Training in progress, step 150, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 41119636
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a289398cbfa812eeb7230c9454af9a80f27c7792195f3439f23efd2658cc3c05
|
| 3 |
size 41119636
|
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 sha256:352ff13a94a6d85925e3b7180673ce4da0bce537a09578b8f895cb139c3dce3a
|
| 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:fd5d42bb0afda20ec4c83d38c6af1131541c335ecab229c74e7f418894f3c13b
|
| 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": 50,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -731,6 +731,364 @@
|
|
| 731 |
"eval_samples_per_second": 33.404,
|
| 732 |
"eval_steps_per_second": 16.702,
|
| 733 |
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
@@ -750,7 +1108,7 @@
|
|
| 750 |
"attributes": {}
|
| 751 |
}
|
| 752 |
},
|
| 753 |
-
"total_flos":
|
| 754 |
"train_batch_size": 2,
|
| 755 |
"trial_name": null,
|
| 756 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.01265689273283409,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 150,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 731 |
"eval_samples_per_second": 33.404,
|
| 732 |
"eval_steps_per_second": 16.702,
|
| 733 |
"step": 100
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.00852230777344162,
|
| 737 |
+
"grad_norm": NaN,
|
| 738 |
+
"learning_rate": 0.00010660905843256994,
|
| 739 |
+
"loss": 0.0,
|
| 740 |
+
"step": 101
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.00860668705832718,
|
| 744 |
+
"grad_norm": NaN,
|
| 745 |
+
"learning_rate": 0.00010495837546732224,
|
| 746 |
+
"loss": 0.0,
|
| 747 |
+
"step": 102
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.008691066343212742,
|
| 751 |
+
"grad_norm": NaN,
|
| 752 |
+
"learning_rate": 0.00010330633693173082,
|
| 753 |
+
"loss": 0.0,
|
| 754 |
+
"step": 103
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.008775445628098302,
|
| 758 |
+
"grad_norm": NaN,
|
| 759 |
+
"learning_rate": 0.00010165339447663587,
|
| 760 |
+
"loss": 0.0,
|
| 761 |
+
"step": 104
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.008859824912983863,
|
| 765 |
+
"grad_norm": NaN,
|
| 766 |
+
"learning_rate": 0.0001,
|
| 767 |
+
"loss": 0.0,
|
| 768 |
+
"step": 105
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.008944204197869423,
|
| 772 |
+
"grad_norm": NaN,
|
| 773 |
+
"learning_rate": 9.834660552336415e-05,
|
| 774 |
+
"loss": 0.0,
|
| 775 |
+
"step": 106
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.009028583482754983,
|
| 779 |
+
"grad_norm": NaN,
|
| 780 |
+
"learning_rate": 9.669366306826919e-05,
|
| 781 |
+
"loss": 2.8749,
|
| 782 |
+
"step": 107
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.009112962767640544,
|
| 786 |
+
"grad_norm": NaN,
|
| 787 |
+
"learning_rate": 9.504162453267777e-05,
|
| 788 |
+
"loss": 0.0,
|
| 789 |
+
"step": 108
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.009197342052526106,
|
| 793 |
+
"grad_norm": NaN,
|
| 794 |
+
"learning_rate": 9.339094156743007e-05,
|
| 795 |
+
"loss": 0.0,
|
| 796 |
+
"step": 109
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.009281721337411666,
|
| 800 |
+
"grad_norm": NaN,
|
| 801 |
+
"learning_rate": 9.174206545276677e-05,
|
| 802 |
+
"loss": 0.0,
|
| 803 |
+
"step": 110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.009366100622297226,
|
| 807 |
+
"grad_norm": NaN,
|
| 808 |
+
"learning_rate": 9.009544697495374e-05,
|
| 809 |
+
"loss": 0.0,
|
| 810 |
+
"step": 111
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.009450479907182787,
|
| 814 |
+
"grad_norm": NaN,
|
| 815 |
+
"learning_rate": 8.845153630304139e-05,
|
| 816 |
+
"loss": 0.0,
|
| 817 |
+
"step": 112
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.009534859192068347,
|
| 821 |
+
"grad_norm": NaN,
|
| 822 |
+
"learning_rate": 8.681078286579311e-05,
|
| 823 |
+
"loss": 3.7729,
|
| 824 |
+
"step": 113
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.009619238476953907,
|
| 828 |
+
"grad_norm": NaN,
|
| 829 |
+
"learning_rate": 8.517363522881579e-05,
|
| 830 |
+
"loss": 0.0,
|
| 831 |
+
"step": 114
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.009703617761839468,
|
| 835 |
+
"grad_norm": NaN,
|
| 836 |
+
"learning_rate": 8.35405409719266e-05,
|
| 837 |
+
"loss": 0.0,
|
| 838 |
+
"step": 115
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.00978799704672503,
|
| 842 |
+
"grad_norm": NaN,
|
| 843 |
+
"learning_rate": 8.191194656678904e-05,
|
| 844 |
+
"loss": 0.0,
|
| 845 |
+
"step": 116
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.00987237633161059,
|
| 849 |
+
"grad_norm": NaN,
|
| 850 |
+
"learning_rate": 8.028829725485199e-05,
|
| 851 |
+
"loss": 0.0,
|
| 852 |
+
"step": 117
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.00995675561649615,
|
| 856 |
+
"grad_norm": NaN,
|
| 857 |
+
"learning_rate": 7.867003692562534e-05,
|
| 858 |
+
"loss": 0.0,
|
| 859 |
+
"step": 118
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.01004113490138171,
|
| 863 |
+
"grad_norm": NaN,
|
| 864 |
+
"learning_rate": 7.705760799532485e-05,
|
| 865 |
+
"loss": 0.0,
|
| 866 |
+
"step": 119
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.010125514186267271,
|
| 870 |
+
"grad_norm": NaN,
|
| 871 |
+
"learning_rate": 7.54514512859201e-05,
|
| 872 |
+
"loss": 0.0,
|
| 873 |
+
"step": 120
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.010209893471152831,
|
| 877 |
+
"grad_norm": NaN,
|
| 878 |
+
"learning_rate": 7.385200590461803e-05,
|
| 879 |
+
"loss": 0.0,
|
| 880 |
+
"step": 121
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.010294272756038392,
|
| 884 |
+
"grad_norm": NaN,
|
| 885 |
+
"learning_rate": 7.225970912381556e-05,
|
| 886 |
+
"loss": 0.0,
|
| 887 |
+
"step": 122
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.010378652040923954,
|
| 891 |
+
"grad_norm": NaN,
|
| 892 |
+
"learning_rate": 7.067499626155354e-05,
|
| 893 |
+
"loss": 0.0,
|
| 894 |
+
"step": 123
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.010463031325809514,
|
| 898 |
+
"grad_norm": NaN,
|
| 899 |
+
"learning_rate": 6.909830056250527e-05,
|
| 900 |
+
"loss": 0.0,
|
| 901 |
+
"step": 124
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.010547410610695074,
|
| 905 |
+
"grad_norm": NaN,
|
| 906 |
+
"learning_rate": 6.753005307953167e-05,
|
| 907 |
+
"loss": 0.0,
|
| 908 |
+
"step": 125
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.010631789895580635,
|
| 912 |
+
"grad_norm": NaN,
|
| 913 |
+
"learning_rate": 6.59706825558357e-05,
|
| 914 |
+
"loss": 0.0,
|
| 915 |
+
"step": 126
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.010716169180466195,
|
| 919 |
+
"grad_norm": NaN,
|
| 920 |
+
"learning_rate": 6.442061530774834e-05,
|
| 921 |
+
"loss": 0.0,
|
| 922 |
+
"step": 127
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.010800548465351755,
|
| 926 |
+
"grad_norm": NaN,
|
| 927 |
+
"learning_rate": 6.28802751081779e-05,
|
| 928 |
+
"loss": 0.7095,
|
| 929 |
+
"step": 128
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.010884927750237318,
|
| 933 |
+
"grad_norm": NaN,
|
| 934 |
+
"learning_rate": 6.135008307075481e-05,
|
| 935 |
+
"loss": 0.0,
|
| 936 |
+
"step": 129
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.010969307035122878,
|
| 940 |
+
"grad_norm": NaN,
|
| 941 |
+
"learning_rate": 5.983045753470308e-05,
|
| 942 |
+
"loss": 0.0,
|
| 943 |
+
"step": 130
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.011053686320008438,
|
| 947 |
+
"grad_norm": NaN,
|
| 948 |
+
"learning_rate": 5.832181395047098e-05,
|
| 949 |
+
"loss": 0.0,
|
| 950 |
+
"step": 131
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.011138065604893999,
|
| 954 |
+
"grad_norm": NaN,
|
| 955 |
+
"learning_rate": 5.6824564766150726e-05,
|
| 956 |
+
"loss": 0.0,
|
| 957 |
+
"step": 132
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.011222444889779559,
|
| 961 |
+
"grad_norm": NaN,
|
| 962 |
+
"learning_rate": 5.533911931471936e-05,
|
| 963 |
+
"loss": 0.0,
|
| 964 |
+
"step": 133
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.01130682417466512,
|
| 968 |
+
"grad_norm": NaN,
|
| 969 |
+
"learning_rate": 5.386588370213124e-05,
|
| 970 |
+
"loss": 0.0,
|
| 971 |
+
"step": 134
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.01139120345955068,
|
| 975 |
+
"grad_norm": NaN,
|
| 976 |
+
"learning_rate": 5.240526069629265e-05,
|
| 977 |
+
"loss": 0.0,
|
| 978 |
+
"step": 135
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.011475582744436242,
|
| 982 |
+
"grad_norm": NaN,
|
| 983 |
+
"learning_rate": 5.095764961694922e-05,
|
| 984 |
+
"loss": 0.0,
|
| 985 |
+
"step": 136
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.011559962029321802,
|
| 989 |
+
"grad_norm": NaN,
|
| 990 |
+
"learning_rate": 4.952344622651566e-05,
|
| 991 |
+
"loss": 0.0,
|
| 992 |
+
"step": 137
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.011644341314207362,
|
| 996 |
+
"grad_norm": NaN,
|
| 997 |
+
"learning_rate": 4.810304262187852e-05,
|
| 998 |
+
"loss": 0.0,
|
| 999 |
+
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.011728720599092923,
|
| 1003 |
+
"grad_norm": NaN,
|
| 1004 |
+
"learning_rate": 4.669682712720065e-05,
|
| 1005 |
+
"loss": 0.0,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.011813099883978483,
|
| 1010 |
+
"grad_norm": NaN,
|
| 1011 |
+
"learning_rate": 4.530518418775733e-05,
|
| 1012 |
+
"loss": 0.0,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.011897479168864043,
|
| 1017 |
+
"grad_norm": NaN,
|
| 1018 |
+
"learning_rate": 4.392849426483274e-05,
|
| 1019 |
+
"loss": 0.0,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.011981858453749604,
|
| 1024 |
+
"grad_norm": NaN,
|
| 1025 |
+
"learning_rate": 4.256713373170564e-05,
|
| 1026 |
+
"loss": 0.0,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.012066237738635166,
|
| 1031 |
+
"grad_norm": NaN,
|
| 1032 |
+
"learning_rate": 4.12214747707527e-05,
|
| 1033 |
+
"loss": 0.0,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.012150617023520726,
|
| 1038 |
+
"grad_norm": NaN,
|
| 1039 |
+
"learning_rate": 3.9891885271697496e-05,
|
| 1040 |
+
"loss": 0.0,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.012234996308406286,
|
| 1045 |
+
"grad_norm": NaN,
|
| 1046 |
+
"learning_rate": 3.857872873103322e-05,
|
| 1047 |
+
"loss": 4.1448,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.012319375593291847,
|
| 1052 |
+
"grad_norm": NaN,
|
| 1053 |
+
"learning_rate": 3.7282364152646297e-05,
|
| 1054 |
+
"loss": 0.0,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.012403754878177407,
|
| 1059 |
+
"grad_norm": NaN,
|
| 1060 |
+
"learning_rate": 3.600314594966834e-05,
|
| 1061 |
+
"loss": 0.0,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.012488134163062967,
|
| 1066 |
+
"grad_norm": NaN,
|
| 1067 |
+
"learning_rate": 3.4741423847583134e-05,
|
| 1068 |
+
"loss": 0.0,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.01257251344794853,
|
| 1073 |
+
"grad_norm": NaN,
|
| 1074 |
+
"learning_rate": 3.349754278861517e-05,
|
| 1075 |
+
"loss": 0.0,
|
| 1076 |
+
"step": 149
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.01265689273283409,
|
| 1080 |
+
"grad_norm": NaN,
|
| 1081 |
+
"learning_rate": 3.227184283742591e-05,
|
| 1082 |
+
"loss": 0.0,
|
| 1083 |
+
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.01265689273283409,
|
| 1087 |
+
"eval_loss": NaN,
|
| 1088 |
+
"eval_runtime": 148.9295,
|
| 1089 |
+
"eval_samples_per_second": 33.506,
|
| 1090 |
+
"eval_steps_per_second": 16.753,
|
| 1091 |
+
"step": 150
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
|
|
| 1108 |
"attributes": {}
|
| 1109 |
}
|
| 1110 |
},
|
| 1111 |
+
"total_flos": 2.540848817582899e+16,
|
| 1112 |
"train_batch_size": 2,
|
| 1113 |
"trial_name": null,
|
| 1114 |
"trial_params": null
|