Training in progress, step 30366, 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 sha256:8f029d94ada083d9f73da8396acffc7080689e7a18b6b09c49757919fbbf1873
|
| 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:b43b95c7c2bcc4d33bab54d53ae4315d00ba28963345e7442c91061a996dda06
|
| 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:f59244a96507a763bbbf8b5c267158cde54ecf6046ddd9e27a3ef772af4e971e
|
| 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 sha256:1850260f05fcd1a5df6ff4ed141317e98095595d0fc6182edb5b4a90c0561849
|
| 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:c972d95c54b9db33869ff2d09f16d763d338db651fadaae6d08441b00c57a6c6
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": 12000,
|
| 3 |
"best_metric": 0.1958443854995579,
|
| 4 |
"best_model_checkpoint": "./distil-whisper/checkpoint-12000",
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 1000,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -2378,6 +2378,27 @@
|
|
| 2378 |
"eval_steps_per_second": 0.429,
|
| 2379 |
"eval_wer": 0.20218096080165046,
|
| 2380 |
"step": 30000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2381 |
}
|
| 2382 |
],
|
| 2383 |
"logging_steps": 100,
|
|
@@ -2392,12 +2413,12 @@
|
|
| 2392 |
"should_evaluate": false,
|
| 2393 |
"should_log": false,
|
| 2394 |
"should_save": true,
|
| 2395 |
-
"should_training_stop":
|
| 2396 |
},
|
| 2397 |
"attributes": {}
|
| 2398 |
}
|
| 2399 |
},
|
| 2400 |
-
"total_flos": 3.
|
| 2401 |
"train_batch_size": 8,
|
| 2402 |
"trial_name": null,
|
| 2403 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": 12000,
|
| 3 |
"best_metric": 0.1958443854995579,
|
| 4 |
"best_model_checkpoint": "./distil-whisper/checkpoint-12000",
|
| 5 |
+
"epoch": 18.0,
|
| 6 |
"eval_steps": 1000,
|
| 7 |
+
"global_step": 30366,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2378 |
"eval_steps_per_second": 0.429,
|
| 2379 |
"eval_wer": 0.20218096080165046,
|
| 2380 |
"step": 30000
|
| 2381 |
+
},
|
| 2382 |
+
{
|
| 2383 |
+
"epoch": 17.842323651452283,
|
| 2384 |
+
"grad_norm": 9.971963882446289,
|
| 2385 |
+
"learning_rate": 9.442175048550191e-07,
|
| 2386 |
+
"loss": 0.8318,
|
| 2387 |
+
"step": 30100
|
| 2388 |
+
},
|
| 2389 |
+
{
|
| 2390 |
+
"epoch": 17.901600474214582,
|
| 2391 |
+
"grad_norm": 7.2862443923950195,
|
| 2392 |
+
"learning_rate": 6.093886024241613e-07,
|
| 2393 |
+
"loss": 0.8582,
|
| 2394 |
+
"step": 30200
|
| 2395 |
+
},
|
| 2396 |
+
{
|
| 2397 |
+
"epoch": 17.960877296976882,
|
| 2398 |
+
"grad_norm": 6.241823196411133,
|
| 2399 |
+
"learning_rate": 2.745596999933034e-07,
|
| 2400 |
+
"loss": 0.8877,
|
| 2401 |
+
"step": 30300
|
| 2402 |
}
|
| 2403 |
],
|
| 2404 |
"logging_steps": 100,
|
|
|
|
| 2413 |
"should_evaluate": false,
|
| 2414 |
"should_log": false,
|
| 2415 |
"should_save": true,
|
| 2416 |
+
"should_training_stop": true
|
| 2417 |
},
|
| 2418 |
"attributes": {}
|
| 2419 |
}
|
| 2420 |
},
|
| 2421 |
+
"total_flos": 3.949562194034688e+19,
|
| 2422 |
"train_batch_size": 8,
|
| 2423 |
"trial_name": null,
|
| 2424 |
"trial_params": null
|