Training in progress, step 2763, 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 290403936
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c94525c9a6809073d87ec2cff927fa43d93d9121268bf8ab37bd9a336e8cf634
|
| 3 |
size 290403936
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 574811514
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee68835b920c4a59946b6380b961daaad38afda3f0cc3b0030a78392ec6dbc37
|
| 3 |
size 574811514
|
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 sha256:6901c444ab97c57108e339f99c5b9e43b779ab205a488010b1adb83b370f6a91
|
| 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:b0b1d9fe1253b680c199039b2fc336566831953f07ddd076cc65cd71af2df3b7
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 13.181589828805503,
|
| 3 |
"best_model_checkpoint": "./Whisper_base_fine_tune_Quran/checkpoint-2400",
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 800,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -373,6 +373,55 @@
|
|
| 373 |
"eval_steps_per_second": 0.152,
|
| 374 |
"eval_wer": 13.181589828805503,
|
| 375 |
"step": 2400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 376 |
}
|
| 377 |
],
|
| 378 |
"logging_steps": 50,
|
|
@@ -387,12 +436,12 @@
|
|
| 387 |
"should_evaluate": false,
|
| 388 |
"should_log": false,
|
| 389 |
"should_save": true,
|
| 390 |
-
"should_training_stop":
|
| 391 |
},
|
| 392 |
"attributes": {}
|
| 393 |
}
|
| 394 |
},
|
| 395 |
-
"total_flos":
|
| 396 |
"train_batch_size": 16,
|
| 397 |
"trial_name": null,
|
| 398 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 13.181589828805503,
|
| 3 |
"best_model_checkpoint": "./Whisper_base_fine_tune_Quran/checkpoint-2400",
|
| 4 |
+
"epoch": 0.9998190700199023,
|
| 5 |
"eval_steps": 800,
|
| 6 |
+
"global_step": 2763,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 373 |
"eval_steps_per_second": 0.152,
|
| 374 |
"eval_wer": 13.181589828805503,
|
| 375 |
"step": 2400
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.8865569024787407,
|
| 379 |
+
"grad_norm": 31105.876953125,
|
| 380 |
+
"learning_rate": 4.646386846367878e-06,
|
| 381 |
+
"loss": 0.0041,
|
| 382 |
+
"step": 2450
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.9046499004885109,
|
| 386 |
+
"grad_norm": 37322.1015625,
|
| 387 |
+
"learning_rate": 3.2957355110758757e-06,
|
| 388 |
+
"loss": 0.006,
|
| 389 |
+
"step": 2500
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.9227428984982812,
|
| 393 |
+
"grad_norm": 27944.677734375,
|
| 394 |
+
"learning_rate": 2.1700169840716875e-06,
|
| 395 |
+
"loss": 0.0042,
|
| 396 |
+
"step": 2550
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.9408358965080514,
|
| 400 |
+
"grad_norm": 15180.865234375,
|
| 401 |
+
"learning_rate": 1.2746528479964659e-06,
|
| 402 |
+
"loss": 0.004,
|
| 403 |
+
"step": 2600
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.9589288945178216,
|
| 407 |
+
"grad_norm": 35244.10546875,
|
| 408 |
+
"learning_rate": 6.139552737359112e-07,
|
| 409 |
+
"loss": 0.0045,
|
| 410 |
+
"step": 2650
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.9770218925275919,
|
| 414 |
+
"grad_norm": 25496.6171875,
|
| 415 |
+
"learning_rate": 1.911062525371543e-07,
|
| 416 |
+
"loss": 0.0043,
|
| 417 |
+
"step": 2700
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.995114890537362,
|
| 421 |
+
"grad_norm": 15512.5556640625,
|
| 422 |
+
"learning_rate": 8.142271193450902e-09,
|
| 423 |
+
"loss": 0.0041,
|
| 424 |
+
"step": 2750
|
| 425 |
}
|
| 426 |
],
|
| 427 |
"logging_steps": 50,
|
|
|
|
| 436 |
"should_evaluate": false,
|
| 437 |
"should_log": false,
|
| 438 |
"should_save": true,
|
| 439 |
+
"should_training_stop": true
|
| 440 |
},
|
| 441 |
"attributes": {}
|
| 442 |
}
|
| 443 |
},
|
| 444 |
+
"total_flos": 1.146932284096512e+19,
|
| 445 |
"train_batch_size": 16,
|
| 446 |
"trial_name": null,
|
| 447 |
"trial_params": null
|