prxy5604 commited on
Commit
4d14229
·
verified ·
1 Parent(s): 08e4ee4

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:bf828ab75bc3ba224f9e0cbdc5a62c7b3ffb8086d2a6b3c32864e3da1327da26
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79da49f4f174f529a5dcf3f2a173e480299cda83aa9e4374f982c194b22c5338
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f69a315556aa73fcb125ae5d95c4b96ab8d37d91da8efae54c4d25515724e726
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f529f79de8f4bf602a919cd3685f1db263b7c74e21b6af279cc94b1eb543335
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d33d22b90a7bd3379aae21ce93afbb8f09a2071b1cbd1155aea1c7c5c70ad6f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c28762cfb18eb3c143ab7e2caf856e9aeedc7b949636c0eb8eadec37d4c783b7
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": 1.4252018928527832,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.20964360587002095,
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": 8.869,
374
  "eval_steps_per_second": 2.228,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.834714099207373e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.33364999294281,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.4192872117400419,
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": 8.869,
374
  "eval_steps_per_second": 2.228,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.2138364779874214,
379
+ "grad_norm": 17.839067459106445,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 8.458,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.2180293501048218,
386
+ "grad_norm": 16.638402938842773,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 8.5195,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.2222222222222222,
393
+ "grad_norm": 18.481019973754883,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 7.6538,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.22641509433962265,
400
+ "grad_norm": 15.877742767333984,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 8.4381,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.23060796645702306,
407
+ "grad_norm": 18.584312438964844,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 7.5717,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.2348008385744235,
414
+ "grad_norm": 15.255925178527832,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 6.4571,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.2389937106918239,
421
+ "grad_norm": 14.540227890014648,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 6.3747,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.2431865828092243,
428
+ "grad_norm": 64.81522369384766,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 6.495,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.24737945492662475,
435
+ "grad_norm": 17.637868881225586,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 6.1676,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.25157232704402516,
442
+ "grad_norm": 16.184396743774414,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 6.3003,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.2557651991614256,
449
+ "grad_norm": 14.975420951843262,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 5.7779,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.259958071278826,
456
+ "grad_norm": 12.618855476379395,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 5.7407,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.2641509433962264,
463
+ "grad_norm": 20.052886962890625,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 5.6884,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.26834381551362685,
470
+ "grad_norm": 13.004949569702148,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 5.2275,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.27253668763102723,
477
+ "grad_norm": 12.57992172241211,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 5.3673,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.27672955974842767,
484
+ "grad_norm": 12.553001403808594,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 5.4621,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.2809224318658281,
491
+ "grad_norm": 14.872114181518555,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 5.331,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.2851153039832285,
498
+ "grad_norm": 13.390371322631836,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 5.3942,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.2893081761006289,
505
+ "grad_norm": 12.523579597473145,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 5.4148,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.29350104821802936,
512
+ "grad_norm": 12.635327339172363,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 5.3922,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.2976939203354298,
519
+ "grad_norm": 11.972217559814453,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 4.5972,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.3018867924528302,
526
+ "grad_norm": 11.309503555297852,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 5.3812,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.3060796645702306,
533
+ "grad_norm": 13.033599853515625,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 4.6551,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.31027253668763105,
540
+ "grad_norm": 12.664169311523438,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 5.5423,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.31446540880503143,
547
+ "grad_norm": 13.637231826782227,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 5.3014,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.31865828092243187,
554
+ "grad_norm": 12.818574905395508,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 5.273,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.3228511530398323,
561
+ "grad_norm": 12.218353271484375,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 5.3526,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.3270440251572327,
568
+ "grad_norm": 11.470541000366211,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 4.8623,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.3312368972746331,
575
+ "grad_norm": 11.281693458557129,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 5.1589,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.33542976939203356,
582
+ "grad_norm": 12.148499488830566,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 4.6785,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.33962264150943394,
589
+ "grad_norm": 12.78722095489502,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 4.869,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.3438155136268344,
596
+ "grad_norm": 11.150115013122559,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 4.8388,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.3480083857442348,
603
+ "grad_norm": 11.860318183898926,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 5.3106,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.3522012578616352,
610
+ "grad_norm": 12.364052772521973,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 4.795,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.35639412997903563,
617
+ "grad_norm": 15.005729675292969,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 5.5391,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.36058700209643607,
624
+ "grad_norm": 12.835009574890137,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 4.8894,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.36477987421383645,
631
+ "grad_norm": 12.573246002197266,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 4.6682,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.3689727463312369,
638
+ "grad_norm": 12.361988067626953,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 4.6504,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.3731656184486373,
645
+ "grad_norm": 13.073786735534668,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 4.7555,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.37735849056603776,
652
+ "grad_norm": 11.83043098449707,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 4.4787,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.38155136268343814,
659
+ "grad_norm": 11.655750274658203,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 4.8748,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.3857442348008386,
666
+ "grad_norm": 14.224935531616211,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 5.0494,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.389937106918239,
673
+ "grad_norm": 11.915684700012207,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 4.7808,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.3941299790356394,
680
+ "grad_norm": 13.685681343078613,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 4.7294,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.39832285115303984,
687
+ "grad_norm": 13.151580810546875,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 5.6233,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.4025157232704403,
694
+ "grad_norm": 16.578044891357422,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 5.0588,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.40670859538784065,
701
+ "grad_norm": 13.421004295349121,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 5.2463,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.4109014675052411,
708
+ "grad_norm": 13.570477485656738,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 5.4574,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.41509433962264153,
715
+ "grad_norm": 13.61705493927002,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 5.8082,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.4192872117400419,
722
+ "grad_norm": 14.726000785827637,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 6.2693,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.4192872117400419,
729
+ "eval_loss": 1.33364999294281,
730
+ "eval_runtime": 44.4249,
731
+ "eval_samples_per_second": 9.049,
732
+ "eval_steps_per_second": 2.274,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.581252799931351e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null