elsayedissa
commited on
Commit
·
38f73f2
1
Parent(s):
22fd223
Training in progress, step 2000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +252 -3
- pytorch_model.bin +1 -1
- runs/Apr09_14-45-21_gpu07.cyverse.org/events.out.tfevents.1681076808.gpu07.cyverse.org.48142.0 +2 -2
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2524414853
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c22fbe8882f8237fdad9f99aee540b3eee7a95a06ed453d7dbf634c5e50ad4a
|
3 |
size 2524414853
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262229869
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7766aaba3075cb7cda575d932f2711e23f9758a8c4cf6beb80955eb66a503a07
|
3 |
size 1262229869
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14639
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f76adf0ffd2c50b454ef9f773fefb9715aac5ca126b5dc5340154393be241e4a
|
3 |
size 14639
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12c4c42f5c0f6326c3478ca4b895e02f447517c1b69320adf8921f0dc4132efb
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": 0.07856032524213799,
|
3 |
"best_model_checkpoint": "./wav2vec2-xls-r-300m-ar/checkpoint-1000",
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -255,11 +255,260 @@
|
|
255 |
"eval_steps_per_second": 1.116,
|
256 |
"eval_wer": 0.07856032524213799,
|
257 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
258 |
}
|
259 |
],
|
260 |
"max_steps": 10000,
|
261 |
"num_train_epochs": 89,
|
262 |
-
"total_flos":
|
263 |
"trial_name": null,
|
264 |
"trial_params": null
|
265 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 0.07856032524213799,
|
3 |
"best_model_checkpoint": "./wav2vec2-xls-r-300m-ar/checkpoint-1000",
|
4 |
+
"epoch": 17.699115044247787,
|
5 |
+
"global_step": 2000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
255 |
"eval_steps_per_second": 1.116,
|
256 |
"eval_wer": 0.07856032524213799,
|
257 |
"step": 1000
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 9.07,
|
261 |
+
"learning_rate": 0.00028342105263157895,
|
262 |
+
"loss": 0.0863,
|
263 |
+
"step": 1025
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 9.29,
|
267 |
+
"learning_rate": 0.0002826315789473684,
|
268 |
+
"loss": 0.0638,
|
269 |
+
"step": 1050
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 9.51,
|
273 |
+
"learning_rate": 0.00028184210526315787,
|
274 |
+
"loss": 0.0604,
|
275 |
+
"step": 1075
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 9.73,
|
279 |
+
"learning_rate": 0.00028105263157894735,
|
280 |
+
"loss": 0.0621,
|
281 |
+
"step": 1100
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 9.96,
|
285 |
+
"learning_rate": 0.00028026315789473683,
|
286 |
+
"loss": 0.0707,
|
287 |
+
"step": 1125
|
288 |
+
},
|
289 |
+
{
|
290 |
+
"epoch": 10.18,
|
291 |
+
"learning_rate": 0.0002794736842105263,
|
292 |
+
"loss": 0.0799,
|
293 |
+
"step": 1150
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 10.4,
|
297 |
+
"learning_rate": 0.00027868421052631574,
|
298 |
+
"loss": 0.0694,
|
299 |
+
"step": 1175
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 10.62,
|
303 |
+
"learning_rate": 0.00027789473684210523,
|
304 |
+
"loss": 0.0655,
|
305 |
+
"step": 1200
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 10.84,
|
309 |
+
"learning_rate": 0.0002771052631578947,
|
310 |
+
"loss": 0.0776,
|
311 |
+
"step": 1225
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 11.06,
|
315 |
+
"learning_rate": 0.0002763157894736842,
|
316 |
+
"loss": 0.0582,
|
317 |
+
"step": 1250
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 11.28,
|
321 |
+
"learning_rate": 0.0002755263157894737,
|
322 |
+
"loss": 0.0547,
|
323 |
+
"step": 1275
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 11.5,
|
327 |
+
"learning_rate": 0.0002747368421052631,
|
328 |
+
"loss": 0.0597,
|
329 |
+
"step": 1300
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 11.73,
|
333 |
+
"learning_rate": 0.0002739473684210526,
|
334 |
+
"loss": 0.0492,
|
335 |
+
"step": 1325
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 11.95,
|
339 |
+
"learning_rate": 0.00027315789473684207,
|
340 |
+
"loss": 0.0699,
|
341 |
+
"step": 1350
|
342 |
+
},
|
343 |
+
{
|
344 |
+
"epoch": 12.17,
|
345 |
+
"learning_rate": 0.00027236842105263155,
|
346 |
+
"loss": 0.0594,
|
347 |
+
"step": 1375
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 12.39,
|
351 |
+
"learning_rate": 0.00027157894736842104,
|
352 |
+
"loss": 0.0541,
|
353 |
+
"step": 1400
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 12.61,
|
357 |
+
"learning_rate": 0.0002707894736842105,
|
358 |
+
"loss": 0.0522,
|
359 |
+
"step": 1425
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 12.83,
|
363 |
+
"learning_rate": 0.00027,
|
364 |
+
"loss": 0.0645,
|
365 |
+
"step": 1450
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 13.05,
|
369 |
+
"learning_rate": 0.00026921052631578943,
|
370 |
+
"loss": 0.0583,
|
371 |
+
"step": 1475
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 13.27,
|
375 |
+
"learning_rate": 0.0002684210526315789,
|
376 |
+
"loss": 0.0443,
|
377 |
+
"step": 1500
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 13.5,
|
381 |
+
"learning_rate": 0.0002676315789473684,
|
382 |
+
"loss": 0.0548,
|
383 |
+
"step": 1525
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 13.72,
|
387 |
+
"learning_rate": 0.0002668421052631579,
|
388 |
+
"loss": 0.0484,
|
389 |
+
"step": 1550
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 13.94,
|
393 |
+
"learning_rate": 0.00026605263157894736,
|
394 |
+
"loss": 0.0775,
|
395 |
+
"step": 1575
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 14.16,
|
399 |
+
"learning_rate": 0.0002652631578947368,
|
400 |
+
"loss": 0.0554,
|
401 |
+
"step": 1600
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 14.38,
|
405 |
+
"learning_rate": 0.0002644736842105263,
|
406 |
+
"loss": 0.0456,
|
407 |
+
"step": 1625
|
408 |
+
},
|
409 |
+
{
|
410 |
+
"epoch": 14.6,
|
411 |
+
"learning_rate": 0.00026368421052631576,
|
412 |
+
"loss": 0.0563,
|
413 |
+
"step": 1650
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 14.82,
|
417 |
+
"learning_rate": 0.00026289473684210524,
|
418 |
+
"loss": 0.0493,
|
419 |
+
"step": 1675
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 15.04,
|
423 |
+
"learning_rate": 0.0002621052631578947,
|
424 |
+
"loss": 0.0452,
|
425 |
+
"step": 1700
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 15.27,
|
429 |
+
"learning_rate": 0.0002613157894736842,
|
430 |
+
"loss": 0.0389,
|
431 |
+
"step": 1725
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 15.49,
|
435 |
+
"learning_rate": 0.0002605263157894737,
|
436 |
+
"loss": 0.0436,
|
437 |
+
"step": 1750
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 15.71,
|
441 |
+
"learning_rate": 0.0002597368421052631,
|
442 |
+
"loss": 0.0407,
|
443 |
+
"step": 1775
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 15.93,
|
447 |
+
"learning_rate": 0.0002589473684210526,
|
448 |
+
"loss": 0.0448,
|
449 |
+
"step": 1800
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 16.15,
|
453 |
+
"learning_rate": 0.0002581578947368421,
|
454 |
+
"loss": 0.0457,
|
455 |
+
"step": 1825
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 16.37,
|
459 |
+
"learning_rate": 0.00025736842105263157,
|
460 |
+
"loss": 0.0461,
|
461 |
+
"step": 1850
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 16.59,
|
465 |
+
"learning_rate": 0.00025657894736842105,
|
466 |
+
"loss": 0.0452,
|
467 |
+
"step": 1875
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 16.81,
|
471 |
+
"learning_rate": 0.0002557894736842105,
|
472 |
+
"loss": 0.0484,
|
473 |
+
"step": 1900
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 17.04,
|
477 |
+
"learning_rate": 0.00025499999999999996,
|
478 |
+
"loss": 0.0376,
|
479 |
+
"step": 1925
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 17.26,
|
483 |
+
"learning_rate": 0.00025421052631578945,
|
484 |
+
"loss": 0.0409,
|
485 |
+
"step": 1950
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 17.48,
|
489 |
+
"learning_rate": 0.00025342105263157893,
|
490 |
+
"loss": 0.0315,
|
491 |
+
"step": 1975
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 17.7,
|
495 |
+
"learning_rate": 0.00025263157894736836,
|
496 |
+
"loss": 0.0396,
|
497 |
+
"step": 2000
|
498 |
+
},
|
499 |
+
{
|
500 |
+
"epoch": 17.7,
|
501 |
+
"eval_loss": 0.21985749900341034,
|
502 |
+
"eval_runtime": 11.0577,
|
503 |
+
"eval_samples_per_second": 9.043,
|
504 |
+
"eval_steps_per_second": 1.176,
|
505 |
+
"eval_wer": 0.08071266292000479,
|
506 |
+
"step": 2000
|
507 |
}
|
508 |
],
|
509 |
"max_steps": 10000,
|
510 |
"num_train_epochs": 89,
|
511 |
+
"total_flos": 7.898916075572138e+18,
|
512 |
"trial_name": null,
|
513 |
"trial_params": null
|
514 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262229869
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7766aaba3075cb7cda575d932f2711e23f9758a8c4cf6beb80955eb66a503a07
|
3 |
size 1262229869
|
runs/Apr09_14-45-21_gpu07.cyverse.org/events.out.tfevents.1681076808.gpu07.cyverse.org.48142.0
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 sha256:65c3d972900bf03bff1b80a32a9fbc17a6bd3bf805d064d49e97a10dc60048cd
|
3 |
+
size 18578
|