warmestman
commited on
Commit
•
882d11c
1
Parent(s):
947f61a
Training in progress, step 2000, checkpoint
Browse files
last-checkpoint/model-00001-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4993448880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80b1f8d231b5ff1859039320fa0188cee6c8c45459e38193a22bc1676daee37c
|
3 |
size 4993448880
|
last-checkpoint/model-00002-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1180663192
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d9006daf5d78d90bf22b0c813d9e776720f90a688af4a7bd80cbc7dc7c09b019
|
3 |
size 1180663192
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3095446256
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba2a236d039fcf4f5348b184a304acbdf17c1575f2f90a02947dc19886042b45
|
3 |
size 3095446256
|
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:ad76ae298f288aa3230881b9dfb28684fc083c10f565ddf65a09a40de5f4dc0c
|
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 sha256:318a20b90d087d5ab98fe55e815e26cf3c50d3ca88ad22e2ca83eebaaef1c1d2
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric":
|
3 |
-
"best_model_checkpoint": "warmestman/whisper-large-v3-mn-cv-fleurs/checkpoint-
|
4 |
-
"epoch":
|
5 |
"eval_steps": 1000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -256,6 +256,255 @@
|
|
256 |
"eval_steps_per_second": 0.091,
|
257 |
"eval_wer": 41.504867719047354,
|
258 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
259 |
}
|
260 |
],
|
261 |
"logging_steps": 25,
|
@@ -263,7 +512,7 @@
|
|
263 |
"num_input_tokens_seen": 0,
|
264 |
"num_train_epochs": 60,
|
265 |
"save_steps": 1000,
|
266 |
-
"total_flos":
|
267 |
"train_batch_size": 16,
|
268 |
"trial_name": null,
|
269 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 38.2982234200539,
|
3 |
+
"best_model_checkpoint": "warmestman/whisper-large-v3-mn-cv-fleurs/checkpoint-2000",
|
4 |
+
"epoch": 11.976047904191617,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 2000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
256 |
"eval_steps_per_second": 0.091,
|
257 |
"eval_wer": 41.504867719047354,
|
258 |
"step": 1000
|
259 |
+
},
|
260 |
+
{
|
261 |
+
"epoch": 6.14,
|
262 |
+
"learning_rate": 9.447368421052633e-05,
|
263 |
+
"loss": 0.0455,
|
264 |
+
"step": 1025
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 6.29,
|
268 |
+
"learning_rate": 9.421052631578949e-05,
|
269 |
+
"loss": 0.0471,
|
270 |
+
"step": 1050
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 6.44,
|
274 |
+
"learning_rate": 9.394736842105264e-05,
|
275 |
+
"loss": 0.0471,
|
276 |
+
"step": 1075
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 6.59,
|
280 |
+
"learning_rate": 9.36842105263158e-05,
|
281 |
+
"loss": 0.0465,
|
282 |
+
"step": 1100
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 6.74,
|
286 |
+
"learning_rate": 9.342105263157896e-05,
|
287 |
+
"loss": 0.0486,
|
288 |
+
"step": 1125
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"epoch": 6.89,
|
292 |
+
"learning_rate": 9.315789473684211e-05,
|
293 |
+
"loss": 0.044,
|
294 |
+
"step": 1150
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 7.04,
|
298 |
+
"learning_rate": 9.289473684210527e-05,
|
299 |
+
"loss": 0.0421,
|
300 |
+
"step": 1175
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"epoch": 7.19,
|
304 |
+
"learning_rate": 9.263157894736843e-05,
|
305 |
+
"loss": 0.0333,
|
306 |
+
"step": 1200
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"epoch": 7.34,
|
310 |
+
"learning_rate": 9.236842105263158e-05,
|
311 |
+
"loss": 0.0323,
|
312 |
+
"step": 1225
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 7.49,
|
316 |
+
"learning_rate": 9.210526315789474e-05,
|
317 |
+
"loss": 0.0289,
|
318 |
+
"step": 1250
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 7.63,
|
322 |
+
"learning_rate": 9.18421052631579e-05,
|
323 |
+
"loss": 0.0339,
|
324 |
+
"step": 1275
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 7.78,
|
328 |
+
"learning_rate": 9.157894736842105e-05,
|
329 |
+
"loss": 0.0332,
|
330 |
+
"step": 1300
|
331 |
+
},
|
332 |
+
{
|
333 |
+
"epoch": 7.93,
|
334 |
+
"learning_rate": 9.131578947368421e-05,
|
335 |
+
"loss": 0.0701,
|
336 |
+
"step": 1325
|
337 |
+
},
|
338 |
+
{
|
339 |
+
"epoch": 8.08,
|
340 |
+
"learning_rate": 9.105263157894738e-05,
|
341 |
+
"loss": 0.0601,
|
342 |
+
"step": 1350
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 8.23,
|
346 |
+
"learning_rate": 9.078947368421054e-05,
|
347 |
+
"loss": 0.0285,
|
348 |
+
"step": 1375
|
349 |
+
},
|
350 |
+
{
|
351 |
+
"epoch": 8.38,
|
352 |
+
"learning_rate": 9.052631578947369e-05,
|
353 |
+
"loss": 0.0258,
|
354 |
+
"step": 1400
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 8.53,
|
358 |
+
"learning_rate": 9.026315789473685e-05,
|
359 |
+
"loss": 0.0262,
|
360 |
+
"step": 1425
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 8.68,
|
364 |
+
"learning_rate": 9e-05,
|
365 |
+
"loss": 0.0256,
|
366 |
+
"step": 1450
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 8.83,
|
370 |
+
"learning_rate": 8.973684210526316e-05,
|
371 |
+
"loss": 0.0286,
|
372 |
+
"step": 1475
|
373 |
+
},
|
374 |
+
{
|
375 |
+
"epoch": 8.98,
|
376 |
+
"learning_rate": 8.947368421052632e-05,
|
377 |
+
"loss": 0.0265,
|
378 |
+
"step": 1500
|
379 |
+
},
|
380 |
+
{
|
381 |
+
"epoch": 9.13,
|
382 |
+
"learning_rate": 8.921052631578948e-05,
|
383 |
+
"loss": 0.0208,
|
384 |
+
"step": 1525
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 9.28,
|
388 |
+
"learning_rate": 8.894736842105263e-05,
|
389 |
+
"loss": 0.0237,
|
390 |
+
"step": 1550
|
391 |
+
},
|
392 |
+
{
|
393 |
+
"epoch": 9.43,
|
394 |
+
"learning_rate": 8.868421052631579e-05,
|
395 |
+
"loss": 0.0235,
|
396 |
+
"step": 1575
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 9.58,
|
400 |
+
"learning_rate": 8.842105263157894e-05,
|
401 |
+
"loss": 0.0224,
|
402 |
+
"step": 1600
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 9.73,
|
406 |
+
"learning_rate": 8.81578947368421e-05,
|
407 |
+
"loss": 0.024,
|
408 |
+
"step": 1625
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 9.88,
|
412 |
+
"learning_rate": 8.789473684210526e-05,
|
413 |
+
"loss": 0.0246,
|
414 |
+
"step": 1650
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 10.03,
|
418 |
+
"learning_rate": 8.763157894736841e-05,
|
419 |
+
"loss": 0.0248,
|
420 |
+
"step": 1675
|
421 |
+
},
|
422 |
+
{
|
423 |
+
"epoch": 10.18,
|
424 |
+
"learning_rate": 8.736842105263158e-05,
|
425 |
+
"loss": 0.0173,
|
426 |
+
"step": 1700
|
427 |
+
},
|
428 |
+
{
|
429 |
+
"epoch": 10.33,
|
430 |
+
"learning_rate": 8.710526315789474e-05,
|
431 |
+
"loss": 0.0174,
|
432 |
+
"step": 1725
|
433 |
+
},
|
434 |
+
{
|
435 |
+
"epoch": 10.48,
|
436 |
+
"learning_rate": 8.68421052631579e-05,
|
437 |
+
"loss": 0.0215,
|
438 |
+
"step": 1750
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 10.63,
|
442 |
+
"learning_rate": 8.657894736842105e-05,
|
443 |
+
"loss": 0.0236,
|
444 |
+
"step": 1775
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 10.78,
|
448 |
+
"learning_rate": 8.631578947368421e-05,
|
449 |
+
"loss": 0.0203,
|
450 |
+
"step": 1800
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 10.93,
|
454 |
+
"learning_rate": 8.605263157894738e-05,
|
455 |
+
"loss": 0.0192,
|
456 |
+
"step": 1825
|
457 |
+
},
|
458 |
+
{
|
459 |
+
"epoch": 11.08,
|
460 |
+
"learning_rate": 8.578947368421054e-05,
|
461 |
+
"loss": 0.0172,
|
462 |
+
"step": 1850
|
463 |
+
},
|
464 |
+
{
|
465 |
+
"epoch": 11.23,
|
466 |
+
"learning_rate": 8.552631578947369e-05,
|
467 |
+
"loss": 0.0197,
|
468 |
+
"step": 1875
|
469 |
+
},
|
470 |
+
{
|
471 |
+
"epoch": 11.38,
|
472 |
+
"learning_rate": 8.526315789473685e-05,
|
473 |
+
"loss": 0.0188,
|
474 |
+
"step": 1900
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 11.53,
|
478 |
+
"learning_rate": 8.5e-05,
|
479 |
+
"loss": 0.0197,
|
480 |
+
"step": 1925
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"epoch": 11.68,
|
484 |
+
"learning_rate": 8.473684210526316e-05,
|
485 |
+
"loss": 0.0197,
|
486 |
+
"step": 1950
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 11.83,
|
490 |
+
"learning_rate": 8.447368421052632e-05,
|
491 |
+
"loss": 0.0212,
|
492 |
+
"step": 1975
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 11.98,
|
496 |
+
"learning_rate": 8.421052631578948e-05,
|
497 |
+
"loss": 0.0183,
|
498 |
+
"step": 2000
|
499 |
+
},
|
500 |
+
{
|
501 |
+
"epoch": 11.98,
|
502 |
+
"eval_loss": 0.49957072734832764,
|
503 |
+
"eval_runtime": 578.898,
|
504 |
+
"eval_samples_per_second": 0.724,
|
505 |
+
"eval_steps_per_second": 0.092,
|
506 |
+
"eval_wer": 38.2982234200539,
|
507 |
+
"step": 2000
|
508 |
}
|
509 |
],
|
510 |
"logging_steps": 25,
|
|
|
512 |
"num_input_tokens_seen": 0,
|
513 |
"num_train_epochs": 60,
|
514 |
"save_steps": 1000,
|
515 |
+
"total_flos": 1.0860782836580352e+20,
|
516 |
"train_batch_size": 16,
|
517 |
"trial_name": null,
|
518 |
"trial_params": null
|