
|
|
| 726 |
"attributes": {}
|
| 727 |
}
|
| 728 |
},
|
| 729 |
-
"total_flos":
|
| 730 |
"train_batch_size": 1,
|
| 731 |
"trial_name": null,
|
| 732 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.2631939684715556,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 150,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 707 |
"learning_rate": 1.769911504424779e-05,
|
| 708 |
"loss": 2.72,
|
| 709 |
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 2.197395476353667,
|
| 713 |
+
"grad_norm": 0.27964890003204346,
|
| 714 |
+
"learning_rate": 1.7876106194690265e-05,
|
| 715 |
+
"loss": 2.703,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 2.2193283070596297,
|
| 720 |
+
"grad_norm": 0.23122280836105347,
|
| 721 |
+
"learning_rate": 1.8053097345132743e-05,
|
| 722 |
+
"loss": 2.6755,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 2.241261137765593,
|
| 727 |
+
"grad_norm": 0.13872268795967102,
|
| 728 |
+
"learning_rate": 1.823008849557522e-05,
|
| 729 |
+
"loss": 2.5387,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 2.2631939684715556,
|
| 734 |
+
"grad_norm": 0.15757662057876587,
|
| 735 |
+
"learning_rate": 1.8407079646017702e-05,
|
| 736 |
+
"loss": 2.7089,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 2.285126799177519,
|
| 741 |
+
"grad_norm": 0.14636781811714172,
|
| 742 |
+
"learning_rate": 1.858407079646018e-05,
|
| 743 |
+
"loss": 2.7059,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 2.307059629883482,
|
| 748 |
+
"grad_norm": 0.12666302919387817,
|
| 749 |
+
"learning_rate": 1.8761061946902657e-05,
|
| 750 |
+
"loss": 2.677,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 2.3289924605894448,
|
| 755 |
+
"grad_norm": 0.09550761431455612,
|
| 756 |
+
"learning_rate": 1.8938053097345135e-05,
|
| 757 |
+
"loss": 2.5572,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 2.350925291295408,
|
| 762 |
+
"grad_norm": 0.22307220101356506,
|
| 763 |
+
"learning_rate": 1.9115044247787613e-05,
|
| 764 |
+
"loss": 2.5424,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 2.3728581220013707,
|
| 769 |
+
"grad_norm": 0.1976032704114914,
|
| 770 |
+
"learning_rate": 1.929203539823009e-05,
|
| 771 |
+
"loss": 2.608,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 2.394790952707334,
|
| 776 |
+
"grad_norm": 0.1282164454460144,
|
| 777 |
+
"learning_rate": 1.946902654867257e-05,
|
| 778 |
+
"loss": 2.6157,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 2.4167237834132966,
|
| 783 |
+
"grad_norm": 0.12939345836639404,
|
| 784 |
+
"learning_rate": 1.9646017699115046e-05,
|
| 785 |
+
"loss": 2.631,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 2.43865661411926,
|
| 790 |
+
"grad_norm": 0.1813574880361557,
|
| 791 |
+
"learning_rate": 1.9823008849557524e-05,
|
| 792 |
+
"loss": 2.5653,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 2.4605894448252226,
|
| 797 |
+
"grad_norm": 0.21558630466461182,
|
| 798 |
+
"learning_rate": 2e-05,
|
| 799 |
+
"loss": 2.6836,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 2.4825222755311858,
|
| 804 |
+
"grad_norm": 0.1171233206987381,
|
| 805 |
+
"learning_rate": 1.9999989194107888e-05,
|
| 806 |
+
"loss": 2.6329,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 2.504455106237149,
|
| 811 |
+
"grad_norm": 0.09073666483163834,
|
| 812 |
+
"learning_rate": 1.9999956776454904e-05,
|
| 813 |
+
"loss": 2.6365,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 2.5263879369431117,
|
| 818 |
+
"grad_norm": 0.15764959156513214,
|
| 819 |
+
"learning_rate": 1.999990274711111e-05,
|
| 820 |
+
"loss": 2.5957,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 2.5483207676490744,
|
| 825 |
+
"grad_norm": 0.1431242674589157,
|
| 826 |
+
"learning_rate": 1.9999827106193264e-05,
|
| 827 |
+
"loss": 2.6047,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 2.5702535983550376,
|
| 832 |
+
"grad_norm": 0.14802202582359314,
|
| 833 |
+
"learning_rate": 1.9999729853864854e-05,
|
| 834 |
+
"loss": 2.7031,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 2.592186429061001,
|
| 839 |
+
"grad_norm": 0.1163327619433403,
|
| 840 |
+
"learning_rate": 1.999961099033605e-05,
|
| 841 |
+
"loss": 2.5701,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 2.6141192597669636,
|
| 846 |
+
"grad_norm": 0.12083975225687027,
|
| 847 |
+
"learning_rate": 1.9999470515863738e-05,
|
| 848 |
+
"loss": 2.5481,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 2.6360520904729268,
|
| 853 |
+
"grad_norm": 0.11876373738050461,
|
| 854 |
+
"learning_rate": 1.9999308430751513e-05,
|
| 855 |
+
"loss": 2.6219,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 2.6579849211788895,
|
| 860 |
+
"grad_norm": 0.12213423103094101,
|
| 861 |
+
"learning_rate": 1.9999124735349666e-05,
|
| 862 |
+
"loss": 2.5822,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 2.6799177518848527,
|
| 867 |
+
"grad_norm": 0.1777854710817337,
|
| 868 |
+
"learning_rate": 1.9998919430055193e-05,
|
| 869 |
+
"loss": 2.6359,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 2.701850582590816,
|
| 874 |
+
"grad_norm": 0.10676445066928864,
|
| 875 |
+
"learning_rate": 1.9998692515311806e-05,
|
| 876 |
+
"loss": 2.6015,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 2.7237834132967786,
|
| 881 |
+
"grad_norm": 0.08957359939813614,
|
| 882 |
+
"learning_rate": 1.9998443991609897e-05,
|
| 883 |
+
"loss": 2.6041,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 2.7457162440027414,
|
| 888 |
+
"grad_norm": 0.14414869248867035,
|
| 889 |
+
"learning_rate": 1.9998173859486575e-05,
|
| 890 |
+
"loss": 2.6832,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 2.7676490747087046,
|
| 895 |
+
"grad_norm": 0.14377790689468384,
|
| 896 |
+
"learning_rate": 1.9997882119525644e-05,
|
| 897 |
+
"loss": 2.502,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 2.7895819054146678,
|
| 902 |
+
"grad_norm": 0.14488162100315094,
|
| 903 |
+
"learning_rate": 1.9997568772357603e-05,
|
| 904 |
+
"loss": 2.6653,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 2.8115147361206305,
|
| 909 |
+
"grad_norm": 0.10184569656848907,
|
| 910 |
+
"learning_rate": 1.999723381865965e-05,
|
| 911 |
+
"loss": 2.6141,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 2.8334475668265937,
|
| 916 |
+
"grad_norm": 0.08704333007335663,
|
| 917 |
+
"learning_rate": 1.999687725915569e-05,
|
| 918 |
+
"loss": 2.7103,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 2.8553803975325565,
|
| 923 |
+
"grad_norm": 0.09079142659902573,
|
| 924 |
+
"learning_rate": 1.99964990946163e-05,
|
| 925 |
+
"loss": 2.4572,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 2.8773132282385196,
|
| 930 |
+
"grad_norm": 0.11046919226646423,
|
| 931 |
+
"learning_rate": 1.9996099325858766e-05,
|
| 932 |
+
"loss": 2.6408,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 2.8992460589444824,
|
| 937 |
+
"grad_norm": 0.11394225060939789,
|
| 938 |
+
"learning_rate": 1.999567795374706e-05,
|
| 939 |
+
"loss": 2.4854,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 2.9211788896504456,
|
| 944 |
+
"grad_norm": 0.1528523713350296,
|
| 945 |
+
"learning_rate": 1.9995234979191843e-05,
|
| 946 |
+
"loss": 2.5499,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 2.9431117203564083,
|
| 951 |
+
"grad_norm": 0.07764479517936707,
|
| 952 |
+
"learning_rate": 1.999477040315046e-05,
|
| 953 |
+
"loss": 2.6315,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 2.9650445510623715,
|
| 958 |
+
"grad_norm": 0.09709993004798889,
|
| 959 |
+
"learning_rate": 1.9994284226626944e-05,
|
| 960 |
+
"loss": 2.6537,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 2.9869773817683347,
|
| 965 |
+
"grad_norm": 0.07892050594091415,
|
| 966 |
+
"learning_rate": 1.9993776450672007e-05,
|
| 967 |
+
"loss": 2.5603,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 3.0,
|
| 972 |
+
"grad_norm": 0.09977299720048904,
|
| 973 |
+
"learning_rate": 1.999324707638304e-05,
|
| 974 |
+
"loss": 2.6216,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 3.021932830705963,
|
| 979 |
+
"grad_norm": 0.10072707384824753,
|
| 980 |
+
"learning_rate": 1.999269610490413e-05,
|
| 981 |
+
"loss": 2.7363,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 3.043865661411926,
|
| 986 |
+
"grad_norm": 0.11965449154376984,
|
| 987 |
+
"learning_rate": 1.999212353742601e-05,
|
| 988 |
+
"loss": 2.5138,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 3.065798492117889,
|
| 993 |
+
"grad_norm": 0.09121505171060562,
|
| 994 |
+
"learning_rate": 1.9991529375186104e-05,
|
| 995 |
+
"loss": 2.6217,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 3.087731322823852,
|
| 1000 |
+
"grad_norm": 0.143572136759758,
|
| 1001 |
+
"learning_rate": 1.9990913619468507e-05,
|
| 1002 |
+
"loss": 2.6007,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 3.109664153529815,
|
| 1007 |
+
"grad_norm": 0.06798284500837326,
|
| 1008 |
+
"learning_rate": 1.9990276271603972e-05,
|
| 1009 |
+
"loss": 2.5446,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 3.131596984235778,
|
| 1014 |
+
"grad_norm": 0.07691462337970734,
|
| 1015 |
+
"learning_rate": 1.9989617332969924e-05,
|
| 1016 |
+
"loss": 2.5537,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 3.153529814941741,
|
| 1021 |
+
"grad_norm": 0.05225904658436775,
|
| 1022 |
+
"learning_rate": 1.9988936804990446e-05,
|
| 1023 |
+
"loss": 2.5238,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 3.1754626456477038,
|
| 1028 |
+
"grad_norm": 0.10837385058403015,
|
| 1029 |
+
"learning_rate": 1.9988234689136284e-05,
|
| 1030 |
+
"loss": 2.6316,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 3.197395476353667,
|
| 1035 |
+
"grad_norm": 0.08016310632228851,
|
| 1036 |
+
"learning_rate": 1.9987510986924828e-05,
|
| 1037 |
+
"loss": 2.5408,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 3.2193283070596297,
|
| 1042 |
+
"grad_norm": 0.1278998851776123,
|
| 1043 |
+
"learning_rate": 1.9986765699920134e-05,
|
| 1044 |
+
"loss": 2.6916,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 3.241261137765593,
|
| 1049 |
+
"grad_norm": 0.115745909512043,
|
| 1050 |
+
"learning_rate": 1.9985998829732898e-05,
|
| 1051 |
+
"loss": 2.5964,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 3.2631939684715556,
|
| 1056 |
+
"grad_norm": 0.05191206559538841,
|
| 1057 |
+
"learning_rate": 1.9985210378020464e-05,
|
| 1058 |
+
"loss": 2.5719,
|
| 1059 |
+
"step": 150
|
| 1060 |
}
|
| 1061 |
],
|
| 1062 |
"logging_steps": 1,
|
|
|
|
| 1076 |
"attributes": {}
|
| 1077 |
}
|
| 1078 |
},
|
| 1079 |
+
"total_flos": 3.2639143951466496e+17,
|
| 1080 |
"train_batch_size": 1,
|
| 1081 |
"trial_name": null,
|
| 1082 |
"trial_params": null
|