Commit
•
8139f4e
1
Parent(s):
f97408c
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 +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +255 -5
- pytorch_model.bin +1 -1
- runs/Aug17_16-46-37_8582233f681d/events.out.tfevents.1692290809.8582233f681d.216.0 +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 1934161157
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5948a7ee44e31ea06a7e61c4b6e04d8656f582d82f6fb80834e5461835499046
|
| 3 |
size 1934161157
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 967102729
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4b876019bf694adee9c9238f3e1357059ae51ca004fd16638879e785129283b
|
| 3 |
size 967102729
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fea25640b33473c2c750c09b44cf70fb34a378c8114c19ff3af953a9b65fac26
|
| 3 |
size 14575
|
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 sha256:3be3e16e7a5628d50352078d8c3f4228325e660ea5cf0f4ec5b03b9a13573f4c
|
| 3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint": "./whisper-vietnamese-3/checkpoint-
|
| 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": 0.122,
|
| 757 |
"eval_wer": 109.13163064833007,
|
| 758 |
"step": 3000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 759 |
}
|
| 760 |
],
|
| 761 |
"max_steps": 4000,
|
| 762 |
"num_train_epochs": 29,
|
| 763 |
-
"total_flos": 1.
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|
| 766 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 104.12573673870334,
|
| 3 |
+
"best_model_checkpoint": "./whisper-vietnamese-3/checkpoint-4000",
|
| 4 |
+
"epoch": 28.776978417266186,
|
| 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": 0.122,
|
| 757 |
"eval_wer": 109.13163064833007,
|
| 758 |
"step": 3000
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 21.76,
|
| 762 |
+
"learning_rate": 2.7914285714285716e-06,
|
| 763 |
+
"loss": 0.0007,
|
| 764 |
+
"step": 3025
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 21.94,
|
| 768 |
+
"learning_rate": 2.7200000000000002e-06,
|
| 769 |
+
"loss": 0.0008,
|
| 770 |
+
"step": 3050
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 22.12,
|
| 774 |
+
"learning_rate": 2.648571428571429e-06,
|
| 775 |
+
"loss": 0.0008,
|
| 776 |
+
"step": 3075
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 22.3,
|
| 780 |
+
"learning_rate": 2.5771428571428574e-06,
|
| 781 |
+
"loss": 0.0008,
|
| 782 |
+
"step": 3100
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 22.48,
|
| 786 |
+
"learning_rate": 2.5057142857142856e-06,
|
| 787 |
+
"loss": 0.0007,
|
| 788 |
+
"step": 3125
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 22.66,
|
| 792 |
+
"learning_rate": 2.4342857142857146e-06,
|
| 793 |
+
"loss": 0.0007,
|
| 794 |
+
"step": 3150
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 22.84,
|
| 798 |
+
"learning_rate": 2.362857142857143e-06,
|
| 799 |
+
"loss": 0.0007,
|
| 800 |
+
"step": 3175
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 23.02,
|
| 804 |
+
"learning_rate": 2.2914285714285718e-06,
|
| 805 |
+
"loss": 0.0008,
|
| 806 |
+
"step": 3200
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 23.2,
|
| 810 |
+
"learning_rate": 2.2200000000000003e-06,
|
| 811 |
+
"loss": 0.0007,
|
| 812 |
+
"step": 3225
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 23.38,
|
| 816 |
+
"learning_rate": 2.148571428571429e-06,
|
| 817 |
+
"loss": 0.0007,
|
| 818 |
+
"step": 3250
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 23.56,
|
| 822 |
+
"learning_rate": 2.077142857142857e-06,
|
| 823 |
+
"loss": 0.0007,
|
| 824 |
+
"step": 3275
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 23.74,
|
| 828 |
+
"learning_rate": 2.0057142857142857e-06,
|
| 829 |
+
"loss": 0.0007,
|
| 830 |
+
"step": 3300
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 23.92,
|
| 834 |
+
"learning_rate": 1.9342857142857143e-06,
|
| 835 |
+
"loss": 0.0007,
|
| 836 |
+
"step": 3325
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 24.1,
|
| 840 |
+
"learning_rate": 1.8628571428571429e-06,
|
| 841 |
+
"loss": 0.0007,
|
| 842 |
+
"step": 3350
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 24.28,
|
| 846 |
+
"learning_rate": 1.7914285714285715e-06,
|
| 847 |
+
"loss": 0.0007,
|
| 848 |
+
"step": 3375
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 24.46,
|
| 852 |
+
"learning_rate": 1.72e-06,
|
| 853 |
+
"loss": 0.0006,
|
| 854 |
+
"step": 3400
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 24.64,
|
| 858 |
+
"learning_rate": 1.6485714285714289e-06,
|
| 859 |
+
"loss": 0.0006,
|
| 860 |
+
"step": 3425
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 24.82,
|
| 864 |
+
"learning_rate": 1.5771428571428574e-06,
|
| 865 |
+
"loss": 0.0006,
|
| 866 |
+
"step": 3450
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 25.0,
|
| 870 |
+
"learning_rate": 1.5057142857142858e-06,
|
| 871 |
+
"loss": 0.0006,
|
| 872 |
+
"step": 3475
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 25.18,
|
| 876 |
+
"learning_rate": 1.4342857142857144e-06,
|
| 877 |
+
"loss": 0.0007,
|
| 878 |
+
"step": 3500
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 25.36,
|
| 882 |
+
"learning_rate": 1.362857142857143e-06,
|
| 883 |
+
"loss": 0.0006,
|
| 884 |
+
"step": 3525
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 25.54,
|
| 888 |
+
"learning_rate": 1.2914285714285716e-06,
|
| 889 |
+
"loss": 0.0006,
|
| 890 |
+
"step": 3550
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 25.72,
|
| 894 |
+
"learning_rate": 1.2200000000000002e-06,
|
| 895 |
+
"loss": 0.0006,
|
| 896 |
+
"step": 3575
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 25.9,
|
| 900 |
+
"learning_rate": 1.1485714285714286e-06,
|
| 901 |
+
"loss": 0.0006,
|
| 902 |
+
"step": 3600
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 26.08,
|
| 906 |
+
"learning_rate": 1.0771428571428574e-06,
|
| 907 |
+
"loss": 0.0006,
|
| 908 |
+
"step": 3625
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 26.26,
|
| 912 |
+
"learning_rate": 1.0057142857142857e-06,
|
| 913 |
+
"loss": 0.0006,
|
| 914 |
+
"step": 3650
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 26.44,
|
| 918 |
+
"learning_rate": 9.342857142857144e-07,
|
| 919 |
+
"loss": 0.0006,
|
| 920 |
+
"step": 3675
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 26.62,
|
| 924 |
+
"learning_rate": 8.628571428571429e-07,
|
| 925 |
+
"loss": 0.0006,
|
| 926 |
+
"step": 3700
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 26.8,
|
| 930 |
+
"learning_rate": 7.914285714285715e-07,
|
| 931 |
+
"loss": 0.0006,
|
| 932 |
+
"step": 3725
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 26.98,
|
| 936 |
+
"learning_rate": 7.2e-07,
|
| 937 |
+
"loss": 0.0007,
|
| 938 |
+
"step": 3750
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 27.16,
|
| 942 |
+
"learning_rate": 6.485714285714287e-07,
|
| 943 |
+
"loss": 0.0006,
|
| 944 |
+
"step": 3775
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 27.34,
|
| 948 |
+
"learning_rate": 5.771428571428572e-07,
|
| 949 |
+
"loss": 0.0006,
|
| 950 |
+
"step": 3800
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 27.52,
|
| 954 |
+
"learning_rate": 5.057142857142858e-07,
|
| 955 |
+
"loss": 0.0006,
|
| 956 |
+
"step": 3825
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 27.7,
|
| 960 |
+
"learning_rate": 4.342857142857143e-07,
|
| 961 |
+
"loss": 0.0006,
|
| 962 |
+
"step": 3850
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 27.88,
|
| 966 |
+
"learning_rate": 3.6285714285714283e-07,
|
| 967 |
+
"loss": 0.0006,
|
| 968 |
+
"step": 3875
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 28.06,
|
| 972 |
+
"learning_rate": 2.914285714285715e-07,
|
| 973 |
+
"loss": 0.0006,
|
| 974 |
+
"step": 3900
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 28.24,
|
| 978 |
+
"learning_rate": 2.2e-07,
|
| 979 |
+
"loss": 0.0006,
|
| 980 |
+
"step": 3925
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 28.42,
|
| 984 |
+
"learning_rate": 1.4857142857142857e-07,
|
| 985 |
+
"loss": 0.0006,
|
| 986 |
+
"step": 3950
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 28.6,
|
| 990 |
+
"learning_rate": 7.714285714285715e-08,
|
| 991 |
+
"loss": 0.0006,
|
| 992 |
+
"step": 3975
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 28.78,
|
| 996 |
+
"learning_rate": 5.714285714285715e-09,
|
| 997 |
+
"loss": 0.0006,
|
| 998 |
+
"step": 4000
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 28.78,
|
| 1002 |
+
"eval_cer": 100.82641572223558,
|
| 1003 |
+
"eval_loss": 0.6164063811302185,
|
| 1004 |
+
"eval_runtime": 252.3206,
|
| 1005 |
+
"eval_samples_per_second": 0.979,
|
| 1006 |
+
"eval_steps_per_second": 0.123,
|
| 1007 |
+
"eval_wer": 104.12573673870334,
|
| 1008 |
+
"step": 4000
|
| 1009 |
}
|
| 1010 |
],
|
| 1011 |
"max_steps": 4000,
|
| 1012 |
"num_train_epochs": 29,
|
| 1013 |
+
"total_flos": 1.841290288201728e+19,
|
| 1014 |
"trial_name": null,
|
| 1015 |
"trial_params": null
|
| 1016 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 967102729
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4b876019bf694adee9c9238f3e1357059ae51ca004fd16638879e785129283b
|
| 3 |
size 967102729
|
runs/Aug17_16-46-37_8582233f681d/events.out.tfevents.1692290809.8582233f681d.216.0
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 sha256:888a1289dfa30d5e985b32553043fa759e533438856c0461c16f165bcba19c46
|
| 3 |
+
size 31466
|