prxy5605 commited on
Commit
d070609
·
verified ·
1 Parent(s): f82dd0e

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 sha256:41d9d9d2365daaad4920cf9a2303566cadfa7e8ff96eac98fb6767288b92c20f
3
  size 78207176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78e507eb0dd3771044e7c4fbbe4ca924e1fa5edf0c42e9ce2cf2bded8cb30119
3
  size 78207176
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a2f02cca5b8ceb6b9d34da990ede974cb297abcf51250b754f0669f04041b0b
3
  size 40177764
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47e571c88e558d75c0e97849c2eaf3e5c84d943e8bd45ee2af386831c7fe9f25
3
  size 40177764
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61495867c396e8364345d83add53b377186de9c4832654c93a924db5f2e78fee
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ff12fac1a4052f8c5adf657dbd14e156097f123faf5ab7bd05e271ceb798920
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": 4.712304592132568,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.12165450121654502,
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": 75.532,
374
  "eval_steps_per_second": 18.965,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1242268462743552.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 4.185164451599121,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.24330900243309003,
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": 75.532,
374
  "eval_steps_per_second": 18.965,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.12408759124087591,
379
+ "grad_norm": 1.7757056951522827,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 4.5692,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.12652068126520682,
386
+ "grad_norm": 1.6864593029022217,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 4.5767,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.12895377128953772,
393
+ "grad_norm": 1.4113835096359253,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 4.55,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.13138686131386862,
400
+ "grad_norm": 1.090064525604248,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 4.5021,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.13381995133819952,
407
+ "grad_norm": 0.9537211656570435,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 4.4824,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.1362530413625304,
414
+ "grad_norm": 0.8344225883483887,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 4.3658,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.1386861313868613,
421
+ "grad_norm": 0.6728500723838806,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 4.2867,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.1411192214111922,
428
+ "grad_norm": 0.5792769193649292,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 4.3504,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.1435523114355231,
435
+ "grad_norm": 0.4859144687652588,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 4.1665,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.145985401459854,
442
+ "grad_norm": 0.4857715666294098,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 4.1907,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.14841849148418493,
449
+ "grad_norm": 0.605350136756897,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 4.2865,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.15085158150851583,
456
+ "grad_norm": 0.63717120885849,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 4.3976,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.15328467153284672,
463
+ "grad_norm": 0.6708590984344482,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 4.3357,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.15571776155717762,
470
+ "grad_norm": 0.5998736023902893,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 4.1715,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.15815085158150852,
477
+ "grad_norm": 0.4863462746143341,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 4.2261,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.16058394160583941,
484
+ "grad_norm": 0.4783068299293518,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 4.2536,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.1630170316301703,
491
+ "grad_norm": 0.5137869715690613,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 4.2038,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.1654501216545012,
498
+ "grad_norm": 0.518310546875,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 4.2425,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.1678832116788321,
505
+ "grad_norm": 0.48414185643196106,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 4.2913,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.170316301703163,
512
+ "grad_norm": 0.5184882879257202,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 4.3359,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.17274939172749393,
519
+ "grad_norm": 0.5165735483169556,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 4.3767,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.17518248175182483,
526
+ "grad_norm": 0.508715808391571,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 4.1377,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.17761557177615572,
533
+ "grad_norm": 0.5977687239646912,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 4.3855,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.18004866180048662,
540
+ "grad_norm": 0.557275116443634,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 4.271,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.18248175182481752,
547
+ "grad_norm": 0.6329896450042725,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 4.4042,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.18491484184914841,
554
+ "grad_norm": 0.5772005319595337,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 4.4691,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.1873479318734793,
561
+ "grad_norm": 0.6361019015312195,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 4.3219,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.1897810218978102,
568
+ "grad_norm": 0.7251425385475159,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 4.2401,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.1922141119221411,
575
+ "grad_norm": 0.6354728937149048,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 4.445,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.19464720194647203,
582
+ "grad_norm": 0.6783463358879089,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 4.245,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.19708029197080293,
589
+ "grad_norm": 0.7329065203666687,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 4.1838,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.19951338199513383,
596
+ "grad_norm": 0.6637375950813293,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 4.1502,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.20194647201946472,
603
+ "grad_norm": 0.7039035558700562,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 4.2224,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.20437956204379562,
610
+ "grad_norm": 0.7096616625785828,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 4.247,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.20681265206812652,
617
+ "grad_norm": 0.7598410248756409,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 4.2627,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.20924574209245742,
624
+ "grad_norm": 0.7319227457046509,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 4.1582,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.2116788321167883,
631
+ "grad_norm": 0.8318302035331726,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 4.2787,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.2141119221411192,
638
+ "grad_norm": 0.7554244995117188,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 4.1737,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.21654501216545013,
645
+ "grad_norm": 0.8304018974304199,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 4.247,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.21897810218978103,
652
+ "grad_norm": 0.7371103167533875,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 4.0402,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.22141119221411193,
659
+ "grad_norm": 0.8232166767120361,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 4.3153,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.22384428223844283,
666
+ "grad_norm": 0.796526312828064,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 4.2081,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.22627737226277372,
673
+ "grad_norm": 0.9313976168632507,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 4.3794,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.22871046228710462,
680
+ "grad_norm": 0.8513618111610413,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 4.4181,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.23114355231143552,
687
+ "grad_norm": 0.8770570755004883,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 4.1982,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.23357664233576642,
694
+ "grad_norm": 0.9517497420310974,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 4.3447,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.2360097323600973,
701
+ "grad_norm": 1.0358669757843018,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 4.0967,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.2384428223844282,
708
+ "grad_norm": 1.1383416652679443,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 4.3606,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.24087591240875914,
715
+ "grad_norm": 1.243801236152649,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 4.5482,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.24330900243309003,
722
+ "grad_norm": 1.8168234825134277,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 5.0682,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.24330900243309003,
729
+ "eval_loss": 4.185164451599121,
730
+ "eval_runtime": 9.1234,
731
+ "eval_samples_per_second": 75.959,
732
+ "eval_steps_per_second": 19.072,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2484536925487104.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null