Training in progress, step 75, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 47860
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8430047d8b90d42bd78b0782f3678dbe6ea191029aa9ec20961ed733e662fe9d
|
3 |
size 47860
|
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 sha256:6fd333563d341e5baa5c8b808fe012ad11a41788bafd15e1988d5d595a4760af
|
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:babd43118aa66a4f5266d730539cf7f09611158b169d9e63dbcb83f6bbaa8626
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 25,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -381,6 +381,189 @@
|
|
381 |
"eval_samples_per_second": 42.277,
|
382 |
"eval_steps_per_second": 21.139,
|
383 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
384 |
}
|
385 |
],
|
386 |
"logging_steps": 1,
|
@@ -395,12 +578,12 @@
|
|
395 |
"should_evaluate": false,
|
396 |
"should_log": false,
|
397 |
"should_save": true,
|
398 |
-
"should_training_stop":
|
399 |
},
|
400 |
"attributes": {}
|
401 |
}
|
402 |
},
|
403 |
-
"total_flos":
|
404 |
"train_batch_size": 2,
|
405 |
"trial_name": null,
|
406 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0026279942709724895,
|
5 |
"eval_steps": 25,
|
6 |
+
"global_step": 75,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
381 |
"eval_samples_per_second": 42.277,
|
382 |
"eval_steps_per_second": 21.139,
|
383 |
"step": 50
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 0.0017870361042612926,
|
387 |
+
"grad_norm": NaN,
|
388 |
+
"learning_rate": 5.000000000000002e-05,
|
389 |
+
"loss": 0.0,
|
390 |
+
"step": 51
|
391 |
+
},
|
392 |
+
{
|
393 |
+
"epoch": 0.0018220760278742593,
|
394 |
+
"grad_norm": NaN,
|
395 |
+
"learning_rate": 4.6270039165317605e-05,
|
396 |
+
"loss": 0.0,
|
397 |
+
"step": 52
|
398 |
+
},
|
399 |
+
{
|
400 |
+
"epoch": 0.0018571159514872257,
|
401 |
+
"grad_norm": NaN,
|
402 |
+
"learning_rate": 4.264235636489542e-05,
|
403 |
+
"loss": 0.0,
|
404 |
+
"step": 53
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 0.0018921558751001924,
|
408 |
+
"grad_norm": NaN,
|
409 |
+
"learning_rate": 3.9123857099127936e-05,
|
410 |
+
"loss": 0.0,
|
411 |
+
"step": 54
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 0.0019271957987131588,
|
415 |
+
"grad_norm": NaN,
|
416 |
+
"learning_rate": 3.5721239031346066e-05,
|
417 |
+
"loss": 0.0,
|
418 |
+
"step": 55
|
419 |
+
},
|
420 |
+
{
|
421 |
+
"epoch": 0.0019622357223261252,
|
422 |
+
"grad_norm": NaN,
|
423 |
+
"learning_rate": 3.244097923843398e-05,
|
424 |
+
"loss": 0.0,
|
425 |
+
"step": 56
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 0.001997275645939092,
|
429 |
+
"grad_norm": NaN,
|
430 |
+
"learning_rate": 2.9289321881345254e-05,
|
431 |
+
"loss": 0.0,
|
432 |
+
"step": 57
|
433 |
+
},
|
434 |
+
{
|
435 |
+
"epoch": 0.0020323155695520585,
|
436 |
+
"grad_norm": NaN,
|
437 |
+
"learning_rate": 2.6272266318987603e-05,
|
438 |
+
"loss": 0.0,
|
439 |
+
"step": 58
|
440 |
+
},
|
441 |
+
{
|
442 |
+
"epoch": 0.0020673554931650248,
|
443 |
+
"grad_norm": NaN,
|
444 |
+
"learning_rate": 2.339555568810221e-05,
|
445 |
+
"loss": 0.0,
|
446 |
+
"step": 59
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.0021023954167779914,
|
450 |
+
"grad_norm": NaN,
|
451 |
+
"learning_rate": 2.0664665970876496e-05,
|
452 |
+
"loss": 0.0,
|
453 |
+
"step": 60
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.002137435340390958,
|
457 |
+
"grad_norm": NaN,
|
458 |
+
"learning_rate": 1.808479557110081e-05,
|
459 |
+
"loss": 0.0,
|
460 |
+
"step": 61
|
461 |
+
},
|
462 |
+
{
|
463 |
+
"epoch": 0.0021724752640039243,
|
464 |
+
"grad_norm": NaN,
|
465 |
+
"learning_rate": 1.566085541871145e-05,
|
466 |
+
"loss": 0.0,
|
467 |
+
"step": 62
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 0.002207515187616891,
|
471 |
+
"grad_norm": NaN,
|
472 |
+
"learning_rate": 1.339745962155613e-05,
|
473 |
+
"loss": 0.0,
|
474 |
+
"step": 63
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 0.0022425551112298576,
|
478 |
+
"grad_norm": NaN,
|
479 |
+
"learning_rate": 1.129891668217783e-05,
|
480 |
+
"loss": 0.0,
|
481 |
+
"step": 64
|
482 |
+
},
|
483 |
+
{
|
484 |
+
"epoch": 0.0022775950348428243,
|
485 |
+
"grad_norm": NaN,
|
486 |
+
"learning_rate": 9.369221296335006e-06,
|
487 |
+
"loss": 0.0,
|
488 |
+
"step": 65
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 0.0023126349584557905,
|
492 |
+
"grad_norm": NaN,
|
493 |
+
"learning_rate": 7.612046748871327e-06,
|
494 |
+
"loss": 0.0,
|
495 |
+
"step": 66
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 0.002347674882068757,
|
499 |
+
"grad_norm": NaN,
|
500 |
+
"learning_rate": 6.030737921409169e-06,
|
501 |
+
"loss": 0.0,
|
502 |
+
"step": 67
|
503 |
+
},
|
504 |
+
{
|
505 |
+
"epoch": 0.0023827148056817238,
|
506 |
+
"grad_norm": NaN,
|
507 |
+
"learning_rate": 4.628304925177318e-06,
|
508 |
+
"loss": 0.0,
|
509 |
+
"step": 68
|
510 |
+
},
|
511 |
+
{
|
512 |
+
"epoch": 0.00241775472929469,
|
513 |
+
"grad_norm": NaN,
|
514 |
+
"learning_rate": 3.40741737109318e-06,
|
515 |
+
"loss": 0.0,
|
516 |
+
"step": 69
|
517 |
+
},
|
518 |
+
{
|
519 |
+
"epoch": 0.0024527946529076567,
|
520 |
+
"grad_norm": NaN,
|
521 |
+
"learning_rate": 2.3703992880066638e-06,
|
522 |
+
"loss": 0.0,
|
523 |
+
"step": 70
|
524 |
+
},
|
525 |
+
{
|
526 |
+
"epoch": 0.0024878345765206233,
|
527 |
+
"grad_norm": NaN,
|
528 |
+
"learning_rate": 1.5192246987791981e-06,
|
529 |
+
"loss": 0.0,
|
530 |
+
"step": 71
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 0.0025228745001335895,
|
534 |
+
"grad_norm": NaN,
|
535 |
+
"learning_rate": 8.555138626189618e-07,
|
536 |
+
"loss": 0.0,
|
537 |
+
"step": 72
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 0.002557914423746556,
|
541 |
+
"grad_norm": NaN,
|
542 |
+
"learning_rate": 3.805301908254455e-07,
|
543 |
+
"loss": 0.0,
|
544 |
+
"step": 73
|
545 |
+
},
|
546 |
+
{
|
547 |
+
"epoch": 0.002592954347359523,
|
548 |
+
"grad_norm": NaN,
|
549 |
+
"learning_rate": 9.517784181422019e-08,
|
550 |
+
"loss": 0.0,
|
551 |
+
"step": 74
|
552 |
+
},
|
553 |
+
{
|
554 |
+
"epoch": 0.0026279942709724895,
|
555 |
+
"grad_norm": NaN,
|
556 |
+
"learning_rate": 0.0,
|
557 |
+
"loss": 0.0,
|
558 |
+
"step": 75
|
559 |
+
},
|
560 |
+
{
|
561 |
+
"epoch": 0.0026279942709724895,
|
562 |
+
"eval_loss": NaN,
|
563 |
+
"eval_runtime": 568.4882,
|
564 |
+
"eval_samples_per_second": 42.275,
|
565 |
+
"eval_steps_per_second": 21.139,
|
566 |
+
"step": 75
|
567 |
}
|
568 |
],
|
569 |
"logging_steps": 1,
|
|
|
578 |
"should_evaluate": false,
|
579 |
"should_log": false,
|
580 |
"should_save": true,
|
581 |
+
"should_training_stop": true
|
582 |
},
|
583 |
"attributes": {}
|
584 |
}
|
585 |
},
|
586 |
+
"total_flos": 92484403200.0,
|
587 |
"train_batch_size": 2,
|
588 |
"trial_name": null,
|
589 |
"trial_params": null
|