nttx commited on
Commit
7b810f0
·
verified ·
1 Parent(s): 8d33496

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:b98b41f3a28c7f04f71271c4e8a0f32b8baf1313eb69023fac19aa1cdc5b351b
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83fe436dc5a7cbc7acee3d73a8646cad5401b3cd844f549a5d6ead5c4dcbe76b
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:efc81c160873e03dc79872f1ff09addeea9c4c50394859b9e24ad3c5cda1c3d2
3
  size 320194002
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6da46b2bb1653ec2d60a7367f2a064464690e1dac5ab714001b78bd11a12200f
3
  size 320194002
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf895f4c85036b0d011f684e435307206f29bb65c07ecd50088c1eac5bbb7464
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f35e90cceaa518d07b7905faf3f2b29ba7c2087659cc0dcfcef653d2bd5e5858
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1900bd8021f13c38b942ed30aea6e2cea1b47664e4ce28d0276b142334732307
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2c4a11c3ec7ace2e963dc6e2b0b5b6372cc0250cefb36d5f7289475908638cb
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.9785971641540527,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.013889130019618397,
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": 10.97,
374
  "eval_steps_per_second": 1.371,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -396,12 +754,12 @@
396
  "should_evaluate": false,
397
  "should_log": false,
398
  "should_save": true,
399
- "should_training_stop": false
400
  },
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 2.6171259006379622e+17,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.8610045909881592,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.027778260039236793,
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": 10.97,
374
  "eval_steps_per_second": 1.371,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.014166912620010763,
379
+ "grad_norm": 15.105279922485352,
380
+ "learning_rate": 2.847932752400164e-06,
381
+ "loss": 28.6279,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.014444695220403132,
386
+ "grad_norm": 13.486973762512207,
387
+ "learning_rate": 2.761321158169134e-06,
388
+ "loss": 31.4456,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.0147224778207955,
393
+ "grad_norm": 11.410908699035645,
394
+ "learning_rate": 2.6743911843603134e-06,
395
+ "loss": 28.7939,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.015000260421187867,
400
+ "grad_norm": 17.802974700927734,
401
+ "learning_rate": 2.587248741756253e-06,
402
+ "loss": 28.446,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.015278043021580236,
407
+ "grad_norm": 12.340092658996582,
408
+ "learning_rate": 2.5e-06,
409
+ "loss": 27.5885,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.015555825621972604,
414
+ "grad_norm": 13.71504020690918,
415
+ "learning_rate": 2.4127512582437486e-06,
416
+ "loss": 28.1596,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.015833608222364973,
421
+ "grad_norm": 15.670882225036621,
422
+ "learning_rate": 2.325608815639687e-06,
423
+ "loss": 30.8707,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.01611139082275734,
428
+ "grad_norm": 13.578393936157227,
429
+ "learning_rate": 2.238678841830867e-06,
430
+ "loss": 28.5625,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.016389173423149706,
435
+ "grad_norm": 13.906554222106934,
436
+ "learning_rate": 2.1520672475998374e-06,
437
+ "loss": 29.2829,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.016666956023542075,
442
+ "grad_norm": 13.766081809997559,
443
+ "learning_rate": 2.0658795558326745e-06,
444
+ "loss": 27.9378,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.016944738623934443,
449
+ "grad_norm": 17.766794204711914,
450
+ "learning_rate": 1.9802207729556023e-06,
451
+ "loss": 29.4873,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.01722252122432681,
456
+ "grad_norm": 13.73377799987793,
457
+ "learning_rate": 1.895195261000831e-06,
458
+ "loss": 28.992,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.01750030382471918,
463
+ "grad_norm": 15.233474731445312,
464
+ "learning_rate": 1.8109066104575023e-06,
465
+ "loss": 27.6017,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.01777808642511155,
470
+ "grad_norm": 15.239630699157715,
471
+ "learning_rate": 1.7274575140626318e-06,
472
+ "loss": 28.4568,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.018055869025503914,
477
+ "grad_norm": 14.983368873596191,
478
+ "learning_rate": 1.6449496416858285e-06,
479
+ "loss": 29.2176,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.018333651625896282,
484
+ "grad_norm": 17.093082427978516,
485
+ "learning_rate": 1.56348351646022e-06,
486
+ "loss": 30.3518,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.01861143422628865,
491
+ "grad_norm": 18.445396423339844,
492
+ "learning_rate": 1.4831583923105e-06,
493
+ "loss": 29.1137,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.01888921682668102,
498
+ "grad_norm": 17.467205047607422,
499
+ "learning_rate": 1.4040721330273063e-06,
500
+ "loss": 29.8494,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.019166999427073388,
505
+ "grad_norm": 18.905086517333984,
506
+ "learning_rate": 1.3263210930352737e-06,
507
+ "loss": 31.4163,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.019444782027465756,
512
+ "grad_norm": 22.314186096191406,
513
+ "learning_rate": 1.2500000000000007e-06,
514
+ "loss": 29.8957,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.01972256462785812,
519
+ "grad_norm": 18.803869247436523,
520
+ "learning_rate": 1.1752018394169882e-06,
521
+ "loss": 29.6537,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.02000034722825049,
526
+ "grad_norm": 20.8019962310791,
527
+ "learning_rate": 1.1020177413231334e-06,
528
+ "loss": 31.4087,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.020278129828642858,
533
+ "grad_norm": 18.184175491333008,
534
+ "learning_rate": 1.0305368692688175e-06,
535
+ "loss": 30.0676,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.020555912429035227,
540
+ "grad_norm": 21.649564743041992,
541
+ "learning_rate": 9.608463116858544e-07,
542
+ "loss": 30.1305,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.020833695029427595,
547
+ "grad_norm": 19.38674545288086,
548
+ "learning_rate": 8.930309757836517e-07,
549
+ "loss": 29.1156,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.021111477629819964,
554
+ "grad_norm": 21.317813873291016,
555
+ "learning_rate": 8.271734841028553e-07,
556
+ "loss": 30.6399,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.02138926023021233,
561
+ "grad_norm": 20.849931716918945,
562
+ "learning_rate": 7.633540738525066e-07,
563
+ "loss": 30.9903,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.021667042830604697,
568
+ "grad_norm": 20.501638412475586,
569
+ "learning_rate": 7.016504991533727e-07,
570
+ "loss": 30.4718,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.021944825430997066,
575
+ "grad_norm": 18.88482666015625,
576
+ "learning_rate": 6.421379363065142e-07,
577
+ "loss": 30.7271,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.022222608031389434,
582
+ "grad_norm": 21.85283088684082,
583
+ "learning_rate": 5.848888922025553e-07,
584
+ "loss": 31.2117,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.022500390631781803,
589
+ "grad_norm": 20.323278427124023,
590
+ "learning_rate": 5.299731159831953e-07,
591
+ "loss": 29.8021,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.02277817323217417,
596
+ "grad_norm": 24.70086097717285,
597
+ "learning_rate": 4.774575140626317e-07,
598
+ "loss": 29.1231,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.023055955832566536,
603
+ "grad_norm": 22.418100357055664,
604
+ "learning_rate": 4.27406068612396e-07,
605
+ "loss": 29.6823,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.023333738432958905,
610
+ "grad_norm": 22.023237228393555,
611
+ "learning_rate": 3.798797596089351e-07,
612
+ "loss": 29.8833,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.023611521033351273,
617
+ "grad_norm": 23.640119552612305,
618
+ "learning_rate": 3.3493649053890325e-07,
619
+ "loss": 29.7865,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.02388930363374364,
624
+ "grad_norm": 25.109132766723633,
625
+ "learning_rate": 2.9263101785268253e-07,
626
+ "loss": 31.5167,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.02416708623413601,
631
+ "grad_norm": 24.796283721923828,
632
+ "learning_rate": 2.53014884252083e-07,
633
+ "loss": 30.6463,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.02444486883452838,
638
+ "grad_norm": 21.855819702148438,
639
+ "learning_rate": 2.1613635589349756e-07,
640
+ "loss": 29.4907,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.024722651434920744,
645
+ "grad_norm": 25.80754852294922,
646
+ "learning_rate": 1.8204036358303173e-07,
647
+ "loss": 30.5733,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.025000434035313112,
652
+ "grad_norm": 24.23963737487793,
653
+ "learning_rate": 1.507684480352292e-07,
654
+ "loss": 32.1402,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.02527821663570548,
659
+ "grad_norm": 24.823196411132812,
660
+ "learning_rate": 1.223587092621162e-07,
661
+ "loss": 32.7492,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.02555599923609785,
666
+ "grad_norm": 24.919946670532227,
667
+ "learning_rate": 9.684576015420277e-08,
668
+ "loss": 32.7238,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.025833781836490217,
673
+ "grad_norm": 30.453264236450195,
674
+ "learning_rate": 7.426068431000883e-08,
675
+ "loss": 32.058,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.026111564436882586,
680
+ "grad_norm": 25.096824645996094,
681
+ "learning_rate": 5.463099816548578e-08,
682
+ "loss": 30.7904,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.02638934703727495,
687
+ "grad_norm": 32.097557067871094,
688
+ "learning_rate": 3.798061746947995e-08,
689
+ "loss": 32.8395,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.02666712963766732,
694
+ "grad_norm": 38.559356689453125,
695
+ "learning_rate": 2.4329828146074096e-08,
696
+ "loss": 29.9401,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.026944912238059688,
701
+ "grad_norm": 30.296693801879883,
702
+ "learning_rate": 1.3695261579316776e-08,
703
+ "loss": 31.4049,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.027222694838452056,
708
+ "grad_norm": 35.62953567504883,
709
+ "learning_rate": 6.089874350439507e-09,
710
+ "loss": 32.2416,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.027500477438844425,
715
+ "grad_norm": 37.22911071777344,
716
+ "learning_rate": 1.5229324522605949e-09,
717
+ "loss": 34.6788,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.027778260039236793,
722
+ "grad_norm": 32.37774658203125,
723
+ "learning_rate": 0.0,
724
+ "loss": 36.398,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.027778260039236793,
729
+ "eval_loss": 1.8610045909881592,
730
+ "eval_runtime": 2211.9293,
731
+ "eval_samples_per_second": 10.964,
732
+ "eval_steps_per_second": 1.371,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
754
  "should_evaluate": false,
755
  "should_log": false,
756
  "should_save": true,
757
+ "should_training_stop": true
758
  },
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 5.230984478054154e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null