Commit
•
157cd14
1
Parent(s):
214ecc9
Training in progress, step 4000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +2 -2
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +252 -3
- pytorch_model.bin +1 -1
- runs/Apr09_14-45-21_gpu07.cyverse.org/events.out.tfevents.1681076808.gpu07.cyverse.org.48142.0 +2 -2
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2524414853
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27258b0c1d06a9b5e61d8f927d63726deb3b0f232f363bb381e6603a2e047efd
|
| 3 |
size 2524414853
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262229869
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb9bb8d82c12f7963f345a3bc44171138b5cd9c15813fe124d03c8957cb8aa3d
|
| 3 |
size 1262229869
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc101980f72fb94e34cbe7f2fcca59c7772750d7ccf19bcd551759aee050f696
|
| 3 |
+
size 14639
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4eb4748670085a8091d197542279b737c13c5a3f63f48bc90750499483c77941
|
| 3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.0693531029534856,
|
| 3 |
"best_model_checkpoint": "./wav2vec2-xls-r-300m-ar/checkpoint-3000",
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -753,11 +753,260 @@
|
|
| 753 |
"eval_steps_per_second": 1.197,
|
| 754 |
"eval_wer": 0.0693531029534856,
|
| 755 |
"step": 3000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 756 |
}
|
| 757 |
],
|
| 758 |
"max_steps": 10000,
|
| 759 |
"num_train_epochs": 89,
|
| 760 |
-
"total_flos": 1.
|
| 761 |
"trial_name": null,
|
| 762 |
"trial_params": null
|
| 763 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.0693531029534856,
|
| 3 |
"best_model_checkpoint": "./wav2vec2-xls-r-300m-ar/checkpoint-3000",
|
| 4 |
+
"epoch": 35.39823008849557,
|
| 5 |
+
"global_step": 4000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 753 |
"eval_steps_per_second": 1.197,
|
| 754 |
"eval_wer": 0.0693531029534856,
|
| 755 |
"step": 3000
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 26.77,
|
| 759 |
+
"learning_rate": 0.0002202631578947368,
|
| 760 |
+
"loss": 0.0238,
|
| 761 |
+
"step": 3025
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 26.99,
|
| 765 |
+
"learning_rate": 0.00021947368421052632,
|
| 766 |
+
"loss": 0.0226,
|
| 767 |
+
"step": 3050
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 27.21,
|
| 771 |
+
"learning_rate": 0.00021868421052631578,
|
| 772 |
+
"loss": 0.0255,
|
| 773 |
+
"step": 3075
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 27.43,
|
| 777 |
+
"learning_rate": 0.00021789473684210526,
|
| 778 |
+
"loss": 0.0326,
|
| 779 |
+
"step": 3100
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 27.65,
|
| 783 |
+
"learning_rate": 0.00021710526315789472,
|
| 784 |
+
"loss": 0.0629,
|
| 785 |
+
"step": 3125
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 27.88,
|
| 789 |
+
"learning_rate": 0.0002163157894736842,
|
| 790 |
+
"loss": 0.0348,
|
| 791 |
+
"step": 3150
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 28.1,
|
| 795 |
+
"learning_rate": 0.00021552631578947368,
|
| 796 |
+
"loss": 0.0311,
|
| 797 |
+
"step": 3175
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 28.32,
|
| 801 |
+
"learning_rate": 0.00021473684210526314,
|
| 802 |
+
"loss": 0.023,
|
| 803 |
+
"step": 3200
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 28.54,
|
| 807 |
+
"learning_rate": 0.00021394736842105262,
|
| 808 |
+
"loss": 0.0214,
|
| 809 |
+
"step": 3225
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 28.76,
|
| 813 |
+
"learning_rate": 0.00021315789473684208,
|
| 814 |
+
"loss": 0.0201,
|
| 815 |
+
"step": 3250
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 28.98,
|
| 819 |
+
"learning_rate": 0.00021236842105263156,
|
| 820 |
+
"loss": 0.0202,
|
| 821 |
+
"step": 3275
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 29.2,
|
| 825 |
+
"learning_rate": 0.00021157894736842102,
|
| 826 |
+
"loss": 0.0231,
|
| 827 |
+
"step": 3300
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 29.42,
|
| 831 |
+
"learning_rate": 0.0002107894736842105,
|
| 832 |
+
"loss": 0.0291,
|
| 833 |
+
"step": 3325
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 29.65,
|
| 837 |
+
"learning_rate": 0.00020999999999999998,
|
| 838 |
+
"loss": 0.0241,
|
| 839 |
+
"step": 3350
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 29.87,
|
| 843 |
+
"learning_rate": 0.00020921052631578944,
|
| 844 |
+
"loss": 0.0261,
|
| 845 |
+
"step": 3375
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 30.09,
|
| 849 |
+
"learning_rate": 0.00020842105263157895,
|
| 850 |
+
"loss": 0.0281,
|
| 851 |
+
"step": 3400
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 30.31,
|
| 855 |
+
"learning_rate": 0.0002076315789473684,
|
| 856 |
+
"loss": 0.0237,
|
| 857 |
+
"step": 3425
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 30.53,
|
| 861 |
+
"learning_rate": 0.0002068421052631579,
|
| 862 |
+
"loss": 0.0199,
|
| 863 |
+
"step": 3450
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 30.75,
|
| 867 |
+
"learning_rate": 0.00020605263157894737,
|
| 868 |
+
"loss": 0.0199,
|
| 869 |
+
"step": 3475
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 30.97,
|
| 873 |
+
"learning_rate": 0.00020526315789473683,
|
| 874 |
+
"loss": 0.0207,
|
| 875 |
+
"step": 3500
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 31.19,
|
| 879 |
+
"learning_rate": 0.0002044736842105263,
|
| 880 |
+
"loss": 0.0221,
|
| 881 |
+
"step": 3525
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 31.42,
|
| 885 |
+
"learning_rate": 0.00020368421052631576,
|
| 886 |
+
"loss": 0.0234,
|
| 887 |
+
"step": 3550
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 31.64,
|
| 891 |
+
"learning_rate": 0.00020289473684210525,
|
| 892 |
+
"loss": 0.025,
|
| 893 |
+
"step": 3575
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 31.86,
|
| 897 |
+
"learning_rate": 0.0002021052631578947,
|
| 898 |
+
"loss": 0.0251,
|
| 899 |
+
"step": 3600
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 32.08,
|
| 903 |
+
"learning_rate": 0.0002013157894736842,
|
| 904 |
+
"loss": 0.0232,
|
| 905 |
+
"step": 3625
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 32.3,
|
| 909 |
+
"learning_rate": 0.00020052631578947367,
|
| 910 |
+
"loss": 0.0215,
|
| 911 |
+
"step": 3650
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 32.52,
|
| 915 |
+
"learning_rate": 0.00019973684210526313,
|
| 916 |
+
"loss": 0.019,
|
| 917 |
+
"step": 3675
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 32.74,
|
| 921 |
+
"learning_rate": 0.0001989473684210526,
|
| 922 |
+
"loss": 0.0215,
|
| 923 |
+
"step": 3700
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 32.96,
|
| 927 |
+
"learning_rate": 0.0001981578947368421,
|
| 928 |
+
"loss": 0.0209,
|
| 929 |
+
"step": 3725
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 33.19,
|
| 933 |
+
"learning_rate": 0.00019736842105263157,
|
| 934 |
+
"loss": 0.0258,
|
| 935 |
+
"step": 3750
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 33.41,
|
| 939 |
+
"learning_rate": 0.00019657894736842106,
|
| 940 |
+
"loss": 0.0206,
|
| 941 |
+
"step": 3775
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 33.63,
|
| 945 |
+
"learning_rate": 0.0001957894736842105,
|
| 946 |
+
"loss": 0.019,
|
| 947 |
+
"step": 3800
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 33.85,
|
| 951 |
+
"learning_rate": 0.000195,
|
| 952 |
+
"loss": 0.0205,
|
| 953 |
+
"step": 3825
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 34.07,
|
| 957 |
+
"learning_rate": 0.00019421052631578945,
|
| 958 |
+
"loss": 0.0243,
|
| 959 |
+
"step": 3850
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 34.29,
|
| 963 |
+
"learning_rate": 0.00019342105263157894,
|
| 964 |
+
"loss": 0.0166,
|
| 965 |
+
"step": 3875
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 34.51,
|
| 969 |
+
"learning_rate": 0.0001926315789473684,
|
| 970 |
+
"loss": 0.0159,
|
| 971 |
+
"step": 3900
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 34.73,
|
| 975 |
+
"learning_rate": 0.00019184210526315787,
|
| 976 |
+
"loss": 0.0194,
|
| 977 |
+
"step": 3925
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 34.96,
|
| 981 |
+
"learning_rate": 0.00019105263157894736,
|
| 982 |
+
"loss": 0.0207,
|
| 983 |
+
"step": 3950
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 35.18,
|
| 987 |
+
"learning_rate": 0.0001902631578947368,
|
| 988 |
+
"loss": 0.0212,
|
| 989 |
+
"step": 3975
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 35.4,
|
| 993 |
+
"learning_rate": 0.0001894736842105263,
|
| 994 |
+
"loss": 0.021,
|
| 995 |
+
"step": 4000
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 35.4,
|
| 999 |
+
"eval_loss": 0.26615452766418457,
|
| 1000 |
+
"eval_runtime": 10.7513,
|
| 1001 |
+
"eval_samples_per_second": 9.301,
|
| 1002 |
+
"eval_steps_per_second": 1.209,
|
| 1003 |
+
"eval_wer": 0.07222288652397466,
|
| 1004 |
+
"step": 4000
|
| 1005 |
}
|
| 1006 |
],
|
| 1007 |
"max_steps": 10000,
|
| 1008 |
"num_train_epochs": 89,
|
| 1009 |
+
"total_flos": 1.5768864774399195e+19,
|
| 1010 |
"trial_name": null,
|
| 1011 |
"trial_params": null
|
| 1012 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262229869
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb9bb8d82c12f7963f345a3bc44171138b5cd9c15813fe124d03c8957cb8aa3d
|
| 3 |
size 1262229869
|
runs/Apr09_14-45-21_gpu07.cyverse.org/events.out.tfevents.1681076808.gpu07.cyverse.org.48142.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50fa134d7573be5c46508e873e8bb15f1862c32825a16d7b12c777045dccecb2
|
| 3 |
+
size 31774
|