Training in progress, step 25305, 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 sha256:08f5c1d536526f34a6e5dccd4fca7908cf03bd039f3454908cb22834829d1d0f
|
| 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 sha256:918f59dceab7d3b5966f2e329ae2f8054700029f83893903fe5b824b61590cba
|
| 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:a385f76e78556f89ee9225d36f306db0256a2277bd19e992b8db4bda9d985e7f
|
| 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:cd1d747d83b5c42d3e8da230ee54d494d7bcc37f83be433b8929108874835b7f
|
| 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 sha256:90b2346a22bacb7ec5622b952524c2c5b6f93368a7e6179106d9a0ec2e0ff4ba
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": 4000,
|
| 3 |
"best_metric": 0.18950781019746538,
|
| 4 |
"best_model_checkpoint": "./distil-whisper/checkpoint-4000",
|
| 5 |
-
"epoch":
|
| 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,
|
|
@@ -2339,6 +2339,13 @@
|
|
| 2339 |
"eval_steps_per_second": 0.421,
|
| 2340 |
"eval_wer": 0.20159151193633953,
|
| 2341 |
"step": 25200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2342 |
}
|
| 2343 |
],
|
| 2344 |
"logging_steps": 100,
|
|
@@ -2353,12 +2360,12 @@
|
|
| 2353 |
"should_evaluate": false,
|
| 2354 |
"should_log": false,
|
| 2355 |
"should_save": true,
|
| 2356 |
-
"should_training_stop":
|
| 2357 |
},
|
| 2358 |
"attributes": {}
|
| 2359 |
}
|
| 2360 |
},
|
| 2361 |
-
"total_flos": 3.
|
| 2362 |
"train_batch_size": 8,
|
| 2363 |
"trial_name": null,
|
| 2364 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": 4000,
|
| 3 |
"best_metric": 0.18950781019746538,
|
| 4 |
"best_model_checkpoint": "./distil-whisper/checkpoint-4000",
|
| 5 |
+
"epoch": 15.0,
|
| 6 |
"eval_steps": 400,
|
| 7 |
+
"global_step": 25305,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2339 |
"eval_steps_per_second": 0.421,
|
| 2340 |
"eval_wer": 0.20159151193633953,
|
| 2341 |
"step": 25200
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 14.997036158861885,
|
| 2345 |
+
"grad_norm": 8.718119621276855,
|
| 2346 |
+
"learning_rate": 8.062890546260835e-08,
|
| 2347 |
+
"loss": 0.8887,
|
| 2348 |
+
"step": 25300
|
| 2349 |
}
|
| 2350 |
],
|
| 2351 |
"logging_steps": 100,
|
|
|
|
| 2360 |
"should_evaluate": false,
|
| 2361 |
"should_log": false,
|
| 2362 |
"should_save": true,
|
| 2363 |
+
"should_training_stop": true
|
| 2364 |
},
|
| 2365 |
"attributes": {}
|
| 2366 |
}
|
| 2367 |
},
|
| 2368 |
+
"total_flos": 3.29130182836224e+19,
|
| 2369 |
"train_batch_size": 8,
|
| 2370 |
"trial_name": null,
|
| 2371 |
"trial_params": null
|