Upload with huggingface_hub
Browse files- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +253 -3
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 535706209
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48f15460627a73f5a7810580fc1400107c8567b84291d910de6c908e2d0c3061
|
| 3 |
size 535706209
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 267857393
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84c9f4f6379f05b6336b225c87d388cd0859702bb1578ef217f5cbe5a701836b
|
| 3 |
size 267857393
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6434b53c20a9a79004b47b094f4bce06e5cef0e480bad66f94ed659d4db0636
|
| 3 |
size 14503
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d77a8263d2c9ab2d2fd99749ca0bd684b2d23ea39ae6b5deffc35ec07d427d80
|
| 3 |
size 623
|
trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.5875,
|
| 3 |
"best_model_checkpoint": "./results/checkpoint-500",
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -756,11 +756,261 @@
|
|
| 756 |
"eval_steps_per_second": 1.673,
|
| 757 |
"eval_total_time_in_seconds": 13.308728723999593,
|
| 758 |
"step": 3000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 759 |
}
|
| 760 |
],
|
| 761 |
"max_steps": 4000,
|
| 762 |
"num_train_epochs": 20,
|
| 763 |
-
"total_flos":
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|
| 766 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.5875,
|
| 3 |
"best_model_checkpoint": "./results/checkpoint-500",
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"global_step": 4000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 756 |
"eval_steps_per_second": 1.673,
|
| 757 |
"eval_total_time_in_seconds": 13.308728723999593,
|
| 758 |
"step": 3000
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 15.25,
|
| 762 |
+
"eval_accuracy": 0.5875,
|
| 763 |
+
"eval_latency_in_seconds": 0.01662152344999981,
|
| 764 |
+
"eval_loss": 2.6646552085876465,
|
| 765 |
+
"eval_runtime": 29.7986,
|
| 766 |
+
"eval_samples_per_second": 26.847,
|
| 767 |
+
"eval_steps_per_second": 1.678,
|
| 768 |
+
"eval_total_time_in_seconds": 13.29721875999985,
|
| 769 |
+
"step": 3050
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 15.5,
|
| 773 |
+
"eval_accuracy": 0.5875,
|
| 774 |
+
"eval_latency_in_seconds": 0.01662379797125027,
|
| 775 |
+
"eval_loss": 2.743170738220215,
|
| 776 |
+
"eval_runtime": 29.9125,
|
| 777 |
+
"eval_samples_per_second": 26.745,
|
| 778 |
+
"eval_steps_per_second": 1.672,
|
| 779 |
+
"eval_total_time_in_seconds": 13.299038377000215,
|
| 780 |
+
"step": 3100
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 15.75,
|
| 784 |
+
"eval_accuracy": 0.5875,
|
| 785 |
+
"eval_latency_in_seconds": 0.01665628889874938,
|
| 786 |
+
"eval_loss": 2.7203001976013184,
|
| 787 |
+
"eval_runtime": 29.9599,
|
| 788 |
+
"eval_samples_per_second": 26.702,
|
| 789 |
+
"eval_steps_per_second": 1.669,
|
| 790 |
+
"eval_total_time_in_seconds": 13.325031118999505,
|
| 791 |
+
"step": 3150
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 16.0,
|
| 795 |
+
"learning_rate": 4.000000000000001e-06,
|
| 796 |
+
"loss": 0.0063,
|
| 797 |
+
"step": 3200
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 16.0,
|
| 801 |
+
"eval_accuracy": 0.5875,
|
| 802 |
+
"eval_latency_in_seconds": 0.016667092492499477,
|
| 803 |
+
"eval_loss": 2.742436408996582,
|
| 804 |
+
"eval_runtime": 29.9228,
|
| 805 |
+
"eval_samples_per_second": 26.735,
|
| 806 |
+
"eval_steps_per_second": 1.671,
|
| 807 |
+
"eval_total_time_in_seconds": 13.333673993999582,
|
| 808 |
+
"step": 3200
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 16.25,
|
| 812 |
+
"eval_accuracy": 0.5875,
|
| 813 |
+
"eval_latency_in_seconds": 0.01662819170624971,
|
| 814 |
+
"eval_loss": 2.707371711730957,
|
| 815 |
+
"eval_runtime": 29.8589,
|
| 816 |
+
"eval_samples_per_second": 26.793,
|
| 817 |
+
"eval_steps_per_second": 1.675,
|
| 818 |
+
"eval_total_time_in_seconds": 13.302553364999767,
|
| 819 |
+
"step": 3250
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 16.5,
|
| 823 |
+
"eval_accuracy": 0.5875,
|
| 824 |
+
"eval_latency_in_seconds": 0.01665227038250009,
|
| 825 |
+
"eval_loss": 2.725658655166626,
|
| 826 |
+
"eval_runtime": 29.9363,
|
| 827 |
+
"eval_samples_per_second": 26.723,
|
| 828 |
+
"eval_steps_per_second": 1.67,
|
| 829 |
+
"eval_total_time_in_seconds": 13.321816306000073,
|
| 830 |
+
"step": 3300
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 16.75,
|
| 834 |
+
"eval_accuracy": 0.5875,
|
| 835 |
+
"eval_latency_in_seconds": 0.016652315160000625,
|
| 836 |
+
"eval_loss": 2.734884738922119,
|
| 837 |
+
"eval_runtime": 29.9186,
|
| 838 |
+
"eval_samples_per_second": 26.739,
|
| 839 |
+
"eval_steps_per_second": 1.671,
|
| 840 |
+
"eval_total_time_in_seconds": 13.3218521280005,
|
| 841 |
+
"step": 3350
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 17.0,
|
| 845 |
+
"learning_rate": 3e-06,
|
| 846 |
+
"loss": 0.0051,
|
| 847 |
+
"step": 3400
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 17.0,
|
| 851 |
+
"eval_accuracy": 0.5875,
|
| 852 |
+
"eval_latency_in_seconds": 0.016673584761250596,
|
| 853 |
+
"eval_loss": 2.7681331634521484,
|
| 854 |
+
"eval_runtime": 29.9551,
|
| 855 |
+
"eval_samples_per_second": 26.707,
|
| 856 |
+
"eval_steps_per_second": 1.669,
|
| 857 |
+
"eval_total_time_in_seconds": 13.338867809000476,
|
| 858 |
+
"step": 3400
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 17.25,
|
| 862 |
+
"eval_accuracy": 0.5875,
|
| 863 |
+
"eval_latency_in_seconds": 0.016725112717500677,
|
| 864 |
+
"eval_loss": 2.771609306335449,
|
| 865 |
+
"eval_runtime": 30.0889,
|
| 866 |
+
"eval_samples_per_second": 26.588,
|
| 867 |
+
"eval_steps_per_second": 1.662,
|
| 868 |
+
"eval_total_time_in_seconds": 13.380090174000543,
|
| 869 |
+
"step": 3450
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 17.5,
|
| 873 |
+
"eval_accuracy": 0.5875,
|
| 874 |
+
"eval_latency_in_seconds": 0.016649682186249494,
|
| 875 |
+
"eval_loss": 2.784963369369507,
|
| 876 |
+
"eval_runtime": 29.8969,
|
| 877 |
+
"eval_samples_per_second": 26.759,
|
| 878 |
+
"eval_steps_per_second": 1.672,
|
| 879 |
+
"eval_total_time_in_seconds": 13.319745748999594,
|
| 880 |
+
"step": 3500
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 17.75,
|
| 884 |
+
"eval_accuracy": 0.5875,
|
| 885 |
+
"eval_latency_in_seconds": 0.016661749145000612,
|
| 886 |
+
"eval_loss": 2.8149163722991943,
|
| 887 |
+
"eval_runtime": 29.9288,
|
| 888 |
+
"eval_samples_per_second": 26.73,
|
| 889 |
+
"eval_steps_per_second": 1.671,
|
| 890 |
+
"eval_total_time_in_seconds": 13.32939931600049,
|
| 891 |
+
"step": 3550
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 18.0,
|
| 895 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 896 |
+
"loss": 0.009,
|
| 897 |
+
"step": 3600
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 18.0,
|
| 901 |
+
"eval_accuracy": 0.5875,
|
| 902 |
+
"eval_latency_in_seconds": 0.01670996660875062,
|
| 903 |
+
"eval_loss": 2.823868989944458,
|
| 904 |
+
"eval_runtime": 30.0163,
|
| 905 |
+
"eval_samples_per_second": 26.652,
|
| 906 |
+
"eval_steps_per_second": 1.666,
|
| 907 |
+
"eval_total_time_in_seconds": 13.367973287000495,
|
| 908 |
+
"step": 3600
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 18.25,
|
| 912 |
+
"eval_accuracy": 0.5875,
|
| 913 |
+
"eval_latency_in_seconds": 0.01669507317250009,
|
| 914 |
+
"eval_loss": 2.8000104427337646,
|
| 915 |
+
"eval_runtime": 29.9679,
|
| 916 |
+
"eval_samples_per_second": 26.695,
|
| 917 |
+
"eval_steps_per_second": 1.668,
|
| 918 |
+
"eval_total_time_in_seconds": 13.35605853800007,
|
| 919 |
+
"step": 3650
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 18.5,
|
| 923 |
+
"eval_accuracy": 0.5875,
|
| 924 |
+
"eval_latency_in_seconds": 0.01666891421250057,
|
| 925 |
+
"eval_loss": 2.8489391803741455,
|
| 926 |
+
"eval_runtime": 30.0714,
|
| 927 |
+
"eval_samples_per_second": 26.603,
|
| 928 |
+
"eval_steps_per_second": 1.663,
|
| 929 |
+
"eval_total_time_in_seconds": 13.335131370000454,
|
| 930 |
+
"step": 3700
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 18.75,
|
| 934 |
+
"eval_accuracy": 0.5875,
|
| 935 |
+
"eval_latency_in_seconds": 0.016747756885000624,
|
| 936 |
+
"eval_loss": 2.8278234004974365,
|
| 937 |
+
"eval_runtime": 30.1511,
|
| 938 |
+
"eval_samples_per_second": 26.533,
|
| 939 |
+
"eval_steps_per_second": 1.658,
|
| 940 |
+
"eval_total_time_in_seconds": 13.398205508000501,
|
| 941 |
+
"step": 3750
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 19.0,
|
| 945 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 946 |
+
"loss": 0.0058,
|
| 947 |
+
"step": 3800
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 19.0,
|
| 951 |
+
"eval_accuracy": 0.5875,
|
| 952 |
+
"eval_latency_in_seconds": 0.016664527845000523,
|
| 953 |
+
"eval_loss": 2.8291778564453125,
|
| 954 |
+
"eval_runtime": 29.9616,
|
| 955 |
+
"eval_samples_per_second": 26.701,
|
| 956 |
+
"eval_steps_per_second": 1.669,
|
| 957 |
+
"eval_total_time_in_seconds": 13.331622276000417,
|
| 958 |
+
"step": 3800
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 19.25,
|
| 962 |
+
"eval_accuracy": 0.5875,
|
| 963 |
+
"eval_latency_in_seconds": 0.0166671570925007,
|
| 964 |
+
"eval_loss": 2.848686456680298,
|
| 965 |
+
"eval_runtime": 29.9999,
|
| 966 |
+
"eval_samples_per_second": 26.667,
|
| 967 |
+
"eval_steps_per_second": 1.667,
|
| 968 |
+
"eval_total_time_in_seconds": 13.333725674000561,
|
| 969 |
+
"step": 3850
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 19.5,
|
| 973 |
+
"eval_accuracy": 0.5875,
|
| 974 |
+
"eval_latency_in_seconds": 0.016675078326250058,
|
| 975 |
+
"eval_loss": 2.8558411598205566,
|
| 976 |
+
"eval_runtime": 30.0771,
|
| 977 |
+
"eval_samples_per_second": 26.598,
|
| 978 |
+
"eval_steps_per_second": 1.662,
|
| 979 |
+
"eval_total_time_in_seconds": 13.340062661000047,
|
| 980 |
+
"step": 3900
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 19.75,
|
| 984 |
+
"eval_accuracy": 0.5875,
|
| 985 |
+
"eval_latency_in_seconds": 0.016670747563749727,
|
| 986 |
+
"eval_loss": 2.8526947498321533,
|
| 987 |
+
"eval_runtime": 30.0232,
|
| 988 |
+
"eval_samples_per_second": 26.646,
|
| 989 |
+
"eval_steps_per_second": 1.665,
|
| 990 |
+
"eval_total_time_in_seconds": 13.336598050999783,
|
| 991 |
+
"step": 3950
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 20.0,
|
| 995 |
+
"learning_rate": 0.0,
|
| 996 |
+
"loss": 0.0043,
|
| 997 |
+
"step": 4000
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 20.0,
|
| 1001 |
+
"eval_accuracy": 0.5875,
|
| 1002 |
+
"eval_latency_in_seconds": 0.0166365546787506,
|
| 1003 |
+
"eval_loss": 2.8533031940460205,
|
| 1004 |
+
"eval_runtime": 29.9376,
|
| 1005 |
+
"eval_samples_per_second": 26.722,
|
| 1006 |
+
"eval_steps_per_second": 1.67,
|
| 1007 |
+
"eval_total_time_in_seconds": 13.30924374300048,
|
| 1008 |
+
"step": 4000
|
| 1009 |
}
|
| 1010 |
],
|
| 1011 |
"max_steps": 4000,
|
| 1012 |
"num_train_epochs": 20,
|
| 1013 |
+
"total_flos": 8478064705536000.0,
|
| 1014 |
"trial_name": null,
|
| 1015 |
"trial_params": null
|
| 1016 |
}
|