Training in progress, step 4209, 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 sha256:69413f73615f83d9af3e012f915779e8feb55af85c0f9865e5b11ad6de4098a7
|
| 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:c26ab3bab0f78e1de1ae83243b84b339f9a73fdc9f36898bacd02627010b7e2f
|
| 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:fffa34d617d37d160278a96263e54262610f7be0f6f6036d5ce9daab9c3384b4
|
| 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 sha256:700c62e2c409fb74a77e8989f1568b7a1be716546579ac14b2d28333ee737550
|
| 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 sha256:0b18e7fa03b9a1836a4a0d45bc80a9a0024a1c8c3ed77ce70ed3080f8004f4c9
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": 4000,
|
| 3 |
"best_metric": 0.22192749778956675,
|
| 4 |
"best_model_checkpoint": "./distil-whisper/checkpoint-4000",
|
| 5 |
-
"epoch": 2.
|
| 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,
|
|
@@ -378,6 +378,20 @@
|
|
| 378 |
"eval_steps_per_second": 0.407,
|
| 379 |
"eval_wer": 0.22192749778956675,
|
| 380 |
"step": 4000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 381 |
}
|
| 382 |
],
|
| 383 |
"logging_steps": 100,
|
|
@@ -392,12 +406,12 @@
|
|
| 392 |
"should_evaluate": false,
|
| 393 |
"should_log": false,
|
| 394 |
"should_save": true,
|
| 395 |
-
"should_training_stop":
|
| 396 |
},
|
| 397 |
"attributes": {}
|
| 398 |
}
|
| 399 |
},
|
| 400 |
-
"total_flos": 5.
|
| 401 |
"train_batch_size": 8,
|
| 402 |
"trial_name": null,
|
| 403 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": 4000,
|
| 3 |
"best_metric": 0.22192749778956675,
|
| 4 |
"best_model_checkpoint": "./distil-whisper/checkpoint-4000",
|
| 5 |
+
"epoch": 2.998396579369321,
|
| 6 |
"eval_steps": 400,
|
| 7 |
+
"global_step": 4209,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 378 |
"eval_steps_per_second": 0.407,
|
| 379 |
"eval_wer": 0.22192749778956675,
|
| 380 |
"step": 4000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 2.920719757705327,
|
| 384 |
+
"grad_norm": 50.19482421875,
|
| 385 |
+
"learning_rate": 3.343219196548935e-06,
|
| 386 |
+
"loss": 3.9649,
|
| 387 |
+
"step": 4100
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 2.991982896846606,
|
| 391 |
+
"grad_norm": 70.83031463623047,
|
| 392 |
+
"learning_rate": 6.470746832030197e-07,
|
| 393 |
+
"loss": 4.095,
|
| 394 |
+
"step": 4200
|
| 395 |
}
|
| 396 |
],
|
| 397 |
"logging_steps": 100,
|
|
|
|
| 406 |
"should_evaluate": false,
|
| 407 |
"should_log": false,
|
| 408 |
"should_save": true,
|
| 409 |
+
"should_training_stop": true
|
| 410 |
},
|
| 411 |
"attributes": {}
|
| 412 |
}
|
| 413 |
},
|
| 414 |
+
"total_flos": 5.4727997128704e+18,
|
| 415 |
"train_batch_size": 8,
|
| 416 |
"trial_name": null,
|
| 417 |
"trial_params": null
|