tehreemfarooqi
commited on
Training in progress, step 12446, 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 3055544304
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:560a3733f4bbb77c7facbd8e1fcbec09c47c91778df2706dfaa878b1dab0a8ff
|
3 |
size 3055544304
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6099375168
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a221df9a99724f5892178dc1aee259955a08a1659f7a165bd00b016ef52a032
|
3 |
size 6099375168
|
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 sha256:0b9afb76df39f158a5e48a47e5fd99ff76fe61548f70cccfae2931dd44ced886
|
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 sha256:99cc361e445085ab266b15edad9fa18a2afe08322b075eb52cc3dd62210b622c
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 4.682127039146104,
|
3 |
"best_model_checkpoint": "./whisper-medium-ur/checkpoint-11000",
|
4 |
-
"epoch": 0.
|
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,
|
@@ -955,6 +955,34 @@
|
|
955 |
"eval_steps_per_second": 0.222,
|
956 |
"eval_wer": 4.687628951060494,
|
957 |
"step": 12000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
958 |
}
|
959 |
],
|
960 |
"logging_steps": 100,
|
@@ -978,12 +1006,12 @@
|
|
978 |
"should_evaluate": false,
|
979 |
"should_log": false,
|
980 |
"should_save": true,
|
981 |
-
"should_training_stop":
|
982 |
},
|
983 |
"attributes": {}
|
984 |
}
|
985 |
},
|
986 |
-
"total_flos":
|
987 |
"train_batch_size": 8,
|
988 |
"trial_name": null,
|
989 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 4.682127039146104,
|
3 |
"best_model_checkpoint": "./whisper-medium-ur/checkpoint-11000",
|
4 |
+
"epoch": 0.9999598280641144,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 12446,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
955 |
"eval_steps_per_second": 0.222,
|
956 |
"eval_wer": 4.687628951060494,
|
957 |
"step": 12000
|
958 |
+
},
|
959 |
+
{
|
960 |
+
"epoch": 0.9721608484312859,
|
961 |
+
"grad_norm": 2.960160493850708,
|
962 |
+
"learning_rate": 2.946593001841621e-07,
|
963 |
+
"loss": 0.2245,
|
964 |
+
"step": 12100
|
965 |
+
},
|
966 |
+
{
|
967 |
+
"epoch": 0.9801952356084039,
|
968 |
+
"grad_norm": 1.555345892906189,
|
969 |
+
"learning_rate": 2.109492717227524e-07,
|
970 |
+
"loss": 0.2078,
|
971 |
+
"step": 12200
|
972 |
+
},
|
973 |
+
{
|
974 |
+
"epoch": 0.9882296227855221,
|
975 |
+
"grad_norm": 6.304783821105957,
|
976 |
+
"learning_rate": 1.2723924326134273e-07,
|
977 |
+
"loss": 0.2169,
|
978 |
+
"step": 12300
|
979 |
+
},
|
980 |
+
{
|
981 |
+
"epoch": 0.9962640099626401,
|
982 |
+
"grad_norm": 2.4615955352783203,
|
983 |
+
"learning_rate": 4.352921479993303e-08,
|
984 |
+
"loss": 0.2152,
|
985 |
+
"step": 12400
|
986 |
}
|
987 |
],
|
988 |
"logging_steps": 100,
|
|
|
1006 |
"should_evaluate": false,
|
1007 |
"should_log": false,
|
1008 |
"should_save": true,
|
1009 |
+
"should_training_stop": true
|
1010 |
},
|
1011 |
"attributes": {}
|
1012 |
}
|
1013 |
},
|
1014 |
+
"total_flos": 2.0323917886390272e+20,
|
1015 |
"train_batch_size": 8,
|
1016 |
"trial_name": null,
|
1017 |
"trial_params": null
|