Training in progress, step 2900, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 966995080
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4322cb52e7375952b1b7c62f67285f280a31e123ef3ec661fb690ab98ec4501d
|
3 |
size 966995080
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1925064044
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c8b1e94006a0bd0b5433a91a8d0f2efb9acd8c8debe0a4db87187d4f3df0549
|
3 |
size 1925064044
|
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:aabc5988751cca3ac2633ffd4f8fdf9b2babdfb7020d9a25c5dd343ea5e806c4
|
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 sha256:7b8eb592d2fee38e792ebd9f77ad72aad42bb0e171607f9852785836391c11e4
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 70.1955074875208,
|
3 |
"best_model_checkpoint": "./whisper-it/checkpoint-300",
|
4 |
-
"epoch":
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -865,6 +865,105 @@
|
|
865 |
"eval_steps_per_second": 0.103,
|
866 |
"eval_wer": 181.14254021075985,
|
867 |
"step": 2600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
868 |
}
|
869 |
],
|
870 |
"logging_steps": 25,
|
@@ -872,7 +971,7 @@
|
|
872 |
"num_input_tokens_seen": 0,
|
873 |
"num_train_epochs": 8,
|
874 |
"save_steps": 100,
|
875 |
-
"total_flos": 2.
|
876 |
"trial_name": null,
|
877 |
"trial_params": null
|
878 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 70.1955074875208,
|
3 |
"best_model_checkpoint": "./whisper-it/checkpoint-300",
|
4 |
+
"epoch": 5.534351145038168,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 2900,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
865 |
"eval_steps_per_second": 0.103,
|
866 |
"eval_wer": 181.14254021075985,
|
867 |
"step": 2600
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 5.01,
|
871 |
+
"learning_rate": 3.945714285714286e-06,
|
872 |
+
"loss": 0.0156,
|
873 |
+
"step": 2625
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 5.06,
|
877 |
+
"learning_rate": 3.874285714285715e-06,
|
878 |
+
"loss": 0.0086,
|
879 |
+
"step": 2650
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 5.1,
|
883 |
+
"learning_rate": 3.802857142857143e-06,
|
884 |
+
"loss": 0.0075,
|
885 |
+
"step": 2675
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 5.15,
|
889 |
+
"learning_rate": 3.731428571428572e-06,
|
890 |
+
"loss": 0.009,
|
891 |
+
"step": 2700
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 5.15,
|
895 |
+
"eval_loss": 0.43247538805007935,
|
896 |
+
"eval_runtime": 1622.3539,
|
897 |
+
"eval_samples_per_second": 0.925,
|
898 |
+
"eval_steps_per_second": 0.116,
|
899 |
+
"eval_wer": 161.67498613422075,
|
900 |
+
"step": 2700
|
901 |
+
},
|
902 |
+
{
|
903 |
+
"epoch": 5.2,
|
904 |
+
"learning_rate": 3.66e-06,
|
905 |
+
"loss": 0.0074,
|
906 |
+
"step": 2725
|
907 |
+
},
|
908 |
+
{
|
909 |
+
"epoch": 5.25,
|
910 |
+
"learning_rate": 3.588571428571429e-06,
|
911 |
+
"loss": 0.0096,
|
912 |
+
"step": 2750
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 5.3,
|
916 |
+
"learning_rate": 3.5171428571428573e-06,
|
917 |
+
"loss": 0.0098,
|
918 |
+
"step": 2775
|
919 |
+
},
|
920 |
+
{
|
921 |
+
"epoch": 5.34,
|
922 |
+
"learning_rate": 3.4457142857142863e-06,
|
923 |
+
"loss": 0.0069,
|
924 |
+
"step": 2800
|
925 |
+
},
|
926 |
+
{
|
927 |
+
"epoch": 5.34,
|
928 |
+
"eval_loss": 0.43616336584091187,
|
929 |
+
"eval_runtime": 1644.4427,
|
930 |
+
"eval_samples_per_second": 0.912,
|
931 |
+
"eval_steps_per_second": 0.114,
|
932 |
+
"eval_wer": 161.19661674986133,
|
933 |
+
"step": 2800
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 5.39,
|
937 |
+
"learning_rate": 3.3742857142857145e-06,
|
938 |
+
"loss": 0.0103,
|
939 |
+
"step": 2825
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 5.44,
|
943 |
+
"learning_rate": 3.302857142857143e-06,
|
944 |
+
"loss": 0.0083,
|
945 |
+
"step": 2850
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 5.49,
|
949 |
+
"learning_rate": 3.2314285714285716e-06,
|
950 |
+
"loss": 0.0084,
|
951 |
+
"step": 2875
|
952 |
+
},
|
953 |
+
{
|
954 |
+
"epoch": 5.53,
|
955 |
+
"learning_rate": 3.1600000000000002e-06,
|
956 |
+
"loss": 0.0093,
|
957 |
+
"step": 2900
|
958 |
+
},
|
959 |
+
{
|
960 |
+
"epoch": 5.53,
|
961 |
+
"eval_loss": 0.43420636653900146,
|
962 |
+
"eval_runtime": 1623.2282,
|
963 |
+
"eval_samples_per_second": 0.924,
|
964 |
+
"eval_steps_per_second": 0.116,
|
965 |
+
"eval_wer": 157.52218524681086,
|
966 |
+
"step": 2900
|
967 |
}
|
968 |
],
|
969 |
"logging_steps": 25,
|
|
|
971 |
"num_input_tokens_seen": 0,
|
972 |
"num_train_epochs": 8,
|
973 |
"save_steps": 100,
|
974 |
+
"total_flos": 2.67706246606848e+19,
|
975 |
"trial_name": null,
|
976 |
"trial_params": null
|
977 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4856
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2c92dac35d16dc814e0a1581e1901c1f2948813ba744cab88f1ca1434e0d291
|
3 |
size 4856
|