Commit ·
0c33168
1
Parent(s): 6bd557b
Training in progress, step 3600, checkpoint
Browse files
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 71.37931034482759,
|
| 3 |
"best_model_checkpoint": "./whisper-large-v3-cv17-dv/checkpoint-2700",
|
| 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,
|
|
@@ -337,6 +337,36 @@
|
|
| 337 |
"eval_steps_per_second": 0.02,
|
| 338 |
"eval_wer": 72.58620689655172,
|
| 339 |
"step": 3300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 340 |
}
|
| 341 |
],
|
| 342 |
"logging_steps": 100,
|
|
@@ -356,7 +386,7 @@
|
|
| 356 |
"attributes": {}
|
| 357 |
}
|
| 358 |
},
|
| 359 |
-
"total_flos": 1.
|
| 360 |
"train_batch_size": 16,
|
| 361 |
"trial_name": null,
|
| 362 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 71.37931034482759,
|
| 3 |
"best_model_checkpoint": "./whisper-large-v3-cv17-dv/checkpoint-2700",
|
| 4 |
+
"epoch": 10.88599348534202,
|
| 5 |
"eval_steps": 300,
|
| 6 |
+
"global_step": 3600,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 337 |
"eval_steps_per_second": 0.02,
|
| 338 |
"eval_wer": 72.58620689655172,
|
| 339 |
"step": 3300
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 10.234527687296417,
|
| 343 |
+
"grad_norm": 0.5388866662979126,
|
| 344 |
+
"learning_rate": 1.7285714285714287e-06,
|
| 345 |
+
"loss": 0.0012,
|
| 346 |
+
"step": 3400
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 10.560260586319218,
|
| 350 |
+
"grad_norm": 0.6833564639091492,
|
| 351 |
+
"learning_rate": 1.442857142857143e-06,
|
| 352 |
+
"loss": 0.0007,
|
| 353 |
+
"step": 3500
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 10.88599348534202,
|
| 357 |
+
"grad_norm": 0.26250678300857544,
|
| 358 |
+
"learning_rate": 1.1571428571428572e-06,
|
| 359 |
+
"loss": 0.0008,
|
| 360 |
+
"step": 3600
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 10.88599348534202,
|
| 364 |
+
"eval_loss": 0.45030444860458374,
|
| 365 |
+
"eval_runtime": 147.162,
|
| 366 |
+
"eval_samples_per_second": 0.68,
|
| 367 |
+
"eval_steps_per_second": 0.02,
|
| 368 |
+
"eval_wer": 71.72413793103448,
|
| 369 |
+
"step": 3600
|
| 370 |
}
|
| 371 |
],
|
| 372 |
"logging_steps": 100,
|
|
|
|
| 386 |
"attributes": {}
|
| 387 |
}
|
| 388 |
},
|
| 389 |
+
"total_flos": 1.954580775763968e+20,
|
| 390 |
"train_batch_size": 16,
|
| 391 |
"trial_name": null,
|
| 392 |
"trial_params": null
|