prxy5608 commited on
Commit
21ebb3e
·
verified ·
1 Parent(s): 994f9ad

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 sha256:46496deb92f831e2eda52c263c07050e17caa2ff3b53a4d1663ec321afe886d3
3
  size 871457448
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7327d1c0962af161be6695ac3bf643308988cad0de960ee0a46d60a1282a8f34
3
  size 871457448
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc5b094176b12acbc15e71d9d527b44a5f1cc12a5d06ca09ffeb5f64976478fb
3
  size 443280340
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4f2f09a347c2f8e2296cc08a3a89fc2f71d3a8a680d0ec2056da09a8cd79814
3
  size 443280340
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02f9b295b09ff44b2b969c24960e83081956f04874c37e24b1e40b4bba8afb60
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ba6c05681ae991317f546c8990fa5ff0787d6c81d3a8054bbc2535df924edd0
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d359eb5d29e75fb2bbe5b7026981da69b95b8ad1fea469302d13cde104f7e8a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ddb9588ea654e56e83effcf81a2bc03480954babcf6415cb44d41d3bfb8039f
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.2712900638580322,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.005063803929511849,
5
  "eval_steps": 50,
6
- "global_step": 50,
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": 10.58,
374
  "eval_steps_per_second": 2.645,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 8.63610951696384e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.122905731201172,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.010127607859023698,
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": 10.58,
374
  "eval_steps_per_second": 2.645,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.0051650800081020866,
379
+ "grad_norm": 11.62936019897461,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 1.9625,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.005266356086692323,
386
+ "grad_norm": 8.94434928894043,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 2.1033,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.00536763216528256,
393
+ "grad_norm": 6.63067626953125,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 1.4185,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.005468908243872798,
400
+ "grad_norm": 5.48298454284668,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 1.2189,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.005570184322463034,
407
+ "grad_norm": 5.248403549194336,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 1.4783,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.005671460401053271,
414
+ "grad_norm": 3.091050386428833,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 1.1947,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.005772736479643509,
421
+ "grad_norm": 3.561055898666382,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 1.2281,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.005874012558233745,
428
+ "grad_norm": 3.302882432937622,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.5576,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.005975288636823982,
435
+ "grad_norm": 3.763090133666992,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.8619,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.006076564715414219,
442
+ "grad_norm": 4.980674743652344,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.2353,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.006177840794004456,
449
+ "grad_norm": 3.831450939178467,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 1.069,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.006279116872594693,
456
+ "grad_norm": 10.198344230651855,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 1.1834,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.00638039295118493,
463
+ "grad_norm": 4.180304050445557,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 1.115,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.006481669029775167,
470
+ "grad_norm": 3.688276767730713,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 1.0416,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.006582945108365404,
477
+ "grad_norm": 3.9528965950012207,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 1.2017,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.006684221186955641,
484
+ "grad_norm": 3.0600063800811768,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.8048,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.006785497265545878,
491
+ "grad_norm": 5.901766777038574,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.0497,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.006886773344136115,
498
+ "grad_norm": 6.350919246673584,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 1.1079,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.006988049422726352,
505
+ "grad_norm": 3.647548198699951,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 1.3041,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.007089325501316589,
512
+ "grad_norm": 4.118706226348877,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 1.333,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.007190601579906826,
519
+ "grad_norm": 6.582793712615967,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 1.6024,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.007291877658497063,
526
+ "grad_norm": 5.287528991699219,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 1.3089,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.0073931537370873,
533
+ "grad_norm": 4.048415660858154,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.5625,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.007494429815677537,
540
+ "grad_norm": 10.162145614624023,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 1.4619,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.007595705894267774,
547
+ "grad_norm": 3.710768699645996,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 1.5656,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.007696981972858011,
554
+ "grad_norm": 3.8244152069091797,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 1.8309,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.007798258051448248,
561
+ "grad_norm": 4.590068817138672,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 1.3288,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.007899534130038485,
568
+ "grad_norm": 3.5102505683898926,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 1.3495,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.008000810208628722,
575
+ "grad_norm": 3.706644296646118,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 1.3365,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.008102086287218958,
582
+ "grad_norm": 4.158026695251465,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 1.7593,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.008203362365809196,
589
+ "grad_norm": 4.4503173828125,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 1.9636,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.008304638444399434,
596
+ "grad_norm": 3.916571855545044,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 1.7637,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.00840591452298967,
603
+ "grad_norm": 3.083988904953003,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 1.5923,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.008507190601579907,
610
+ "grad_norm": 2.566749095916748,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 1.3581,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.008608466680170145,
617
+ "grad_norm": 3.232682466506958,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 1.4974,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.00870974275876038,
624
+ "grad_norm": 4.013308048248291,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 1.8144,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.008811018837350618,
631
+ "grad_norm": 2.443804979324341,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 1.4845,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.008912294915940856,
638
+ "grad_norm": 3.423102617263794,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 1.9203,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.009013570994531091,
645
+ "grad_norm": 4.804714679718018,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 2.4277,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.009114847073121329,
652
+ "grad_norm": 4.962749004364014,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 2.5357,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.009216123151711565,
659
+ "grad_norm": 6.186339378356934,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 2.6825,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.009317399230301802,
666
+ "grad_norm": 3.8425121307373047,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 2.2824,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.00941867530889204,
673
+ "grad_norm": 5.106661319732666,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 2.5763,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.009519951387482276,
680
+ "grad_norm": 3.5278234481811523,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 1.9765,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.009621227466072513,
687
+ "grad_norm": 3.7213644981384277,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 2.3297,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.009722503544662751,
694
+ "grad_norm": 3.549769401550293,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 2.2013,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.009823779623252987,
701
+ "grad_norm": 3.8638694286346436,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 2.3581,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.009925055701843224,
708
+ "grad_norm": 4.105386734008789,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 2.4061,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.010026331780433462,
715
+ "grad_norm": 6.937985420227051,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 2.8345,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.010127607859023698,
722
+ "grad_norm": 4.872765064239502,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 2.3537,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.010127607859023698,
729
+ "eval_loss": 2.122905731201172,
730
+ "eval_runtime": 1571.7354,
731
+ "eval_samples_per_second": 10.581,
732
+ "eval_steps_per_second": 2.645,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.727221903392768e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null