Commit ·
cf7fac1
1
Parent(s): 3373d04
Training in progress, step 3900, checkpoint
Browse files
last-checkpoint/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89d76af87c627c8a530615d241fa48d9349e7cd99fb14a2d28c7b767fce70718
|
| 3 |
+
size 3096956278
|
last-checkpoint/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1cdddd1ad7d41a694f625986332e4a3934616b6a0a8ad0bd646e4d5afacb56b6
|
| 3 |
+
size 14244
|
last-checkpoint/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5eb997ec8b3e1b3a4c09f26de1f56eaaf33d1b7ee43d985d4da13efffe0d547
|
| 3 |
+
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 71.
|
| 3 |
-
"best_model_checkpoint": "./whisper-large-v3-cv17-dv/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 300,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -367,6 +367,36 @@
|
|
| 367 |
"eval_steps_per_second": 0.02,
|
| 368 |
"eval_wer": 71.72413793103448,
|
| 369 |
"step": 3600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 370 |
}
|
| 371 |
],
|
| 372 |
"logging_steps": 100,
|
|
@@ -386,7 +416,7 @@
|
|
| 386 |
"attributes": {}
|
| 387 |
}
|
| 388 |
},
|
| 389 |
-
"total_flos":
|
| 390 |
"train_batch_size": 16,
|
| 391 |
"trial_name": null,
|
| 392 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 71.03448275862068,
|
| 3 |
+
"best_model_checkpoint": "./whisper-large-v3-cv17-dv/checkpoint-3900",
|
| 4 |
+
"epoch": 11.863192182410424,
|
| 5 |
"eval_steps": 300,
|
| 6 |
+
"global_step": 3900,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 367 |
"eval_steps_per_second": 0.02,
|
| 368 |
"eval_wer": 71.72413793103448,
|
| 369 |
"step": 3600
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 11.211726384364821,
|
| 373 |
+
"grad_norm": 0.03168971464037895,
|
| 374 |
+
"learning_rate": 8.714285714285716e-07,
|
| 375 |
+
"loss": 0.0005,
|
| 376 |
+
"step": 3700
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 11.537459283387623,
|
| 380 |
+
"grad_norm": 0.020701788365840912,
|
| 381 |
+
"learning_rate": 5.857142857142857e-07,
|
| 382 |
+
"loss": 0.0003,
|
| 383 |
+
"step": 3800
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 11.863192182410424,
|
| 387 |
+
"grad_norm": 0.05785975977778435,
|
| 388 |
+
"learning_rate": 3.0000000000000004e-07,
|
| 389 |
+
"loss": 0.0003,
|
| 390 |
+
"step": 3900
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 11.863192182410424,
|
| 394 |
+
"eval_loss": 0.4610276520252228,
|
| 395 |
+
"eval_runtime": 143.56,
|
| 396 |
+
"eval_samples_per_second": 0.697,
|
| 397 |
+
"eval_steps_per_second": 0.021,
|
| 398 |
+
"eval_wer": 71.03448275862068,
|
| 399 |
+
"step": 3900
|
| 400 |
}
|
| 401 |
],
|
| 402 |
"logging_steps": 100,
|
|
|
|
| 416 |
"attributes": {}
|
| 417 |
}
|
| 418 |
},
|
| 419 |
+
"total_flos": 2.117320944648192e+20,
|
| 420 |
"train_batch_size": 16,
|
| 421 |
"trial_name": null,
|
| 422 |
"trial_params": null
|