Training in progress, step 1400
Browse files- last-checkpoint/model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +3 -69
- last-checkpoint/training_args.bin +2 -2
- model.safetensors +1 -1
- runs/Dec04_11-55-25_198ac3fc2851/events.out.tfevents.1701690947.198ac3fc2851.342.0 +2 -2
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 966995080
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6b8c4943809f31374b9e8f245a7b805ba8d8cb804c954afe70f2b1153c6466b
|
3 |
size 966995080
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1925064044
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:082989c729f6c2197f46184f15b82d0618ed70705d2eb063606785638c33b48c
|
3 |
size 1925064044
|
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 sha256:0f6d4f1e7a172a18196d4af73f4416f5dbae2222daf67fb853e554c8aa388f46
|
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 sha256:5e80f39295701f62f253a4cdc45497251532fc021ede722c8cdba45bced5fc9c
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 70.1955074875208,
|
3 |
"best_model_checkpoint": "./whisper-it/checkpoint-300",
|
4 |
-
"epoch": 2.
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -370,72 +370,6 @@
|
|
370 |
"eval_steps_per_second": 0.106,
|
371 |
"eval_wer": 158.88103161397672,
|
372 |
"step": 1100
|
373 |
-
},
|
374 |
-
{
|
375 |
-
"epoch": 2.15,
|
376 |
-
"learning_rate": 8.231428571428572e-06,
|
377 |
-
"loss": 0.075,
|
378 |
-
"step": 1125
|
379 |
-
},
|
380 |
-
{
|
381 |
-
"epoch": 2.19,
|
382 |
-
"learning_rate": 8.16e-06,
|
383 |
-
"loss": 0.0701,
|
384 |
-
"step": 1150
|
385 |
-
},
|
386 |
-
{
|
387 |
-
"epoch": 2.24,
|
388 |
-
"learning_rate": 8.088571428571429e-06,
|
389 |
-
"loss": 0.0732,
|
390 |
-
"step": 1175
|
391 |
-
},
|
392 |
-
{
|
393 |
-
"epoch": 2.29,
|
394 |
-
"learning_rate": 8.017142857142858e-06,
|
395 |
-
"loss": 0.0769,
|
396 |
-
"step": 1200
|
397 |
-
},
|
398 |
-
{
|
399 |
-
"epoch": 2.29,
|
400 |
-
"eval_loss": 0.3788917660713196,
|
401 |
-
"eval_runtime": 1861.7459,
|
402 |
-
"eval_samples_per_second": 0.806,
|
403 |
-
"eval_steps_per_second": 0.101,
|
404 |
-
"eval_wer": 215.1552967276761,
|
405 |
-
"step": 1200
|
406 |
-
},
|
407 |
-
{
|
408 |
-
"epoch": 2.34,
|
409 |
-
"learning_rate": 7.945714285714287e-06,
|
410 |
-
"loss": 0.0747,
|
411 |
-
"step": 1225
|
412 |
-
},
|
413 |
-
{
|
414 |
-
"epoch": 2.39,
|
415 |
-
"learning_rate": 7.874285714285716e-06,
|
416 |
-
"loss": 0.0737,
|
417 |
-
"step": 1250
|
418 |
-
},
|
419 |
-
{
|
420 |
-
"epoch": 2.43,
|
421 |
-
"learning_rate": 7.802857142857143e-06,
|
422 |
-
"loss": 0.0774,
|
423 |
-
"step": 1275
|
424 |
-
},
|
425 |
-
{
|
426 |
-
"epoch": 2.48,
|
427 |
-
"learning_rate": 7.731428571428572e-06,
|
428 |
-
"loss": 0.0814,
|
429 |
-
"step": 1300
|
430 |
-
},
|
431 |
-
{
|
432 |
-
"epoch": 2.48,
|
433 |
-
"eval_loss": 0.3779347538948059,
|
434 |
-
"eval_runtime": 1837.4869,
|
435 |
-
"eval_samples_per_second": 0.816,
|
436 |
-
"eval_steps_per_second": 0.102,
|
437 |
-
"eval_wer": 170.4520244037715,
|
438 |
-
"step": 1300
|
439 |
}
|
440 |
],
|
441 |
"logging_steps": 25,
|
@@ -443,7 +377,7 @@
|
|
443 |
"num_input_tokens_seen": 0,
|
444 |
"num_train_epochs": 8,
|
445 |
"save_steps": 100,
|
446 |
-
"total_flos": 1.
|
447 |
"trial_name": null,
|
448 |
"trial_params": null
|
449 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 70.1955074875208,
|
3 |
"best_model_checkpoint": "./whisper-it/checkpoint-300",
|
4 |
+
"epoch": 2.099236641221374,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 1100,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
370 |
"eval_steps_per_second": 0.106,
|
371 |
"eval_wer": 158.88103161397672,
|
372 |
"step": 1100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
373 |
}
|
374 |
],
|
375 |
"logging_steps": 25,
|
|
|
377 |
"num_input_tokens_seen": 0,
|
378 |
"num_train_epochs": 8,
|
379 |
"save_steps": 100,
|
380 |
+
"total_flos": 1.015416589565952e+19,
|
381 |
"trial_name": null,
|
382 |
"trial_params": null
|
383 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:26fb5b39845f83ef97933929d4301eb10fbbba57913dc6054b50bd05a1ce5a9f
|
3 |
+
size 4792
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 966995080
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb069e9606f7965f3e3fd3aaa6e7d45a6226560fb8ccfe502bfbe4f1480ead03
|
3 |
size 966995080
|
runs/Dec04_11-55-25_198ac3fc2851/events.out.tfevents.1701690947.198ac3fc2851.342.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:266a395702ff3676bcc594f8ff9dab62e38ac54e8530b2c3c9665151c389d729
|
3 |
+
size 8011
|