prxy5608 commited on
Commit
72db0a1
·
verified ·
1 Parent(s): 444243f

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 sha256:5e906f324a6f9e477a7c13078501c13b6c874a53f048505ae2df8f7353f515ef
3
  size 239906848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac1d2f7e1abd95a89530dd0d4f778c9100c44bbeec8fbcb48fdf4d12eb524480
3
  size 239906848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13ac026464c5a3f38bf938c67359d760779fc1155dde51a2cd44af8e71c91298
3
  size 122200212
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d868fe2217c545dc73bd5ef74fb689326c9ca3fa9e1f6441e18d2605393d7a63
3
  size 122200212
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:086556ce7e71aef1f30abe35aae99dad3f77818d6f8467390172b9101e624fdf
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23129ad987a265315df526ef0e5112247fc3b18fe86fc980088b8f7016853a2f
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": 1.4472647905349731,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.005402047375955487,
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": 28.949,
374
  "eval_steps_per_second": 7.239,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.9427651223552e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.4100725650787354,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.010804094751910975,
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": 28.949,
374
  "eval_steps_per_second": 7.239,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.005510088323474597,
379
+ "grad_norm": 0.5724785923957825,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 1.5719,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.005618129270993707,
386
+ "grad_norm": 0.5202212929725647,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 1.6062,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.005726170218512816,
393
+ "grad_norm": 0.5109375715255737,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 1.4072,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.005834211166031926,
400
+ "grad_norm": 0.49153491854667664,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 1.4472,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.005942252113551036,
407
+ "grad_norm": 0.5157988667488098,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 1.4969,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.0060502930610701455,
414
+ "grad_norm": 0.5498408675193787,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 1.6005,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.006158334008589256,
421
+ "grad_norm": 0.5869506001472473,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 1.746,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.006266374956108365,
428
+ "grad_norm": 0.5549739003181458,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 1.5946,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.0063744159036274745,
435
+ "grad_norm": 0.508307695388794,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 1.6111,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.006482456851146585,
442
+ "grad_norm": 0.5015324354171753,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.6921,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.006590497798665694,
449
+ "grad_norm": 0.5559808015823364,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 1.7278,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.0066985387461848045,
456
+ "grad_norm": 0.5375747084617615,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 1.6452,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.006806579693703914,
463
+ "grad_norm": 0.5635334849357605,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 1.6882,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.006914620641223023,
470
+ "grad_norm": 0.5800416469573975,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 1.6832,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.0070226615887421335,
477
+ "grad_norm": 0.6070132255554199,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 1.763,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.007130702536261243,
484
+ "grad_norm": 0.5629101395606995,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 1.4637,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.007238743483780352,
491
+ "grad_norm": 0.5806207656860352,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.5195,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.007346784431299463,
498
+ "grad_norm": 0.6087584495544434,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 1.5393,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.007454825378818572,
505
+ "grad_norm": 0.6380349397659302,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 1.5773,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.007562866326337682,
512
+ "grad_norm": 0.6220327615737915,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 1.5909,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.007670907273856792,
519
+ "grad_norm": 0.6914963126182556,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 1.7632,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.007778948221375901,
526
+ "grad_norm": 0.6657575368881226,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 1.5215,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.007886989168895011,
533
+ "grad_norm": 0.6277755498886108,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.3684,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.007995030116414122,
540
+ "grad_norm": 0.7497745752334595,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 1.3881,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.00810307106393323,
547
+ "grad_norm": 0.6374635100364685,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 1.322,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.00821111201145234,
554
+ "grad_norm": 0.668455958366394,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 1.3848,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.00831915295897145,
561
+ "grad_norm": 0.5366008877754211,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 1.2807,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.00842719390649056,
568
+ "grad_norm": 0.5630325078964233,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 1.3645,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.00853523485400967,
575
+ "grad_norm": 0.5944975018501282,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 1.3041,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.00864327580152878,
582
+ "grad_norm": 0.6403332352638245,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 1.4156,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.00875131674904789,
589
+ "grad_norm": 0.5775466561317444,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 1.401,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.008859357696566999,
596
+ "grad_norm": 0.5093110799789429,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 1.3779,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.008967398644086109,
603
+ "grad_norm": 0.5032273530960083,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 1.2792,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.009075439591605219,
610
+ "grad_norm": 0.5436679720878601,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 1.1895,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.009183480539124328,
617
+ "grad_norm": 0.5496953725814819,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 1.279,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.009291521486643438,
624
+ "grad_norm": 0.4856758713722229,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 1.1795,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.009399562434162548,
631
+ "grad_norm": 0.5258938074111938,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 1.2899,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.009507603381681657,
638
+ "grad_norm": 0.5205855965614319,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 1.1558,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.009615644329200767,
645
+ "grad_norm": 0.49661728739738464,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 1.2421,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.009723685276719877,
652
+ "grad_norm": 0.5139006972312927,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 1.215,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.009831726224238986,
659
+ "grad_norm": 0.5055752992630005,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 1.1881,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.009939767171758096,
666
+ "grad_norm": 0.5600236058235168,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 1.338,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.010047808119277206,
673
+ "grad_norm": 0.4925087094306946,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 1.2178,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.010155849066796317,
680
+ "grad_norm": 0.5316876173019409,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 1.31,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.010263890014315425,
687
+ "grad_norm": 0.5395605564117432,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 1.3661,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.010371930961834535,
694
+ "grad_norm": 0.5037703514099121,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 1.1829,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.010479971909353646,
701
+ "grad_norm": 0.5071983933448792,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 1.2487,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.010588012856872754,
708
+ "grad_norm": 0.561583936214447,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 1.2686,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.010696053804391864,
715
+ "grad_norm": 0.5371668338775635,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 1.1905,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.010804094751910975,
722
+ "grad_norm": 0.5955190062522888,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 1.198,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.010804094751910975,
729
+ "eval_loss": 1.4100725650787354,
730
+ "eval_runtime": 538.1805,
731
+ "eval_samples_per_second": 28.966,
732
+ "eval_steps_per_second": 7.243,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 3.87894460022784e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null