marinone94
commited on
Commit
β’
4807cf3
1
Parent(s):
3a3c417
Training in progress, step 1300
Browse files- {checkpoint-1000 β checkpoint-1300}/config.json +0 -0
- {checkpoint-1000 β checkpoint-1300}/optimizer.pt +1 -1
- {checkpoint-1000 β checkpoint-1300}/preprocessor_config.json +0 -0
- {checkpoint-1000 β checkpoint-1300}/pytorch_model.bin +1 -1
- {checkpoint-1000 β checkpoint-1300}/rng_state.pth +1 -1
- {checkpoint-1000 β checkpoint-1300}/scaler.pt +1 -1
- {checkpoint-1000 β checkpoint-1300}/scheduler.pt +1 -1
- {checkpoint-1000 β checkpoint-1300}/trainer_state.json +120 -3
- {checkpoint-1000 β checkpoint-1300}/training_args.bin +0 -0
- pytorch_model.bin +1 -1
{checkpoint-1000 β checkpoint-1300}/config.json
RENAMED
File without changes
|
{checkpoint-1000 β checkpoint-1300}/optimizer.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2490337809
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9e0206a01417bef4d11f2a95335ad840a1721c6f678b089bdf7abdcafa51906
|
3 |
size 2490337809
|
{checkpoint-1000 β checkpoint-1300}/preprocessor_config.json
RENAMED
File without changes
|
{checkpoint-1000 β checkpoint-1300}/pytorch_model.bin
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262063089
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c32f633d461c6e73651e2cad62b1f33ec6fa6c731ff331293bd3ea3ab178533
|
3 |
size 1262063089
|
{checkpoint-1000 β checkpoint-1300}/rng_state.pth
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14567
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4a3aa97bd65a21ca0d5bb2262a5c675bb5847b62e059527a92ac37b03aa6555
|
3 |
size 14567
|
{checkpoint-1000 β checkpoint-1300}/scaler.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f30aff976137ec8a8f02bc3ed293492299fd63571aec46a1b1426491c85fe082
|
3 |
size 559
|
{checkpoint-1000 β checkpoint-1300}/scheduler.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49a74fb1217961243834b43dc5bb531167031d0d67fb9ade238f561b7c566d57
|
3 |
size 623
|
{checkpoint-1000 β checkpoint-1300}/trainer_state.json
RENAMED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -396,11 +396,128 @@
|
|
396 |
"eval_steps_per_second": 0.748,
|
397 |
"eval_wer": 0.7832245245529378,
|
398 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
399 |
}
|
400 |
],
|
401 |
"max_steps": 4550,
|
402 |
"num_train_epochs": 50,
|
403 |
-
"total_flos":
|
404 |
"trial_name": null,
|
405 |
"trial_params": null
|
406 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 14.28415300546448,
|
5 |
+
"global_step": 1300,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
396 |
"eval_steps_per_second": 0.748,
|
397 |
"eval_wer": 0.7832245245529378,
|
398 |
"step": 1000
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 11.21,
|
402 |
+
"learning_rate": 0.0001275,
|
403 |
+
"loss": 1.8155,
|
404 |
+
"step": 1020
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 11.43,
|
408 |
+
"learning_rate": 0.00013000000000000002,
|
409 |
+
"loss": 1.6767,
|
410 |
+
"step": 1040
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 11.64,
|
414 |
+
"learning_rate": 0.00013250000000000002,
|
415 |
+
"loss": 1.5184,
|
416 |
+
"step": 1060
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 11.86,
|
420 |
+
"learning_rate": 0.000135,
|
421 |
+
"loss": 1.4505,
|
422 |
+
"step": 1080
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 12.09,
|
426 |
+
"learning_rate": 0.0001375,
|
427 |
+
"loss": 1.4286,
|
428 |
+
"step": 1100
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 12.09,
|
432 |
+
"eval_loss": 0.4074769914150238,
|
433 |
+
"eval_runtime": 194.7798,
|
434 |
+
"eval_samples_per_second": 24.864,
|
435 |
+
"eval_steps_per_second": 0.78,
|
436 |
+
"eval_wer": 0.37964802724950325,
|
437 |
+
"step": 1100
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 12.31,
|
441 |
+
"learning_rate": 0.00014000000000000001,
|
442 |
+
"loss": 1.3478,
|
443 |
+
"step": 1120
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 12.52,
|
447 |
+
"learning_rate": 0.0001425,
|
448 |
+
"loss": 1.3164,
|
449 |
+
"step": 1140
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 12.74,
|
453 |
+
"learning_rate": 0.000145,
|
454 |
+
"loss": 1.269,
|
455 |
+
"step": 1160
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 12.96,
|
459 |
+
"learning_rate": 0.0001475,
|
460 |
+
"loss": 1.2292,
|
461 |
+
"step": 1180
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 13.19,
|
465 |
+
"learning_rate": 0.00015,
|
466 |
+
"loss": 1.2229,
|
467 |
+
"step": 1200
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 13.19,
|
471 |
+
"eval_loss": 0.28933778405189514,
|
472 |
+
"eval_runtime": 192.6398,
|
473 |
+
"eval_samples_per_second": 25.14,
|
474 |
+
"eval_steps_per_second": 0.789,
|
475 |
+
"eval_wer": 0.26520011353959694,
|
476 |
+
"step": 1200
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 13.4,
|
480 |
+
"learning_rate": 0.0001525,
|
481 |
+
"loss": 1.182,
|
482 |
+
"step": 1220
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 13.62,
|
486 |
+
"learning_rate": 0.000155,
|
487 |
+
"loss": 1.1768,
|
488 |
+
"step": 1240
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 13.84,
|
492 |
+
"learning_rate": 0.0001575,
|
493 |
+
"loss": 1.1534,
|
494 |
+
"step": 1260
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 14.07,
|
498 |
+
"learning_rate": 0.00016,
|
499 |
+
"loss": 1.1832,
|
500 |
+
"step": 1280
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 14.28,
|
504 |
+
"learning_rate": 0.00016250000000000002,
|
505 |
+
"loss": 1.1106,
|
506 |
+
"step": 1300
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 14.28,
|
510 |
+
"eval_loss": 0.24685777723789215,
|
511 |
+
"eval_runtime": 198.5067,
|
512 |
+
"eval_samples_per_second": 24.397,
|
513 |
+
"eval_steps_per_second": 0.766,
|
514 |
+
"eval_wer": 0.2253760999148453,
|
515 |
+
"step": 1300
|
516 |
}
|
517 |
],
|
518 |
"max_steps": 4550,
|
519 |
"num_train_epochs": 50,
|
520 |
+
"total_flos": 2.013668332353175e+19,
|
521 |
"trial_name": null,
|
522 |
"trial_params": null
|
523 |
}
|
{checkpoint-1000 β checkpoint-1300}/training_args.bin
RENAMED
File without changes
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262063089
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c32f633d461c6e73651e2cad62b1f33ec6fa6c731ff331293bd3ea3ab178533
|
3 |
size 1262063089
|