Hugging Face's logo

obss
/
bsm-pegasus-xsum-multi

Transformers
PyTorch
pegasus
text2text-generation
Model card Files
xet
 Community
Sophylax commited on
Commit
4e3edec
·
1 Parent(s): c80fa46

Training in progress, epoch 3

Browse files
Files changed (6) hide show
  1. last-checkpoint/optimizer.pt +1 -1
  2. last-checkpoint/pytorch_model.bin +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +237 -3
  6. pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ad530ee889033f9a2f7c560dc52bf4118724afc32c9c86f9cb4457131861d78
3
  size 4549998883
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52715dfc3efd5dfd23fc876c6cf26e7723d021f8c84aaf09b7fcf594a8a4331e
3
  size 4549998883
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fc21576ed95891e64a486b1f7ef752722596ed23703a971c08d0475ce291567
3
  size 2279605745
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1af78294b1e631e2f3f3424d3c86953ce7232c3bfecfe21b138a361faf52d2ba
3
  size 2279605745
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73b11f621f22b71e8973444c909d4acab2fab9804169fd0e0240834531353e4b
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ef47b6f9f80dfcd854fc4a608818f9ee67f0971231e89a4bf7e8bd5e9ce2fc1
3
  size 14503
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85f7c916e36ba7cd34e128262c5bd2901df367b9bd0b62634211255bc422d724
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:533eea697fe12cf9049fe226ac477859ceabfc7fd6426babe1b3fb80d2113d2c
3
  size 623
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 2.0,
5
- "global_step": 39272,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -474,11 +474,245 @@
474
  "learning_rate": 1.801385210837238e-05,
475
  "loss": 1.9604,
476
  "step": 39000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
477
  }
478
  ],
479
  "max_steps": 392720,
480
  "num_train_epochs": 20,
481
- "total_flos": 1.5020768451905126e+17,
482
  "trial_name": null,
483
  "trial_params": null
484
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 58908,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
474
  "learning_rate": 1.801385210837238e-05,
475
  "loss": 1.9604,
476
  "step": 39000
477
+ },
478
+ {
479
+ "epoch": 2.01,
480
+ "learning_rate": 1.798838867386433e-05,
481
+ "loss": 1.9376,
482
+ "step": 39500
483
+ },
484
+ {
485
+ "epoch": 2.04,
486
+ "learning_rate": 1.7962925239356287e-05,
487
+ "loss": 1.9137,
488
+ "step": 40000
489
+ },
490
+ {
491
+ "epoch": 2.06,
492
+ "learning_rate": 1.793746180484824e-05,
493
+ "loss": 1.9028,
494
+ "step": 40500
495
+ },
496
+ {
497
+ "epoch": 2.09,
498
+ "learning_rate": 1.7911998370340194e-05,
499
+ "loss": 1.9051,
500
+ "step": 41000
501
+ },
502
+ {
503
+ "epoch": 2.11,
504
+ "learning_rate": 1.7886534935832146e-05,
505
+ "loss": 1.9191,
506
+ "step": 41500
507
+ },
508
+ {
509
+ "epoch": 2.14,
510
+ "learning_rate": 1.7861071501324102e-05,
511
+ "loss": 1.9182,
512
+ "step": 42000
513
+ },
514
+ {
515
+ "epoch": 2.16,
516
+ "learning_rate": 1.7835608066816054e-05,
517
+ "loss": 1.9034,
518
+ "step": 42500
519
+ },
520
+ {
521
+ "epoch": 2.19,
522
+ "learning_rate": 1.7810144632308006e-05,
523
+ "loss": 1.8982,
524
+ "step": 43000
525
+ },
526
+ {
527
+ "epoch": 2.22,
528
+ "learning_rate": 1.778468119779996e-05,
529
+ "loss": 1.9142,
530
+ "step": 43500
531
+ },
532
+ {
533
+ "epoch": 2.24,
534
+ "learning_rate": 1.7759217763291913e-05,
535
+ "loss": 1.9197,
536
+ "step": 44000
537
+ },
538
+ {
539
+ "epoch": 2.27,
540
+ "learning_rate": 1.773375432878387e-05,
541
+ "loss": 1.9035,
542
+ "step": 44500
543
+ },
544
+ {
545
+ "epoch": 2.29,
546
+ "learning_rate": 1.770829089427582e-05,
547
+ "loss": 1.9076,
548
+ "step": 45000
549
+ },
550
+ {
551
+ "epoch": 2.32,
552
+ "learning_rate": 1.7682827459767776e-05,
553
+ "loss": 1.9007,
554
+ "step": 45500
555
+ },
556
+ {
557
+ "epoch": 2.34,
558
+ "learning_rate": 1.7657364025259728e-05,
559
+ "loss": 1.8958,
560
+ "step": 46000
561
+ },
562
+ {
563
+ "epoch": 2.37,
564
+ "learning_rate": 1.7631900590751684e-05,
565
+ "loss": 1.9007,
566
+ "step": 46500
567
+ },
568
+ {
569
+ "epoch": 2.39,
570
+ "learning_rate": 1.7606437156243636e-05,
571
+ "loss": 1.9072,
572
+ "step": 47000
573
+ },
574
+ {
575
+ "epoch": 2.42,
576
+ "learning_rate": 1.7580973721735588e-05,
577
+ "loss": 1.9159,
578
+ "step": 47500
579
+ },
580
+ {
581
+ "epoch": 2.44,
582
+ "learning_rate": 1.7555510287227543e-05,
583
+ "loss": 1.9098,
584
+ "step": 48000
585
+ },
586
+ {
587
+ "epoch": 2.47,
588
+ "learning_rate": 1.7530046852719495e-05,
589
+ "loss": 1.9085,
590
+ "step": 48500
591
+ },
592
+ {
593
+ "epoch": 2.5,
594
+ "learning_rate": 1.750458341821145e-05,
595
+ "loss": 1.8881,
596
+ "step": 49000
597
+ },
598
+ {
599
+ "epoch": 2.52,
600
+ "learning_rate": 1.7479119983703403e-05,
601
+ "loss": 1.8844,
602
+ "step": 49500
603
+ },
604
+ {
605
+ "epoch": 2.55,
606
+ "learning_rate": 1.7453656549195358e-05,
607
+ "loss": 1.9133,
608
+ "step": 50000
609
+ },
610
+ {
611
+ "epoch": 2.57,
612
+ "learning_rate": 1.742819311468731e-05,
613
+ "loss": 1.9036,
614
+ "step": 50500
615
+ },
616
+ {
617
+ "epoch": 2.6,
618
+ "learning_rate": 1.7402729680179266e-05,
619
+ "loss": 1.9144,
620
+ "step": 51000
621
+ },
622
+ {
623
+ "epoch": 2.62,
624
+ "learning_rate": 1.7377266245671218e-05,
625
+ "loss": 1.8944,
626
+ "step": 51500
627
+ },
628
+ {
629
+ "epoch": 2.65,
630
+ "learning_rate": 1.7351802811163173e-05,
631
+ "loss": 1.9044,
632
+ "step": 52000
633
+ },
634
+ {
635
+ "epoch": 2.67,
636
+ "learning_rate": 1.7326339376655125e-05,
637
+ "loss": 1.9013,
638
+ "step": 52500
639
+ },
640
+ {
641
+ "epoch": 2.7,
642
+ "learning_rate": 1.7300875942147077e-05,
643
+ "loss": 1.8929,
644
+ "step": 53000
645
+ },
646
+ {
647
+ "epoch": 2.72,
648
+ "learning_rate": 1.7275412507639033e-05,
649
+ "loss": 1.8953,
650
+ "step": 53500
651
+ },
652
+ {
653
+ "epoch": 2.75,
654
+ "learning_rate": 1.7249949073130985e-05,
655
+ "loss": 1.8984,
656
+ "step": 54000
657
+ },
658
+ {
659
+ "epoch": 2.78,
660
+ "learning_rate": 1.722448563862294e-05,
661
+ "loss": 1.8779,
662
+ "step": 54500
663
+ },
664
+ {
665
+ "epoch": 2.8,
666
+ "learning_rate": 1.7199022204114892e-05,
667
+ "loss": 1.9027,
668
+ "step": 55000
669
+ },
670
+ {
671
+ "epoch": 2.83,
672
+ "learning_rate": 1.7173558769606847e-05,
673
+ "loss": 1.8971,
674
+ "step": 55500
675
+ },
676
+ {
677
+ "epoch": 2.85,
678
+ "learning_rate": 1.71480953350988e-05,
679
+ "loss": 1.9017,
680
+ "step": 56000
681
+ },
682
+ {
683
+ "epoch": 2.88,
684
+ "learning_rate": 1.7122631900590755e-05,
685
+ "loss": 1.8967,
686
+ "step": 56500
687
+ },
688
+ {
689
+ "epoch": 2.9,
690
+ "learning_rate": 1.7097168466082707e-05,
691
+ "loss": 1.8991,
692
+ "step": 57000
693
+ },
694
+ {
695
+ "epoch": 2.93,
696
+ "learning_rate": 1.707170503157466e-05,
697
+ "loss": 1.9058,
698
+ "step": 57500
699
+ },
700
+ {
701
+ "epoch": 2.95,
702
+ "learning_rate": 1.7046241597066614e-05,
703
+ "loss": 1.8997,
704
+ "step": 58000
705
+ },
706
+ {
707
+ "epoch": 2.98,
708
+ "learning_rate": 1.7020778162558566e-05,
709
+ "loss": 1.8926,
710
+ "step": 58500
711
  }
712
  ],
713
  "max_steps": 392720,
714
  "num_train_epochs": 20,
715
+ "total_flos": 2.252811225021481e+17,
716
  "trial_name": null,
717
  "trial_params": null
718
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fc21576ed95891e64a486b1f7ef752722596ed23703a971c08d0475ce291567
3
  size 2279605745
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1af78294b1e631e2f3f3424d3c86953ce7232c3bfecfe21b138a361faf52d2ba
3
  size 2279605745