Training in progress, step 4000, checkpoint
Browse files
last-checkpoint/model-00001-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4993448880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0dc78eb3736d5a634642f33b04366ae8bc82d44f79e35262912a8f79a297da9
|
| 3 |
size 4993448880
|
last-checkpoint/model-00002-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1180663192
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8dd0b804f4d8175687f3626e929c7766181c67e2d08bc33bc20168248f4a9ba9
|
| 3 |
size 1180663192
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3095446256
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b9a68cbcd5de279cabaa6560612707ffd9ca1a64ece09207391eab36fc73a58
|
| 3 |
size 3095446256
|
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 sha256:4b7b6ce3ff2951e767c721be76510187471b655709a639fc1d52c719fdc5af80
|
| 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 sha256:34d49fca63da670319ba76874c77a485016cecfb604305dc12d82741a53f00d7
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 38.
|
| 3 |
-
"best_model_checkpoint": "warmestman/whisper-large-v3-mn-cv-fleurs/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 1000,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -754,6 +754,255 @@
|
|
| 754 |
"eval_steps_per_second": 0.092,
|
| 755 |
"eval_wer": 38.54023431054397,
|
| 756 |
"step": 3000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 757 |
}
|
| 758 |
],
|
| 759 |
"logging_steps": 25,
|
|
@@ -761,7 +1010,7 @@
|
|
| 761 |
"num_input_tokens_seen": 0,
|
| 762 |
"num_train_epochs": 60,
|
| 763 |
"save_steps": 1000,
|
| 764 |
-
"total_flos":
|
| 765 |
"train_batch_size": 16,
|
| 766 |
"trial_name": null,
|
| 767 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 38.127715747208626,
|
| 3 |
+
"best_model_checkpoint": "warmestman/whisper-large-v3-mn-cv-fleurs/checkpoint-4000",
|
| 4 |
+
"epoch": 23.952095808383234,
|
| 5 |
"eval_steps": 1000,
|
| 6 |
+
"global_step": 4000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 754 |
"eval_steps_per_second": 0.092,
|
| 755 |
"eval_wer": 38.54023431054397,
|
| 756 |
"step": 3000
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 18.11,
|
| 760 |
+
"learning_rate": 7.342105263157895e-05,
|
| 761 |
+
"loss": 0.0094,
|
| 762 |
+
"step": 3025
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 18.26,
|
| 766 |
+
"learning_rate": 7.315789473684212e-05,
|
| 767 |
+
"loss": 0.0085,
|
| 768 |
+
"step": 3050
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 18.41,
|
| 772 |
+
"learning_rate": 7.289473684210527e-05,
|
| 773 |
+
"loss": 0.0089,
|
| 774 |
+
"step": 3075
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 18.56,
|
| 778 |
+
"learning_rate": 7.263157894736843e-05,
|
| 779 |
+
"loss": 0.0101,
|
| 780 |
+
"step": 3100
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 18.71,
|
| 784 |
+
"learning_rate": 7.236842105263159e-05,
|
| 785 |
+
"loss": 0.0091,
|
| 786 |
+
"step": 3125
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 18.86,
|
| 790 |
+
"learning_rate": 7.210526315789474e-05,
|
| 791 |
+
"loss": 0.0106,
|
| 792 |
+
"step": 3150
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 19.01,
|
| 796 |
+
"learning_rate": 7.18421052631579e-05,
|
| 797 |
+
"loss": 0.01,
|
| 798 |
+
"step": 3175
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 19.16,
|
| 802 |
+
"learning_rate": 7.157894736842105e-05,
|
| 803 |
+
"loss": 0.0067,
|
| 804 |
+
"step": 3200
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 19.31,
|
| 808 |
+
"learning_rate": 7.131578947368421e-05,
|
| 809 |
+
"loss": 0.0077,
|
| 810 |
+
"step": 3225
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 19.46,
|
| 814 |
+
"learning_rate": 7.105263157894737e-05,
|
| 815 |
+
"loss": 0.0072,
|
| 816 |
+
"step": 3250
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 19.61,
|
| 820 |
+
"learning_rate": 7.078947368421052e-05,
|
| 821 |
+
"loss": 0.0066,
|
| 822 |
+
"step": 3275
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 19.76,
|
| 826 |
+
"learning_rate": 7.052631578947368e-05,
|
| 827 |
+
"loss": 0.0073,
|
| 828 |
+
"step": 3300
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 19.91,
|
| 832 |
+
"learning_rate": 7.026315789473684e-05,
|
| 833 |
+
"loss": 0.0079,
|
| 834 |
+
"step": 3325
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 20.06,
|
| 838 |
+
"learning_rate": 7e-05,
|
| 839 |
+
"loss": 0.0101,
|
| 840 |
+
"step": 3350
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 20.21,
|
| 844 |
+
"learning_rate": 6.973684210526315e-05,
|
| 845 |
+
"loss": 0.0075,
|
| 846 |
+
"step": 3375
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 20.36,
|
| 850 |
+
"learning_rate": 6.947368421052632e-05,
|
| 851 |
+
"loss": 0.0096,
|
| 852 |
+
"step": 3400
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 20.51,
|
| 856 |
+
"learning_rate": 6.921052631578948e-05,
|
| 857 |
+
"loss": 0.0095,
|
| 858 |
+
"step": 3425
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 20.66,
|
| 862 |
+
"learning_rate": 6.894736842105263e-05,
|
| 863 |
+
"loss": 0.0105,
|
| 864 |
+
"step": 3450
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 20.81,
|
| 868 |
+
"learning_rate": 6.868421052631579e-05,
|
| 869 |
+
"loss": 0.0112,
|
| 870 |
+
"step": 3475
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 20.96,
|
| 874 |
+
"learning_rate": 6.842105263157895e-05,
|
| 875 |
+
"loss": 0.0116,
|
| 876 |
+
"step": 3500
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 21.11,
|
| 880 |
+
"learning_rate": 6.81578947368421e-05,
|
| 881 |
+
"loss": 0.0088,
|
| 882 |
+
"step": 3525
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 21.26,
|
| 886 |
+
"learning_rate": 6.789473684210527e-05,
|
| 887 |
+
"loss": 0.01,
|
| 888 |
+
"step": 3550
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 21.41,
|
| 892 |
+
"learning_rate": 6.763157894736843e-05,
|
| 893 |
+
"loss": 0.01,
|
| 894 |
+
"step": 3575
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 21.56,
|
| 898 |
+
"learning_rate": 6.736842105263159e-05,
|
| 899 |
+
"loss": 0.0083,
|
| 900 |
+
"step": 3600
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 21.71,
|
| 904 |
+
"learning_rate": 6.710526315789474e-05,
|
| 905 |
+
"loss": 0.0088,
|
| 906 |
+
"step": 3625
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 21.86,
|
| 910 |
+
"learning_rate": 6.68421052631579e-05,
|
| 911 |
+
"loss": 0.0086,
|
| 912 |
+
"step": 3650
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 22.01,
|
| 916 |
+
"learning_rate": 6.657894736842106e-05,
|
| 917 |
+
"loss": 0.0078,
|
| 918 |
+
"step": 3675
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 22.16,
|
| 922 |
+
"learning_rate": 6.631578947368421e-05,
|
| 923 |
+
"loss": 0.0061,
|
| 924 |
+
"step": 3700
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 22.31,
|
| 928 |
+
"learning_rate": 6.605263157894738e-05,
|
| 929 |
+
"loss": 0.0073,
|
| 930 |
+
"step": 3725
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 22.46,
|
| 934 |
+
"learning_rate": 6.578947368421054e-05,
|
| 935 |
+
"loss": 0.0071,
|
| 936 |
+
"step": 3750
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 22.6,
|
| 940 |
+
"learning_rate": 6.55263157894737e-05,
|
| 941 |
+
"loss": 0.0085,
|
| 942 |
+
"step": 3775
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 22.75,
|
| 946 |
+
"learning_rate": 6.526315789473685e-05,
|
| 947 |
+
"loss": 0.0082,
|
| 948 |
+
"step": 3800
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 22.9,
|
| 952 |
+
"learning_rate": 6.500000000000001e-05,
|
| 953 |
+
"loss": 0.0098,
|
| 954 |
+
"step": 3825
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 23.05,
|
| 958 |
+
"learning_rate": 6.473684210526316e-05,
|
| 959 |
+
"loss": 0.0087,
|
| 960 |
+
"step": 3850
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 23.2,
|
| 964 |
+
"learning_rate": 6.447368421052632e-05,
|
| 965 |
+
"loss": 0.0087,
|
| 966 |
+
"step": 3875
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 23.35,
|
| 970 |
+
"learning_rate": 6.421052631578948e-05,
|
| 971 |
+
"loss": 0.0076,
|
| 972 |
+
"step": 3900
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 23.5,
|
| 976 |
+
"learning_rate": 6.394736842105263e-05,
|
| 977 |
+
"loss": 0.0077,
|
| 978 |
+
"step": 3925
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 23.65,
|
| 982 |
+
"learning_rate": 6.368421052631579e-05,
|
| 983 |
+
"loss": 0.0081,
|
| 984 |
+
"step": 3950
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 23.8,
|
| 988 |
+
"learning_rate": 6.342105263157895e-05,
|
| 989 |
+
"loss": 0.0083,
|
| 990 |
+
"step": 3975
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 23.95,
|
| 994 |
+
"learning_rate": 6.31578947368421e-05,
|
| 995 |
+
"loss": 0.0091,
|
| 996 |
+
"step": 4000
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 23.95,
|
| 1000 |
+
"eval_loss": 0.5618667602539062,
|
| 1001 |
+
"eval_runtime": 582.8261,
|
| 1002 |
+
"eval_samples_per_second": 0.719,
|
| 1003 |
+
"eval_steps_per_second": 0.091,
|
| 1004 |
+
"eval_wer": 38.127715747208626,
|
| 1005 |
+
"step": 4000
|
| 1006 |
}
|
| 1007 |
],
|
| 1008 |
"logging_steps": 25,
|
|
|
|
| 1010 |
"num_input_tokens_seen": 0,
|
| 1011 |
"num_train_epochs": 60,
|
| 1012 |
"save_steps": 1000,
|
| 1013 |
+
"total_flos": 2.1720546423668736e+20,
|
| 1014 |
"train_batch_size": 16,
|
| 1015 |
"trial_name": null,
|
| 1016 |
"trial_params": null
|