Training in progress, step 1400, 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 966995080
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb069e9606f7965f3e3fd3aaa6e7d45a6226560fb8ccfe502bfbe4f1480ead03
|
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 sha256:62123caf560e093f6cb81f4e12690415fcbc59c2ebe37654a7ef021b905912a5
|
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:a161ab96979525c9b08c7ae649d4c37b02c2f5121e90eab56cb35fe094d8fa41
|
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 sha256:86eb457a5e93033c2762ebf17d280891d3b014ff27032f5d3bd7160d46c87be6
|
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,
|
@@ -370,6 +370,105 @@
|
|
370 |
"eval_steps_per_second": 0.106,
|
371 |
"eval_wer": 158.88103161397672,
|
372 |
"step": 1100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
373 |
}
|
374 |
],
|
375 |
"logging_steps": 25,
|
@@ -377,7 +476,7 @@
|
|
377 |
"num_input_tokens_seen": 0,
|
378 |
"num_train_epochs": 8,
|
379 |
"save_steps": 100,
|
380 |
-
"total_flos": 1.
|
381 |
"trial_name": null,
|
382 |
"trial_params": null
|
383 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 70.1955074875208,
|
3 |
"best_model_checkpoint": "./whisper-it/checkpoint-300",
|
4 |
+
"epoch": 2.67175572519084,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 1400,
|
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 |
+
"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 |
+
"epoch": 2.53,
|
442 |
+
"learning_rate": 7.660000000000001e-06,
|
443 |
+
"loss": 0.0782,
|
444 |
+
"step": 1325
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 2.58,
|
448 |
+
"learning_rate": 7.588571428571429e-06,
|
449 |
+
"loss": 0.0732,
|
450 |
+
"step": 1350
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 2.62,
|
454 |
+
"learning_rate": 7.5171428571428575e-06,
|
455 |
+
"loss": 0.078,
|
456 |
+
"step": 1375
|
457 |
+
},
|
458 |
+
{
|
459 |
+
"epoch": 2.67,
|
460 |
+
"learning_rate": 7.445714285714286e-06,
|
461 |
+
"loss": 0.0786,
|
462 |
+
"step": 1400
|
463 |
+
},
|
464 |
+
{
|
465 |
+
"epoch": 2.67,
|
466 |
+
"eval_loss": 0.37702885270118713,
|
467 |
+
"eval_runtime": 1750.66,
|
468 |
+
"eval_samples_per_second": 0.857,
|
469 |
+
"eval_steps_per_second": 0.107,
|
470 |
+
"eval_wer": 140.5851358846367,
|
471 |
+
"step": 1400
|
472 |
}
|
473 |
],
|
474 |
"logging_steps": 25,
|
|
|
476 |
"num_input_tokens_seen": 0,
|
477 |
"num_train_epochs": 8,
|
478 |
"save_steps": 100,
|
479 |
+
"total_flos": 1.292458573873152e+19,
|
480 |
"trial_name": null,
|
481 |
"trial_params": null
|
482 |
}
|
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 sha256:6aa21d9517849e744bc2774d0fa736ea880951b90cffefa75582a90947374bfc
|
3 |
+
size 4856
|