0x1202 commited on
Commit
521fff5
·
verified ·
1 Parent(s): 05bfc48

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 sha256:93cfc23c5ded85bab51b0443d63606c095d5b17ae928a2d3d67751b79cf79a88
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59270dbdba9f182de356f5f103396777ebe29eade59869207d023481f0d83669
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:243f4f8459f77246919124967acb8c7c204e8c52d1e5c1d9053c523e9c2e1233
3
  size 1342555602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb1f00ae3eaed66115b92f7f917cac6eb7a113be2aa854644f4f944783909a5
3
  size 1342555602
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8cd62c4a9459a9935fd15b2e09466379fd4d0036f75ba8c54edad4b61d6ea67
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e180d41c19b5649b27948b8eb0f034809d46a6277ef8de820500f0328edc5156
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5335737b4b4d079cdec612fe6ee661ed4d29f9e0e55eb4eada44a9677240228
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e0244c146d76bf610ae39789eea36d0bff336b81d211db008e020e66921060c
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.30388450622558594,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.005743165632896853,
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": 9.962,
374
  "eval_steps_per_second": 4.981,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.15499004493824e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.17487511038780212,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.011486331265793705,
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": 9.962,
374
  "eval_steps_per_second": 4.981,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.00585802894555479,
379
+ "grad_norm": 2.137791156768799,
380
+ "learning_rate": 9.285836503510562e-05,
381
+ "loss": 1.2646,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.005972892258212727,
386
+ "grad_norm": 2.5329372882843018,
387
+ "learning_rate": 9.24024048078213e-05,
388
+ "loss": 1.0451,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.0060877555708706635,
393
+ "grad_norm": 2.620466470718384,
394
+ "learning_rate": 9.193352839727121e-05,
395
+ "loss": 1.1558,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.006202618883528601,
400
+ "grad_norm": 2.2557244300842285,
401
+ "learning_rate": 9.145187862775209e-05,
402
+ "loss": 1.3604,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.006317482196186538,
407
+ "grad_norm": 1.8479572534561157,
408
+ "learning_rate": 9.09576022144496e-05,
409
+ "loss": 1.2608,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.006432345508844475,
414
+ "grad_norm": 2.1417593955993652,
415
+ "learning_rate": 9.045084971874738e-05,
416
+ "loss": 1.3318,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.006547208821502412,
421
+ "grad_norm": 2.672443151473999,
422
+ "learning_rate": 8.993177550236464e-05,
423
+ "loss": 1.0541,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.006662072134160349,
428
+ "grad_norm": 2.344717025756836,
429
+ "learning_rate": 8.940053768033609e-05,
430
+ "loss": 1.2237,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.006776935446818286,
435
+ "grad_norm": 2.390180826187134,
436
+ "learning_rate": 8.885729807284856e-05,
437
+ "loss": 0.9352,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.006891798759476223,
442
+ "grad_norm": 3.0167908668518066,
443
+ "learning_rate": 8.83022221559489e-05,
444
+ "loss": 1.158,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.00700666207213416,
449
+ "grad_norm": 3.0811192989349365,
450
+ "learning_rate": 8.773547901113862e-05,
451
+ "loss": 1.1718,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.007121525384792098,
456
+ "grad_norm": 3.3268229961395264,
457
+ "learning_rate": 8.715724127386972e-05,
458
+ "loss": 1.2555,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.007236388697450034,
463
+ "grad_norm": 2.296539306640625,
464
+ "learning_rate": 8.656768508095853e-05,
465
+ "loss": 1.0316,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.007351252010107972,
470
+ "grad_norm": 2.4139859676361084,
471
+ "learning_rate": 8.596699001693255e-05,
472
+ "loss": 0.8659,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.007466115322765908,
477
+ "grad_norm": 2.5878524780273438,
478
+ "learning_rate": 8.535533905932738e-05,
479
+ "loss": 1.16,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.007580978635423846,
484
+ "grad_norm": 2.180026054382324,
485
+ "learning_rate": 8.473291852294987e-05,
486
+ "loss": 1.1024,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.0076958419480817825,
491
+ "grad_norm": 1.9273844957351685,
492
+ "learning_rate": 8.409991800312493e-05,
493
+ "loss": 0.8108,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.00781070526073972,
498
+ "grad_norm": 3.0962324142456055,
499
+ "learning_rate": 8.345653031794292e-05,
500
+ "loss": 1.0571,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.007925568573397657,
505
+ "grad_norm": 2.6275441646575928,
506
+ "learning_rate": 8.280295144952536e-05,
507
+ "loss": 0.8768,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.008040431886055594,
512
+ "grad_norm": 3.156315803527832,
513
+ "learning_rate": 8.213938048432697e-05,
514
+ "loss": 1.0539,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.008155295198713532,
519
+ "grad_norm": 2.818579912185669,
520
+ "learning_rate": 8.146601955249188e-05,
521
+ "loss": 0.9232,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.008270158511371467,
526
+ "grad_norm": 2.329266309738159,
527
+ "learning_rate": 8.07830737662829e-05,
528
+ "loss": 1.0234,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.008385021824029405,
533
+ "grad_norm": 3.1287198066711426,
534
+ "learning_rate": 8.009075115760243e-05,
535
+ "loss": 1.2203,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.008499885136687342,
540
+ "grad_norm": 2.1660828590393066,
541
+ "learning_rate": 7.938926261462366e-05,
542
+ "loss": 0.8592,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.00861474844934528,
547
+ "grad_norm": 2.362858533859253,
548
+ "learning_rate": 7.86788218175523e-05,
549
+ "loss": 1.0678,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.008729611762003216,
554
+ "grad_norm": 2.5020713806152344,
555
+ "learning_rate": 7.795964517353735e-05,
556
+ "loss": 0.8854,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.008844475074661153,
561
+ "grad_norm": 2.5885136127471924,
562
+ "learning_rate": 7.723195175075136e-05,
563
+ "loss": 0.8222,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.00895933838731909,
568
+ "grad_norm": 3.7722344398498535,
569
+ "learning_rate": 7.649596321166024e-05,
570
+ "loss": 1.1339,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.009074201699977026,
575
+ "grad_norm": 2.223078489303589,
576
+ "learning_rate": 7.575190374550272e-05,
577
+ "loss": 0.7033,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.009189065012634964,
582
+ "grad_norm": 2.346508026123047,
583
+ "learning_rate": 7.500000000000001e-05,
584
+ "loss": 0.7375,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.009303928325292901,
589
+ "grad_norm": 2.3102056980133057,
590
+ "learning_rate": 7.424048101231686e-05,
591
+ "loss": 0.8455,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.009418791637950839,
596
+ "grad_norm": 2.787309169769287,
597
+ "learning_rate": 7.347357813929454e-05,
598
+ "loss": 1.0711,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.009533654950608775,
603
+ "grad_norm": 2.9215545654296875,
604
+ "learning_rate": 7.269952498697734e-05,
605
+ "loss": 0.8927,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.009648518263266712,
610
+ "grad_norm": 2.4672605991363525,
611
+ "learning_rate": 7.191855733945387e-05,
612
+ "loss": 0.713,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.00976338157592465,
617
+ "grad_norm": 3.549206018447876,
618
+ "learning_rate": 7.113091308703498e-05,
619
+ "loss": 1.0348,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.009878244888582587,
624
+ "grad_norm": 2.957688093185425,
625
+ "learning_rate": 7.033683215379002e-05,
626
+ "loss": 0.9689,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.009993108201240523,
631
+ "grad_norm": 2.4251294136047363,
632
+ "learning_rate": 6.953655642446368e-05,
633
+ "loss": 0.6512,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.01010797151389846,
638
+ "grad_norm": 2.5786890983581543,
639
+ "learning_rate": 6.873032967079561e-05,
640
+ "loss": 0.7163,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.010222834826556398,
645
+ "grad_norm": 3.341750144958496,
646
+ "learning_rate": 6.7918397477265e-05,
647
+ "loss": 0.6509,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.010337698139214336,
652
+ "grad_norm": 3.332127094268799,
653
+ "learning_rate": 6.710100716628344e-05,
654
+ "loss": 1.0058,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.010452561451872271,
659
+ "grad_norm": 3.31768536567688,
660
+ "learning_rate": 6.627840772285784e-05,
661
+ "loss": 0.7874,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.010567424764530209,
666
+ "grad_norm": 2.435286521911621,
667
+ "learning_rate": 6.545084971874738e-05,
668
+ "loss": 0.6309,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.010682288077188146,
673
+ "grad_norm": 2.9863882064819336,
674
+ "learning_rate": 6.461858523613684e-05,
675
+ "loss": 0.8979,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.010797151389846084,
680
+ "grad_norm": 3.188188314437866,
681
+ "learning_rate": 6.378186779084995e-05,
682
+ "loss": 0.8585,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.01091201470250402,
687
+ "grad_norm": 3.706717014312744,
688
+ "learning_rate": 6.294095225512603e-05,
689
+ "loss": 0.8157,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.011026878015161957,
694
+ "grad_norm": 3.348717212677002,
695
+ "learning_rate": 6.209609477998338e-05,
696
+ "loss": 0.6131,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.011141741327819895,
701
+ "grad_norm": 3.345127820968628,
702
+ "learning_rate": 6.124755271719325e-05,
703
+ "loss": 0.7124,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.011256604640477832,
708
+ "grad_norm": 3.588732957839966,
709
+ "learning_rate": 6.0395584540887963e-05,
710
+ "loss": 0.6565,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.011371467953135768,
715
+ "grad_norm": 3.6394217014312744,
716
+ "learning_rate": 5.9540449768827246e-05,
717
+ "loss": 0.6834,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.011486331265793705,
722
+ "grad_norm": 3.545775890350342,
723
+ "learning_rate": 5.868240888334653e-05,
724
+ "loss": 0.9438,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.011486331265793705,
729
+ "eval_loss": 0.17487511038780212,
730
+ "eval_runtime": 1471.3897,
731
+ "eval_samples_per_second": 9.965,
732
+ "eval_steps_per_second": 4.983,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.430998008987648e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null