mariadg commited on
Commit
a57739d
·
verified ·
1 Parent(s): 6d44098

Training in progress, epoch 2, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca3a26cb4f2b02fdf78505dcba360fa41760b9d0f1d205bee72034eb88ceb909
3
  size 368871908
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dedcb3bb518a8b8441af7244198f0129c9cb611dda30f7deb89fece7593fda3c
3
  size 368871908
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:70005fdc1fcc0837ee00cab26f99ba01422caf0930cdb9c70748a1a3ef0046b1
3
  size 737866955
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebd5e7344d5ccced1c3cfebce6c28e7a8f131ccbc268f5b9df07704e069e8d2b
3
  size 737866955
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:309a654c3ca5b1a9a6479d7c9d6a0fc2a1057af3810e209d98a0aba0d920ad55
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7111e0d1c3d911c233a9de7a119c4873b430967b8a2fca899f240686d25dbe5e
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2408b440f534d6bf141e5e3eee030bf035f8ee033aa65c33a5266ae6766544ca
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed01cb3ead55d9aead6eb70916572ffd5fc6d58c2675a2442748ceab27932dec
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": 2393,
3
  "best_metric": 0.7003869916491275,
4
  "best_model_checkpoint": "./results_deberta_framing/checkpoint-2393",
5
- "epoch": 1.0,
6
  "eval_steps": 500,
7
- "global_step": 2393,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -350,6 +350,355 @@
350
  "eval_samples_per_second": 125.883,
351
  "eval_steps_per_second": 7.878,
352
  "step": 2393
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
353
  }
354
  ],
355
  "logging_steps": 50,
@@ -364,7 +713,7 @@
364
  "early_stopping_threshold": 0.0
365
  },
366
  "attributes": {
367
- "early_stopping_patience_counter": 0
368
  }
369
  },
370
  "TrainerControl": {
@@ -378,7 +727,7 @@
378
  "attributes": {}
379
  }
380
  },
381
- "total_flos": 6539240997132864.0,
382
  "train_batch_size": 16,
383
  "trial_name": null,
384
  "trial_params": null
 
2
  "best_global_step": 2393,
3
  "best_metric": 0.7003869916491275,
4
  "best_model_checkpoint": "./results_deberta_framing/checkpoint-2393",
5
+ "epoch": 2.0,
6
  "eval_steps": 500,
7
+ "global_step": 4786,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
350
  "eval_samples_per_second": 125.883,
351
  "eval_steps_per_second": 7.878,
352
  "step": 2393
353
+ },
354
+ {
355
+ "epoch": 1.0029251984956122,
356
+ "grad_norm": 1.255859375,
357
+ "learning_rate": 7.083580320094844e-06,
358
+ "loss": 0.692879409790039,
359
+ "step": 2400
360
+ },
361
+ {
362
+ "epoch": 1.0238194734642707,
363
+ "grad_norm": 3.69921875,
364
+ "learning_rate": 7.009484291641968e-06,
365
+ "loss": 0.69281494140625,
366
+ "step": 2450
367
+ },
368
+ {
369
+ "epoch": 1.0447137484329294,
370
+ "grad_norm": 0.873046875,
371
+ "learning_rate": 6.935388263189093e-06,
372
+ "loss": 0.6911331176757812,
373
+ "step": 2500
374
+ },
375
+ {
376
+ "epoch": 1.065608023401588,
377
+ "grad_norm": 1.369140625,
378
+ "learning_rate": 6.8612922347362184e-06,
379
+ "loss": 0.6902473449707032,
380
+ "step": 2550
381
+ },
382
+ {
383
+ "epoch": 1.0865022983702466,
384
+ "grad_norm": 4.4140625,
385
+ "learning_rate": 6.787196206283344e-06,
386
+ "loss": 0.6925992584228515,
387
+ "step": 2600
388
+ },
389
+ {
390
+ "epoch": 1.107396573338905,
391
+ "grad_norm": 1.1943359375,
392
+ "learning_rate": 6.713100177830469e-06,
393
+ "loss": 0.6863495635986329,
394
+ "step": 2650
395
+ },
396
+ {
397
+ "epoch": 1.1282908483075638,
398
+ "grad_norm": 1.166015625,
399
+ "learning_rate": 6.639004149377594e-06,
400
+ "loss": 0.6909130859375,
401
+ "step": 2700
402
+ },
403
+ {
404
+ "epoch": 1.1491851232762222,
405
+ "grad_norm": 0.307861328125,
406
+ "learning_rate": 6.564908120924719e-06,
407
+ "loss": 0.6912396240234375,
408
+ "step": 2750
409
+ },
410
+ {
411
+ "epoch": 1.170079398244881,
412
+ "grad_norm": 0.66552734375,
413
+ "learning_rate": 6.490812092471844e-06,
414
+ "loss": 0.6951913452148437,
415
+ "step": 2800
416
+ },
417
+ {
418
+ "epoch": 1.1909736732135394,
419
+ "grad_norm": 1.3037109375,
420
+ "learning_rate": 6.41671606401897e-06,
421
+ "loss": 0.6881448364257813,
422
+ "step": 2850
423
+ },
424
+ {
425
+ "epoch": 1.2118679481821981,
426
+ "grad_norm": 2.107421875,
427
+ "learning_rate": 6.342620035566094e-06,
428
+ "loss": 0.6895191192626953,
429
+ "step": 2900
430
+ },
431
+ {
432
+ "epoch": 1.2327622231508566,
433
+ "grad_norm": 1.1220703125,
434
+ "learning_rate": 6.268524007113219e-06,
435
+ "loss": 0.6895684051513672,
436
+ "step": 2950
437
+ },
438
+ {
439
+ "epoch": 1.2536564981195153,
440
+ "grad_norm": 1.6328125,
441
+ "learning_rate": 6.194427978660344e-06,
442
+ "loss": 0.6879627990722657,
443
+ "step": 3000
444
+ },
445
+ {
446
+ "epoch": 1.2745507730881738,
447
+ "grad_norm": 1.0078125,
448
+ "learning_rate": 6.1203319502074694e-06,
449
+ "loss": 0.6938941955566407,
450
+ "step": 3050
451
+ },
452
+ {
453
+ "epoch": 1.2954450480568325,
454
+ "grad_norm": 2.87109375,
455
+ "learning_rate": 6.046235921754594e-06,
456
+ "loss": 0.6913877105712891,
457
+ "step": 3100
458
+ },
459
+ {
460
+ "epoch": 1.316339323025491,
461
+ "grad_norm": 0.451416015625,
462
+ "learning_rate": 5.97213989330172e-06,
463
+ "loss": 0.6920624542236328,
464
+ "step": 3150
465
+ },
466
+ {
467
+ "epoch": 1.3372335979941496,
468
+ "grad_norm": 0.1767578125,
469
+ "learning_rate": 5.898043864848845e-06,
470
+ "loss": 0.6932701873779297,
471
+ "step": 3200
472
+ },
473
+ {
474
+ "epoch": 1.3581278729628081,
475
+ "grad_norm": 5.09765625,
476
+ "learning_rate": 5.82394783639597e-06,
477
+ "loss": 0.6879254150390625,
478
+ "step": 3250
479
+ },
480
+ {
481
+ "epoch": 1.3790221479314668,
482
+ "grad_norm": 1.50390625,
483
+ "learning_rate": 5.749851807943094e-06,
484
+ "loss": 0.6952622222900391,
485
+ "step": 3300
486
+ },
487
+ {
488
+ "epoch": 1.3999164229001253,
489
+ "grad_norm": 0.311279296875,
490
+ "learning_rate": 5.675755779490219e-06,
491
+ "loss": 0.69201171875,
492
+ "step": 3350
493
+ },
494
+ {
495
+ "epoch": 1.420810697868784,
496
+ "grad_norm": 0.9912109375,
497
+ "learning_rate": 5.601659751037345e-06,
498
+ "loss": 0.6865205383300781,
499
+ "step": 3400
500
+ },
501
+ {
502
+ "epoch": 1.4417049728374425,
503
+ "grad_norm": 0.39990234375,
504
+ "learning_rate": 5.52756372258447e-06,
505
+ "loss": 0.6907717895507812,
506
+ "step": 3450
507
+ },
508
+ {
509
+ "epoch": 1.4625992478061012,
510
+ "grad_norm": 1.603515625,
511
+ "learning_rate": 5.4534676941315945e-06,
512
+ "loss": 0.6914924621582031,
513
+ "step": 3500
514
+ },
515
+ {
516
+ "epoch": 1.4834935227747597,
517
+ "grad_norm": 2.12890625,
518
+ "learning_rate": 5.37937166567872e-06,
519
+ "loss": 0.6878433990478515,
520
+ "step": 3550
521
+ },
522
+ {
523
+ "epoch": 1.5043877977434184,
524
+ "grad_norm": 0.4619140625,
525
+ "learning_rate": 5.3052756372258455e-06,
526
+ "loss": 0.6909185791015625,
527
+ "step": 3600
528
+ },
529
+ {
530
+ "epoch": 1.525282072712077,
531
+ "grad_norm": 2.080078125,
532
+ "learning_rate": 5.231179608772971e-06,
533
+ "loss": 0.691602783203125,
534
+ "step": 3650
535
+ },
536
+ {
537
+ "epoch": 1.5461763476807355,
538
+ "grad_norm": 1.4306640625,
539
+ "learning_rate": 5.157083580320096e-06,
540
+ "loss": 0.6940252685546875,
541
+ "step": 3700
542
+ },
543
+ {
544
+ "epoch": 1.567070622649394,
545
+ "grad_norm": 3.1015625,
546
+ "learning_rate": 5.08298755186722e-06,
547
+ "loss": 0.6917591094970703,
548
+ "step": 3750
549
+ },
550
+ {
551
+ "epoch": 1.5879648976180527,
552
+ "grad_norm": 0.25927734375,
553
+ "learning_rate": 5.008891523414345e-06,
554
+ "loss": 0.6908160400390625,
555
+ "step": 3800
556
+ },
557
+ {
558
+ "epoch": 1.6088591725867114,
559
+ "grad_norm": 2.240234375,
560
+ "learning_rate": 4.934795494961471e-06,
561
+ "loss": 0.6898457336425782,
562
+ "step": 3850
563
+ },
564
+ {
565
+ "epoch": 1.6297534475553699,
566
+ "grad_norm": 3.2734375,
567
+ "learning_rate": 4.860699466508595e-06,
568
+ "loss": 0.6905417633056641,
569
+ "step": 3900
570
+ },
571
+ {
572
+ "epoch": 1.6506477225240284,
573
+ "grad_norm": 0.85107421875,
574
+ "learning_rate": 4.78660343805572e-06,
575
+ "loss": 0.6887043762207031,
576
+ "step": 3950
577
+ },
578
+ {
579
+ "epoch": 1.671541997492687,
580
+ "grad_norm": 1.8759765625,
581
+ "learning_rate": 4.7125074096028455e-06,
582
+ "loss": 0.6941480255126953,
583
+ "step": 4000
584
+ },
585
+ {
586
+ "epoch": 1.6924362724613455,
587
+ "grad_norm": 6.47265625,
588
+ "learning_rate": 4.638411381149971e-06,
589
+ "loss": 0.6928147888183593,
590
+ "step": 4050
591
+ },
592
+ {
593
+ "epoch": 1.713330547430004,
594
+ "grad_norm": 0.2098388671875,
595
+ "learning_rate": 4.564315352697096e-06,
596
+ "loss": 0.6905602264404297,
597
+ "step": 4100
598
+ },
599
+ {
600
+ "epoch": 1.7342248223986627,
601
+ "grad_norm": 1.919921875,
602
+ "learning_rate": 4.490219324244221e-06,
603
+ "loss": 0.6873908233642578,
604
+ "step": 4150
605
+ },
606
+ {
607
+ "epoch": 1.7551190973673214,
608
+ "grad_norm": 4.09375,
609
+ "learning_rate": 4.416123295791346e-06,
610
+ "loss": 0.6905323028564453,
611
+ "step": 4200
612
+ },
613
+ {
614
+ "epoch": 1.77601337233598,
615
+ "grad_norm": 1.0400390625,
616
+ "learning_rate": 4.342027267338471e-06,
617
+ "loss": 0.6901638793945313,
618
+ "step": 4250
619
+ },
620
+ {
621
+ "epoch": 1.7969076473046384,
622
+ "grad_norm": 1.4990234375,
623
+ "learning_rate": 4.267931238885596e-06,
624
+ "loss": 0.6905714416503906,
625
+ "step": 4300
626
+ },
627
+ {
628
+ "epoch": 1.817801922273297,
629
+ "grad_norm": 4.66796875,
630
+ "learning_rate": 4.193835210432721e-06,
631
+ "loss": 0.6893930816650391,
632
+ "step": 4350
633
+ },
634
+ {
635
+ "epoch": 1.8386961972419558,
636
+ "grad_norm": 1.47265625,
637
+ "learning_rate": 4.119739181979846e-06,
638
+ "loss": 0.6904594421386718,
639
+ "step": 4400
640
+ },
641
+ {
642
+ "epoch": 1.8595904722106142,
643
+ "grad_norm": 1.9189453125,
644
+ "learning_rate": 4.045643153526971e-06,
645
+ "loss": 0.690783462524414,
646
+ "step": 4450
647
+ },
648
+ {
649
+ "epoch": 1.8804847471792727,
650
+ "grad_norm": 0.8525390625,
651
+ "learning_rate": 3.9715471250740965e-06,
652
+ "loss": 0.6880024719238281,
653
+ "step": 4500
654
+ },
655
+ {
656
+ "epoch": 1.9013790221479314,
657
+ "grad_norm": 1.166015625,
658
+ "learning_rate": 3.897451096621222e-06,
659
+ "loss": 0.6909500885009766,
660
+ "step": 4550
661
+ },
662
+ {
663
+ "epoch": 1.9222732971165901,
664
+ "grad_norm": 3.37109375,
665
+ "learning_rate": 3.823355068168346e-06,
666
+ "loss": 0.6909535980224609,
667
+ "step": 4600
668
+ },
669
+ {
670
+ "epoch": 1.9431675720852486,
671
+ "grad_norm": 4.55078125,
672
+ "learning_rate": 3.7492590397154714e-06,
673
+ "loss": 0.6858901977539062,
674
+ "step": 4650
675
+ },
676
+ {
677
+ "epoch": 1.964061847053907,
678
+ "grad_norm": 1.59375,
679
+ "learning_rate": 3.675163011262597e-06,
680
+ "loss": 0.6897322845458984,
681
+ "step": 4700
682
+ },
683
+ {
684
+ "epoch": 1.9849561220225658,
685
+ "grad_norm": 3.55859375,
686
+ "learning_rate": 3.6010669828097216e-06,
687
+ "loss": 0.6893775939941407,
688
+ "step": 4750
689
+ },
690
+ {
691
+ "epoch": 2.0,
692
+ "eval_accuracy": 0.5389196531187964,
693
+ "eval_f1": 0.7003869916491275,
694
+ "eval_loss": 0.6902709603309631,
695
+ "eval_precision": 0.5389196531187964,
696
+ "eval_recall": 1.0,
697
+ "eval_roc_auc": 0.4943111301719065,
698
+ "eval_runtime": 75.9633,
699
+ "eval_samples_per_second": 125.995,
700
+ "eval_steps_per_second": 7.885,
701
+ "step": 4786
702
  }
703
  ],
704
  "logging_steps": 50,
 
713
  "early_stopping_threshold": 0.0
714
  },
715
  "attributes": {
716
+ "early_stopping_patience_counter": 1
717
  }
718
  },
719
  "TrainerControl": {
 
727
  "attributes": {}
728
  }
729
  },
730
+ "total_flos": 1.3062259262328e+16,
731
  "train_batch_size": 16,
732
  "trial_name": null,
733
  "trial_params": null