Training in progress, step 33740, 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 223144592
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfbf3330733366f480058f4acc43f4b33bcf90be58f6148c9e7ba9e9cc16556b
|
| 3 |
size 223144592
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 281574266
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0baa87b6a20f5da63804deb476e869325bdd38434d4801e9ff754af510fe1f2
|
| 3 |
size 281574266
|
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:c8057494ce92a550bfad621d8189c19e910a6d4abd86bbe1cf6f59d4e3d4ca54
|
| 3 |
size 14244
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 988
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb779461c157e920976902f7e10da553ef08690b8cb1e678f1ad0ceb27b3b0a1
|
| 3 |
size 988
|
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:ce728e16d5ac03050b00527a8e1a90dc74db0b69a4e3e2d0415dc2af3e021509
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": 4000,
|
| 3 |
"best_metric": 0.18950781019746538,
|
| 4 |
"best_model_checkpoint": "./distil-whisper/checkpoint-4000",
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 400,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -3116,6 +3116,13 @@
|
|
| 3116 |
"eval_steps_per_second": 0.423,
|
| 3117 |
"eval_wer": 0.2002652519893899,
|
| 3118 |
"step": 33600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3119 |
}
|
| 3120 |
],
|
| 3121 |
"logging_steps": 100,
|
|
@@ -3130,12 +3137,12 @@
|
|
| 3130 |
"should_evaluate": false,
|
| 3131 |
"should_log": false,
|
| 3132 |
"should_save": true,
|
| 3133 |
-
"should_training_stop":
|
| 3134 |
},
|
| 3135 |
"attributes": {}
|
| 3136 |
}
|
| 3137 |
},
|
| 3138 |
-
"total_flos": 4.
|
| 3139 |
"train_batch_size": 8,
|
| 3140 |
"trial_name": null,
|
| 3141 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": 4000,
|
| 3 |
"best_metric": 0.18950781019746538,
|
| 4 |
"best_model_checkpoint": "./distil-whisper/checkpoint-4000",
|
| 5 |
+
"epoch": 20.0,
|
| 6 |
"eval_steps": 400,
|
| 7 |
+
"global_step": 33740,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3116 |
"eval_steps_per_second": 0.423,
|
| 3117 |
"eval_wer": 0.2002652519893899,
|
| 3118 |
"step": 33600
|
| 3119 |
+
},
|
| 3120 |
+
{
|
| 3121 |
+
"epoch": 19.97628927089508,
|
| 3122 |
+
"grad_norm": 6.524932861328125,
|
| 3123 |
+
"learning_rate": 1.7448856799037304e-07,
|
| 3124 |
+
"loss": 0.8792,
|
| 3125 |
+
"step": 33700
|
| 3126 |
}
|
| 3127 |
],
|
| 3128 |
"logging_steps": 100,
|
|
|
|
| 3137 |
"should_evaluate": false,
|
| 3138 |
"should_log": false,
|
| 3139 |
"should_save": true,
|
| 3140 |
+
"should_training_stop": true
|
| 3141 |
},
|
| 3142 |
"attributes": {}
|
| 3143 |
}
|
| 3144 |
},
|
| 3145 |
+
"total_flos": 4.38840243781632e+19,
|
| 3146 |
"train_batch_size": 8,
|
| 3147 |
"trial_name": null,
|
| 3148 |
"trial_params": null
|