Training in progress, step 3100, 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 sha256:9d1c2e4ed987aee90e725ecff305fed01d3e4cec3c313446fbf4acd8456b8756
|
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 sha256:9d53577f76fdefe8556c65117e1ab17e94a9394b496e89807249258044e5ec7e
|
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:b41d2e987cb5c78d26dab771fe721c2da517630b617af0cac6deeb8db36562a9
|
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 sha256:1ea257fad0fa492e3a9fc46adc164d21d7f8ad016c3f3e68a0c6df4900fed1ab
|
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.
|
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,
|
@@ -964,6 +964,72 @@
|
|
964 |
"eval_steps_per_second": 0.116,
|
965 |
"eval_wer": 157.52218524681086,
|
966 |
"step": 2900
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
967 |
}
|
968 |
],
|
969 |
"logging_steps": 25,
|
@@ -971,7 +1037,7 @@
|
|
971 |
"num_input_tokens_seen": 0,
|
972 |
"num_train_epochs": 8,
|
973 |
"save_steps": 100,
|
974 |
-
"total_flos": 2.
|
975 |
"trial_name": null,
|
976 |
"trial_params": null
|
977 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 70.1955074875208,
|
3 |
"best_model_checkpoint": "./whisper-it/checkpoint-300",
|
4 |
+
"epoch": 5.916030534351145,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 3100,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
964 |
"eval_steps_per_second": 0.116,
|
965 |
"eval_wer": 157.52218524681086,
|
966 |
"step": 2900
|
967 |
+
},
|
968 |
+
{
|
969 |
+
"epoch": 5.58,
|
970 |
+
"learning_rate": 3.0885714285714284e-06,
|
971 |
+
"loss": 0.009,
|
972 |
+
"step": 2925
|
973 |
+
},
|
974 |
+
{
|
975 |
+
"epoch": 5.63,
|
976 |
+
"learning_rate": 3.0171428571428574e-06,
|
977 |
+
"loss": 0.0092,
|
978 |
+
"step": 2950
|
979 |
+
},
|
980 |
+
{
|
981 |
+
"epoch": 5.68,
|
982 |
+
"learning_rate": 2.945714285714286e-06,
|
983 |
+
"loss": 0.0086,
|
984 |
+
"step": 2975
|
985 |
+
},
|
986 |
+
{
|
987 |
+
"epoch": 5.73,
|
988 |
+
"learning_rate": 2.8742857142857146e-06,
|
989 |
+
"loss": 0.0076,
|
990 |
+
"step": 3000
|
991 |
+
},
|
992 |
+
{
|
993 |
+
"epoch": 5.73,
|
994 |
+
"eval_loss": 0.43520399928092957,
|
995 |
+
"eval_runtime": 1605.7035,
|
996 |
+
"eval_samples_per_second": 0.934,
|
997 |
+
"eval_steps_per_second": 0.117,
|
998 |
+
"eval_wer": 154.5410427066001,
|
999 |
+
"step": 3000
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 5.77,
|
1003 |
+
"learning_rate": 2.802857142857143e-06,
|
1004 |
+
"loss": 0.0089,
|
1005 |
+
"step": 3025
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 5.82,
|
1009 |
+
"learning_rate": 2.7314285714285714e-06,
|
1010 |
+
"loss": 0.0074,
|
1011 |
+
"step": 3050
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 5.87,
|
1015 |
+
"learning_rate": 2.6600000000000004e-06,
|
1016 |
+
"loss": 0.0084,
|
1017 |
+
"step": 3075
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 5.92,
|
1021 |
+
"learning_rate": 2.5885714285714285e-06,
|
1022 |
+
"loss": 0.0089,
|
1023 |
+
"step": 3100
|
1024 |
+
},
|
1025 |
+
{
|
1026 |
+
"epoch": 5.92,
|
1027 |
+
"eval_loss": 0.4393894076347351,
|
1028 |
+
"eval_runtime": 1680.0289,
|
1029 |
+
"eval_samples_per_second": 0.893,
|
1030 |
+
"eval_steps_per_second": 0.112,
|
1031 |
+
"eval_wer": 184.29007210205214,
|
1032 |
+
"step": 3100
|
1033 |
}
|
1034 |
],
|
1035 |
"logging_steps": 25,
|
|
|
1037 |
"num_input_tokens_seen": 0,
|
1038 |
"num_train_epochs": 8,
|
1039 |
"save_steps": 100,
|
1040 |
+
"total_flos": 2.86175712227328e+19,
|
1041 |
"trial_name": null,
|
1042 |
"trial_params": null
|
1043 |
}
|
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 sha256:41aeb0de3cf3c068ad356f23e2a4d52e468d71a8f1523974035aff9cc867de12
|
3 |
size 4856
|