Training in progress, step 100, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 522227376
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f7faaf0bc6dac6049f37f87c33fe8c933a82138fc1080ba1670ec713471c635
|
3 |
size 522227376
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1044597498
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fcc759905c574245e98d0993ca268bc91db8de18efb1af55d228b0b70e73dc4
|
3 |
size 1044597498
|
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 sha256:72217cd5204ddcebe28b7c1e0c0ca3a07c776eb9b8dd6e6509adae29fdf64235
|
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 sha256:03ad66011cfc1fc727a51190602a41adc332b48eeef62a5ee87c2ca9f9b90b2b
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 50,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -373,6 +373,364 @@
|
|
373 |
"eval_samples_per_second": 4.337,
|
374 |
"eval_steps_per_second": 1.084,
|
375 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
376 |
}
|
377 |
],
|
378 |
"logging_steps": 1,
|
@@ -396,12 +754,12 @@
|
|
396 |
"should_evaluate": false,
|
397 |
"should_log": false,
|
398 |
"should_save": true,
|
399 |
-
"should_training_stop":
|
400 |
},
|
401 |
"attributes": {}
|
402 |
}
|
403 |
},
|
404 |
-
"total_flos":
|
405 |
"train_batch_size": 4,
|
406 |
"trial_name": null,
|
407 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.933211624622345,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
4 |
+
"epoch": 0.09000900090009001,
|
5 |
"eval_steps": 50,
|
6 |
+
"global_step": 100,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
373 |
"eval_samples_per_second": 4.337,
|
374 |
"eval_steps_per_second": 1.084,
|
375 |
"step": 50
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.04590459045904591,
|
379 |
+
"grad_norm": 5.705034255981445,
|
380 |
+
"learning_rate": 2.3816778784387097e-05,
|
381 |
+
"loss": 1.3283,
|
382 |
+
"step": 51
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 0.046804680468046804,
|
386 |
+
"grad_norm": 3.1250901222229004,
|
387 |
+
"learning_rate": 2.3263454721781537e-05,
|
388 |
+
"loss": 1.1372,
|
389 |
+
"step": 52
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 0.04770477047704771,
|
393 |
+
"grad_norm": 3.5653185844421387,
|
394 |
+
"learning_rate": 2.2693489161088592e-05,
|
395 |
+
"loss": 1.1422,
|
396 |
+
"step": 53
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 0.048604860486048604,
|
400 |
+
"grad_norm": 2.5940499305725098,
|
401 |
+
"learning_rate": 2.210802993709498e-05,
|
402 |
+
"loss": 1.0782,
|
403 |
+
"step": 54
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 0.04950495049504951,
|
407 |
+
"grad_norm": 1.700508713722229,
|
408 |
+
"learning_rate": 2.1508256086763372e-05,
|
409 |
+
"loss": 0.8352,
|
410 |
+
"step": 55
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.050405040504050404,
|
414 |
+
"grad_norm": 1.5756418704986572,
|
415 |
+
"learning_rate": 2.0895375474808857e-05,
|
416 |
+
"loss": 1.3823,
|
417 |
+
"step": 56
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.05130513051305131,
|
421 |
+
"grad_norm": 1.4209038019180298,
|
422 |
+
"learning_rate": 2.0270622361220143e-05,
|
423 |
+
"loss": 1.1883,
|
424 |
+
"step": 57
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 0.052205220522052204,
|
428 |
+
"grad_norm": 1.3939372301101685,
|
429 |
+
"learning_rate": 1.963525491562421e-05,
|
430 |
+
"loss": 1.0329,
|
431 |
+
"step": 58
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.05310531053105311,
|
435 |
+
"grad_norm": 1.2505179643630981,
|
436 |
+
"learning_rate": 1.8990552683500128e-05,
|
437 |
+
"loss": 1.2086,
|
438 |
+
"step": 59
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 0.054005400540054004,
|
442 |
+
"grad_norm": 1.3785752058029175,
|
443 |
+
"learning_rate": 1.8337814009344716e-05,
|
444 |
+
"loss": 1.0227,
|
445 |
+
"step": 60
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"epoch": 0.05490549054905491,
|
449 |
+
"grad_norm": 1.367503046989441,
|
450 |
+
"learning_rate": 1.767835342197955e-05,
|
451 |
+
"loss": 1.609,
|
452 |
+
"step": 61
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.0558055805580558,
|
456 |
+
"grad_norm": 1.2117955684661865,
|
457 |
+
"learning_rate": 1.7013498987264832e-05,
|
458 |
+
"loss": 1.3177,
|
459 |
+
"step": 62
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.05670567056705671,
|
463 |
+
"grad_norm": 1.0135844945907593,
|
464 |
+
"learning_rate": 1.6344589633551502e-05,
|
465 |
+
"loss": 1.4245,
|
466 |
+
"step": 63
|
467 |
+
},
|
468 |
+
{
|
469 |
+
"epoch": 0.0576057605760576,
|
470 |
+
"grad_norm": 1.1287009716033936,
|
471 |
+
"learning_rate": 1.5672972455257726e-05,
|
472 |
+
"loss": 1.5013,
|
473 |
+
"step": 64
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 0.05850585058505851,
|
477 |
+
"grad_norm": 1.2982141971588135,
|
478 |
+
"learning_rate": 1.5e-05,
|
479 |
+
"loss": 1.5079,
|
480 |
+
"step": 65
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"epoch": 0.0594059405940594,
|
484 |
+
"grad_norm": 1.1244807243347168,
|
485 |
+
"learning_rate": 1.4327027544742281e-05,
|
486 |
+
"loss": 2.046,
|
487 |
+
"step": 66
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 0.06030603060306031,
|
491 |
+
"grad_norm": 0.9998478293418884,
|
492 |
+
"learning_rate": 1.36554103664485e-05,
|
493 |
+
"loss": 1.3912,
|
494 |
+
"step": 67
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.0612061206120612,
|
498 |
+
"grad_norm": 1.026103138923645,
|
499 |
+
"learning_rate": 1.2986501012735174e-05,
|
500 |
+
"loss": 1.6617,
|
501 |
+
"step": 68
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.062106210621062106,
|
505 |
+
"grad_norm": 1.0572633743286133,
|
506 |
+
"learning_rate": 1.2321646578020452e-05,
|
507 |
+
"loss": 1.7724,
|
508 |
+
"step": 69
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 0.063006300630063,
|
512 |
+
"grad_norm": 1.105764389038086,
|
513 |
+
"learning_rate": 1.1662185990655285e-05,
|
514 |
+
"loss": 1.4844,
|
515 |
+
"step": 70
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 0.0639063906390639,
|
519 |
+
"grad_norm": 0.9881569147109985,
|
520 |
+
"learning_rate": 1.1009447316499875e-05,
|
521 |
+
"loss": 1.5753,
|
522 |
+
"step": 71
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 0.06480648064806481,
|
526 |
+
"grad_norm": 0.9760916829109192,
|
527 |
+
"learning_rate": 1.036474508437579e-05,
|
528 |
+
"loss": 1.7407,
|
529 |
+
"step": 72
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 0.06570657065706571,
|
533 |
+
"grad_norm": 0.998174250125885,
|
534 |
+
"learning_rate": 9.729377638779859e-06,
|
535 |
+
"loss": 1.734,
|
536 |
+
"step": 73
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.0666066606660666,
|
540 |
+
"grad_norm": 0.9511818289756775,
|
541 |
+
"learning_rate": 9.104624525191147e-06,
|
542 |
+
"loss": 1.6426,
|
543 |
+
"step": 74
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.0675067506750675,
|
547 |
+
"grad_norm": 0.995963454246521,
|
548 |
+
"learning_rate": 8.491743913236629e-06,
|
549 |
+
"loss": 1.8299,
|
550 |
+
"step": 75
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 0.06840684068406841,
|
554 |
+
"grad_norm": 0.9901272058486938,
|
555 |
+
"learning_rate": 7.89197006290502e-06,
|
556 |
+
"loss": 1.8434,
|
557 |
+
"step": 76
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 0.06930693069306931,
|
561 |
+
"grad_norm": 1.0815800428390503,
|
562 |
+
"learning_rate": 7.30651083891141e-06,
|
563 |
+
"loss": 2.1484,
|
564 |
+
"step": 77
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.0702070207020702,
|
568 |
+
"grad_norm": 1.1151647567749023,
|
569 |
+
"learning_rate": 6.736545278218464e-06,
|
570 |
+
"loss": 2.0096,
|
571 |
+
"step": 78
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 0.0711071107110711,
|
575 |
+
"grad_norm": 0.9471780061721802,
|
576 |
+
"learning_rate": 6.1832212156129045e-06,
|
577 |
+
"loss": 1.8158,
|
578 |
+
"step": 79
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.07200720072007201,
|
582 |
+
"grad_norm": 0.8763648271560669,
|
583 |
+
"learning_rate": 5.647652972118998e-06,
|
584 |
+
"loss": 1.5679,
|
585 |
+
"step": 80
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.07290729072907291,
|
589 |
+
"grad_norm": 1.0473607778549194,
|
590 |
+
"learning_rate": 5.130919110904311e-06,
|
591 |
+
"loss": 1.9162,
|
592 |
+
"step": 81
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 0.0738073807380738,
|
596 |
+
"grad_norm": 0.9801396727561951,
|
597 |
+
"learning_rate": 4.6340602651970304e-06,
|
598 |
+
"loss": 1.95,
|
599 |
+
"step": 82
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 0.0747074707470747,
|
603 |
+
"grad_norm": 1.2046276330947876,
|
604 |
+
"learning_rate": 4.158077042589129e-06,
|
605 |
+
"loss": 2.0275,
|
606 |
+
"step": 83
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 0.07560756075607561,
|
610 |
+
"grad_norm": 1.0073298215866089,
|
611 |
+
"learning_rate": 3.7039280099458373e-06,
|
612 |
+
"loss": 1.8993,
|
613 |
+
"step": 84
|
614 |
+
},
|
615 |
+
{
|
616 |
+
"epoch": 0.07650765076507651,
|
617 |
+
"grad_norm": 0.9107989072799683,
|
618 |
+
"learning_rate": 3.272527762979553e-06,
|
619 |
+
"loss": 1.8347,
|
620 |
+
"step": 85
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.0774077407740774,
|
624 |
+
"grad_norm": 1.0077648162841797,
|
625 |
+
"learning_rate": 2.86474508437579e-06,
|
626 |
+
"loss": 2.1918,
|
627 |
+
"step": 86
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.0783078307830783,
|
631 |
+
"grad_norm": 0.9970296621322632,
|
632 |
+
"learning_rate": 2.4814011941804603e-06,
|
633 |
+
"loss": 2.0114,
|
634 |
+
"step": 87
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 0.07920792079207921,
|
638 |
+
"grad_norm": 0.9443178176879883,
|
639 |
+
"learning_rate": 2.1232680959720085e-06,
|
640 |
+
"loss": 1.8943,
|
641 |
+
"step": 88
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 0.08010801080108011,
|
645 |
+
"grad_norm": 1.1723785400390625,
|
646 |
+
"learning_rate": 1.79106702214893e-06,
|
647 |
+
"loss": 2.5215,
|
648 |
+
"step": 89
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 0.081008100810081,
|
652 |
+
"grad_norm": 1.1029690504074097,
|
653 |
+
"learning_rate": 1.4854669814637145e-06,
|
654 |
+
"loss": 2.9212,
|
655 |
+
"step": 90
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 0.0819081908190819,
|
659 |
+
"grad_norm": 0.8593942523002625,
|
660 |
+
"learning_rate": 1.2070834117282414e-06,
|
661 |
+
"loss": 1.9948,
|
662 |
+
"step": 91
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.08280828082808281,
|
666 |
+
"grad_norm": 1.2536730766296387,
|
667 |
+
"learning_rate": 9.56476940403942e-07,
|
668 |
+
"loss": 2.9596,
|
669 |
+
"step": 92
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.08370837083708371,
|
673 |
+
"grad_norm": 1.1047546863555908,
|
674 |
+
"learning_rate": 7.341522555726971e-07,
|
675 |
+
"loss": 3.2272,
|
676 |
+
"step": 93
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 0.0846084608460846,
|
680 |
+
"grad_norm": 1.0855673551559448,
|
681 |
+
"learning_rate": 5.405570895622014e-07,
|
682 |
+
"loss": 3.1168,
|
683 |
+
"step": 94
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 0.0855085508550855,
|
687 |
+
"grad_norm": 1.0301321744918823,
|
688 |
+
"learning_rate": 3.760813172726457e-07,
|
689 |
+
"loss": 2.7688,
|
690 |
+
"step": 95
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 0.08640864086408641,
|
694 |
+
"grad_norm": 0.9736518859863281,
|
695 |
+
"learning_rate": 2.41056171020555e-07,
|
696 |
+
"loss": 2.6513,
|
697 |
+
"step": 96
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 0.08730873087308731,
|
701 |
+
"grad_norm": 1.150550365447998,
|
702 |
+
"learning_rate": 1.357535734809795e-07,
|
703 |
+
"loss": 3.3847,
|
704 |
+
"step": 97
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.08820882088208822,
|
708 |
+
"grad_norm": 1.075913906097412,
|
709 |
+
"learning_rate": 6.038559007141397e-08,
|
710 |
+
"loss": 2.7569,
|
711 |
+
"step": 98
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.0891089108910891,
|
715 |
+
"grad_norm": 1.1728016138076782,
|
716 |
+
"learning_rate": 1.510400188028116e-08,
|
717 |
+
"loss": 2.8988,
|
718 |
+
"step": 99
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 0.09000900090009001,
|
722 |
+
"grad_norm": 1.0802109241485596,
|
723 |
+
"learning_rate": 0.0,
|
724 |
+
"loss": 2.9239,
|
725 |
+
"step": 100
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 0.09000900090009001,
|
729 |
+
"eval_loss": 0.933211624622345,
|
730 |
+
"eval_runtime": 107.8918,
|
731 |
+
"eval_samples_per_second": 4.338,
|
732 |
+
"eval_steps_per_second": 1.084,
|
733 |
+
"step": 100
|
734 |
}
|
735 |
],
|
736 |
"logging_steps": 1,
|
|
|
754 |
"should_evaluate": false,
|
755 |
"should_log": false,
|
756 |
"should_save": true,
|
757 |
+
"should_training_stop": true
|
758 |
},
|
759 |
"attributes": {}
|
760 |
}
|
761 |
},
|
762 |
+
"total_flos": 6.6422040428544e+16,
|
763 |
"train_batch_size": 4,
|
764 |
"trial_name": null,
|
765 |
"trial_params": null
|