Femboyuwu2000
commited on
Commit
•
72e7ceb
1
Parent(s):
7c4ee5e
Training in progress, step 2320, 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 13982248
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fca914b2057aa482eb7a6841c80c2efe9c097a9f40f833d983af4537dc40f6bb
|
3 |
size 13982248
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 7062522
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0648084ec0eae35cf7dd3a294bee444ad33f083ffa2a37e0110a6f2612622237
|
3 |
size 7062522
|
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 sha256:5db6383b70031a203d8f79911eab63df2eb868f69d22da66a6d7b3fea0a2b6f6
|
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:b4fa7f675de7d8161961ca1ab082c7d8425357c049f1a3dc57c1e35db98971b1
|
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": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -371,6 +371,454 @@
|
|
371 |
"learning_rate": 2.996193909122197e-05,
|
372 |
"loss": 3.7447,
|
373 |
"step": 1040
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
374 |
}
|
375 |
],
|
376 |
"logging_steps": 20,
|
@@ -378,7 +826,7 @@
|
|
378 |
"num_input_tokens_seen": 0,
|
379 |
"num_train_epochs": 2,
|
380 |
"save_steps": 20,
|
381 |
-
"total_flos":
|
382 |
"train_batch_size": 8,
|
383 |
"trial_name": null,
|
384 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.1856,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 2320,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
371 |
"learning_rate": 2.996193909122197e-05,
|
372 |
"loss": 3.7447,
|
373 |
"step": 1040
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.08,
|
377 |
+
"grad_norm": 26.41890525817871,
|
378 |
+
"learning_rate": 2.995840200683028e-05,
|
379 |
+
"loss": 3.5839,
|
380 |
+
"step": 1060
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.09,
|
384 |
+
"grad_norm": 32.88002014160156,
|
385 |
+
"learning_rate": 2.995470801587973e-05,
|
386 |
+
"loss": 3.6606,
|
387 |
+
"step": 1080
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.09,
|
391 |
+
"grad_norm": 32.0895881652832,
|
392 |
+
"learning_rate": 2.9950857157118544e-05,
|
393 |
+
"loss": 3.677,
|
394 |
+
"step": 1100
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.09,
|
398 |
+
"grad_norm": 37.726783752441406,
|
399 |
+
"learning_rate": 2.9946849470940395e-05,
|
400 |
+
"loss": 3.5546,
|
401 |
+
"step": 1120
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.09,
|
405 |
+
"grad_norm": 56.246299743652344,
|
406 |
+
"learning_rate": 2.9942684999384034e-05,
|
407 |
+
"loss": 3.6391,
|
408 |
+
"step": 1140
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.09,
|
412 |
+
"grad_norm": 35.675662994384766,
|
413 |
+
"learning_rate": 2.993836378613278e-05,
|
414 |
+
"loss": 3.5918,
|
415 |
+
"step": 1160
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.09,
|
419 |
+
"grad_norm": 26.685134887695312,
|
420 |
+
"learning_rate": 2.993388587651412e-05,
|
421 |
+
"loss": 3.6331,
|
422 |
+
"step": 1180
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.1,
|
426 |
+
"grad_norm": 27.400333404541016,
|
427 |
+
"learning_rate": 2.992925131749921e-05,
|
428 |
+
"loss": 3.6214,
|
429 |
+
"step": 1200
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.1,
|
433 |
+
"grad_norm": 28.501314163208008,
|
434 |
+
"learning_rate": 2.9924460157702378e-05,
|
435 |
+
"loss": 3.6619,
|
436 |
+
"step": 1220
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.1,
|
440 |
+
"grad_norm": 30.773778915405273,
|
441 |
+
"learning_rate": 2.991951244738063e-05,
|
442 |
+
"loss": 3.6453,
|
443 |
+
"step": 1240
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.1,
|
447 |
+
"grad_norm": 24.701374053955078,
|
448 |
+
"learning_rate": 2.9914408238433095e-05,
|
449 |
+
"loss": 3.7282,
|
450 |
+
"step": 1260
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.1,
|
454 |
+
"grad_norm": 27.605117797851562,
|
455 |
+
"learning_rate": 2.990914758440052e-05,
|
456 |
+
"loss": 3.6635,
|
457 |
+
"step": 1280
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.1,
|
461 |
+
"grad_norm": 27.829086303710938,
|
462 |
+
"learning_rate": 2.9903730540464668e-05,
|
463 |
+
"loss": 3.5293,
|
464 |
+
"step": 1300
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.11,
|
468 |
+
"grad_norm": 40.916263580322266,
|
469 |
+
"learning_rate": 2.9898157163447767e-05,
|
470 |
+
"loss": 3.6976,
|
471 |
+
"step": 1320
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.11,
|
475 |
+
"grad_norm": 33.31068420410156,
|
476 |
+
"learning_rate": 2.9892427511811912e-05,
|
477 |
+
"loss": 3.548,
|
478 |
+
"step": 1340
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.11,
|
482 |
+
"grad_norm": 29.932533264160156,
|
483 |
+
"learning_rate": 2.9886541645658435e-05,
|
484 |
+
"loss": 3.7486,
|
485 |
+
"step": 1360
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.11,
|
489 |
+
"grad_norm": 35.59455490112305,
|
490 |
+
"learning_rate": 2.9880499626727284e-05,
|
491 |
+
"loss": 3.6342,
|
492 |
+
"step": 1380
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.11,
|
496 |
+
"grad_norm": 29.93869400024414,
|
497 |
+
"learning_rate": 2.9874301518396377e-05,
|
498 |
+
"loss": 3.6615,
|
499 |
+
"step": 1400
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.11,
|
503 |
+
"grad_norm": 43.417213439941406,
|
504 |
+
"learning_rate": 2.986794738568094e-05,
|
505 |
+
"loss": 3.607,
|
506 |
+
"step": 1420
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.12,
|
510 |
+
"grad_norm": 52.483917236328125,
|
511 |
+
"learning_rate": 2.9861437295232825e-05,
|
512 |
+
"loss": 3.5937,
|
513 |
+
"step": 1440
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.12,
|
517 |
+
"grad_norm": 30.312334060668945,
|
518 |
+
"learning_rate": 2.9854771315339787e-05,
|
519 |
+
"loss": 3.5991,
|
520 |
+
"step": 1460
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.12,
|
524 |
+
"grad_norm": 49.459136962890625,
|
525 |
+
"learning_rate": 2.984794951592481e-05,
|
526 |
+
"loss": 3.5261,
|
527 |
+
"step": 1480
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.12,
|
531 |
+
"grad_norm": 34.81111526489258,
|
532 |
+
"learning_rate": 2.984097196854534e-05,
|
533 |
+
"loss": 3.6818,
|
534 |
+
"step": 1500
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.12,
|
538 |
+
"grad_norm": 34.721946716308594,
|
539 |
+
"learning_rate": 2.9833838746392544e-05,
|
540 |
+
"loss": 3.5636,
|
541 |
+
"step": 1520
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.12,
|
545 |
+
"grad_norm": 31.46621322631836,
|
546 |
+
"learning_rate": 2.982654992429056e-05,
|
547 |
+
"loss": 3.5597,
|
548 |
+
"step": 1540
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.12,
|
552 |
+
"grad_norm": 38.78512191772461,
|
553 |
+
"learning_rate": 2.981910557869566e-05,
|
554 |
+
"loss": 3.661,
|
555 |
+
"step": 1560
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.13,
|
559 |
+
"grad_norm": 27.38837432861328,
|
560 |
+
"learning_rate": 2.981150578769553e-05,
|
561 |
+
"loss": 3.6173,
|
562 |
+
"step": 1580
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.13,
|
566 |
+
"grad_norm": 45.619632720947266,
|
567 |
+
"learning_rate": 2.980375063100836e-05,
|
568 |
+
"loss": 3.6632,
|
569 |
+
"step": 1600
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.13,
|
573 |
+
"grad_norm": 30.708433151245117,
|
574 |
+
"learning_rate": 2.979584018998209e-05,
|
575 |
+
"loss": 3.5165,
|
576 |
+
"step": 1620
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.13,
|
580 |
+
"grad_norm": 35.472938537597656,
|
581 |
+
"learning_rate": 2.97877745475935e-05,
|
582 |
+
"loss": 3.5157,
|
583 |
+
"step": 1640
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.13,
|
587 |
+
"grad_norm": 39.029415130615234,
|
588 |
+
"learning_rate": 2.9779553788447358e-05,
|
589 |
+
"loss": 3.6259,
|
590 |
+
"step": 1660
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.13,
|
594 |
+
"grad_norm": 57.90769577026367,
|
595 |
+
"learning_rate": 2.977117799877554e-05,
|
596 |
+
"loss": 3.6378,
|
597 |
+
"step": 1680
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.14,
|
601 |
+
"grad_norm": 36.95255661010742,
|
602 |
+
"learning_rate": 2.9762647266436115e-05,
|
603 |
+
"loss": 3.5845,
|
604 |
+
"step": 1700
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.14,
|
608 |
+
"grad_norm": 27.456787109375,
|
609 |
+
"learning_rate": 2.9753961680912432e-05,
|
610 |
+
"loss": 3.6647,
|
611 |
+
"step": 1720
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.14,
|
615 |
+
"grad_norm": 27.383285522460938,
|
616 |
+
"learning_rate": 2.9745121333312166e-05,
|
617 |
+
"loss": 3.6668,
|
618 |
+
"step": 1740
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.14,
|
622 |
+
"grad_norm": 26.555049896240234,
|
623 |
+
"learning_rate": 2.9736126316366385e-05,
|
624 |
+
"loss": 3.6617,
|
625 |
+
"step": 1760
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.14,
|
629 |
+
"grad_norm": 34.009620666503906,
|
630 |
+
"learning_rate": 2.9726976724428563e-05,
|
631 |
+
"loss": 3.572,
|
632 |
+
"step": 1780
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.14,
|
636 |
+
"grad_norm": 45.44181823730469,
|
637 |
+
"learning_rate": 2.9717672653473588e-05,
|
638 |
+
"loss": 3.6354,
|
639 |
+
"step": 1800
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.15,
|
643 |
+
"grad_norm": 30.79588508605957,
|
644 |
+
"learning_rate": 2.9708214201096758e-05,
|
645 |
+
"loss": 3.6953,
|
646 |
+
"step": 1820
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.15,
|
650 |
+
"grad_norm": 46.61872482299805,
|
651 |
+
"learning_rate": 2.9698601466512767e-05,
|
652 |
+
"loss": 3.5373,
|
653 |
+
"step": 1840
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.15,
|
657 |
+
"grad_norm": 42.86500930786133,
|
658 |
+
"learning_rate": 2.9688834550554647e-05,
|
659 |
+
"loss": 3.5982,
|
660 |
+
"step": 1860
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.15,
|
664 |
+
"grad_norm": 33.480289459228516,
|
665 |
+
"learning_rate": 2.9678913555672733e-05,
|
666 |
+
"loss": 3.6024,
|
667 |
+
"step": 1880
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.15,
|
671 |
+
"grad_norm": 36.41415786743164,
|
672 |
+
"learning_rate": 2.966883858593356e-05,
|
673 |
+
"loss": 3.4843,
|
674 |
+
"step": 1900
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.15,
|
678 |
+
"grad_norm": 41.39873123168945,
|
679 |
+
"learning_rate": 2.9658609747018796e-05,
|
680 |
+
"loss": 3.5257,
|
681 |
+
"step": 1920
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.16,
|
685 |
+
"grad_norm": 31.24024200439453,
|
686 |
+
"learning_rate": 2.964822714622412e-05,
|
687 |
+
"loss": 3.5927,
|
688 |
+
"step": 1940
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.16,
|
692 |
+
"grad_norm": 52.78026580810547,
|
693 |
+
"learning_rate": 2.9637690892458103e-05,
|
694 |
+
"loss": 3.4678,
|
695 |
+
"step": 1960
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.16,
|
699 |
+
"grad_norm": 27.40117835998535,
|
700 |
+
"learning_rate": 2.962700109624106e-05,
|
701 |
+
"loss": 3.5541,
|
702 |
+
"step": 1980
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.16,
|
706 |
+
"grad_norm": 23.172683715820312,
|
707 |
+
"learning_rate": 2.961615786970389e-05,
|
708 |
+
"loss": 3.5713,
|
709 |
+
"step": 2000
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.16,
|
713 |
+
"grad_norm": 24.177541732788086,
|
714 |
+
"learning_rate": 2.960516132658692e-05,
|
715 |
+
"loss": 3.585,
|
716 |
+
"step": 2020
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.16,
|
720 |
+
"grad_norm": 44.673912048339844,
|
721 |
+
"learning_rate": 2.9594011582238672e-05,
|
722 |
+
"loss": 3.5035,
|
723 |
+
"step": 2040
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.16,
|
727 |
+
"grad_norm": 35.91664505004883,
|
728 |
+
"learning_rate": 2.95827087536147e-05,
|
729 |
+
"loss": 3.6404,
|
730 |
+
"step": 2060
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.17,
|
734 |
+
"grad_norm": 27.3450870513916,
|
735 |
+
"learning_rate": 2.9571252959276313e-05,
|
736 |
+
"loss": 3.5121,
|
737 |
+
"step": 2080
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 0.17,
|
741 |
+
"grad_norm": 25.66405487060547,
|
742 |
+
"learning_rate": 2.955964431938939e-05,
|
743 |
+
"loss": 3.5009,
|
744 |
+
"step": 2100
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.17,
|
748 |
+
"grad_norm": 24.1674861907959,
|
749 |
+
"learning_rate": 2.9547882955723052e-05,
|
750 |
+
"loss": 3.5482,
|
751 |
+
"step": 2120
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.17,
|
755 |
+
"grad_norm": 49.72268295288086,
|
756 |
+
"learning_rate": 2.953596899164846e-05,
|
757 |
+
"loss": 3.4969,
|
758 |
+
"step": 2140
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.17,
|
762 |
+
"grad_norm": 26.238168716430664,
|
763 |
+
"learning_rate": 2.9523902552137436e-05,
|
764 |
+
"loss": 3.5541,
|
765 |
+
"step": 2160
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.17,
|
769 |
+
"grad_norm": 30.524545669555664,
|
770 |
+
"learning_rate": 2.951168376376124e-05,
|
771 |
+
"loss": 3.6343,
|
772 |
+
"step": 2180
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 0.18,
|
776 |
+
"grad_norm": 38.179908752441406,
|
777 |
+
"learning_rate": 2.9499312754689168e-05,
|
778 |
+
"loss": 3.4795,
|
779 |
+
"step": 2200
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 0.18,
|
783 |
+
"grad_norm": 32.98453903198242,
|
784 |
+
"learning_rate": 2.9486789654687256e-05,
|
785 |
+
"loss": 3.6333,
|
786 |
+
"step": 2220
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.18,
|
790 |
+
"grad_norm": 26.77848243713379,
|
791 |
+
"learning_rate": 2.94741145951169e-05,
|
792 |
+
"loss": 3.5654,
|
793 |
+
"step": 2240
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 0.18,
|
797 |
+
"grad_norm": 27.737852096557617,
|
798 |
+
"learning_rate": 2.9461287708933475e-05,
|
799 |
+
"loss": 3.5044,
|
800 |
+
"step": 2260
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.18,
|
804 |
+
"grad_norm": 34.2584342956543,
|
805 |
+
"learning_rate": 2.9448309130684944e-05,
|
806 |
+
"loss": 3.5979,
|
807 |
+
"step": 2280
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.18,
|
811 |
+
"grad_norm": 57.86616897583008,
|
812 |
+
"learning_rate": 2.9435178996510456e-05,
|
813 |
+
"loss": 3.5726,
|
814 |
+
"step": 2300
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 0.19,
|
818 |
+
"grad_norm": 37.64597702026367,
|
819 |
+
"learning_rate": 2.9421897444138902e-05,
|
820 |
+
"loss": 3.5913,
|
821 |
+
"step": 2320
|
822 |
}
|
823 |
],
|
824 |
"logging_steps": 20,
|
|
|
826 |
"num_input_tokens_seen": 0,
|
827 |
"num_train_epochs": 2,
|
828 |
"save_steps": 20,
|
829 |
+
"total_flos": 5493973373190144.0,
|
830 |
"train_batch_size": 8,
|
831 |
"trial_name": null,
|
832 |
"trial_params": null
|