lesso07 commited on
Commit
956b610
1 Parent(s): 1ed05d1

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 sha256:4b6292d46eec6d02e1a69cbc9453f408592da5724072ce3b7ce74bcea977921c
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c99554d818c72138fe61c121efd0f17db3714fb9aec6ab0ab5d2c723609f12cf
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:856e7f4a5693f400bafddf6276c335ff6ff75a7b538b2524461a7aa4747c4814
3
  size 335922386
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec02e057b30fe720fab2ccd13847f8802a9ceda90785aacf253d3ab358a7275c
3
  size 335922386
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aeda752780d4d1e2c8cc72596036685baf31024a594da9ff5aea8a1a54a0f80c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b23184210b5274d29d7aab370a6df28ffac3ad6df598e0776930b01f3163f7d
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.0038875210574057274,
5
  "eval_steps": 9,
6
- "global_step": 75,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -604,6 +604,205 @@
604
  "learning_rate": 1.7860619515673033e-05,
605
  "loss": 2.3924,
606
  "step": 75
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
607
  }
608
  ],
609
  "logging_steps": 1,
@@ -618,12 +817,12 @@
618
  "should_evaluate": false,
619
  "should_log": false,
620
  "should_save": true,
621
- "should_training_stop": false
622
  },
623
  "attributes": {}
624
  }
625
  },
626
- "total_flos": 5.56415462670336e+16,
627
  "train_batch_size": 8,
628
  "trial_name": null,
629
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.005183361409874304,
5
  "eval_steps": 9,
6
+ "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
604
  "learning_rate": 1.7860619515673033e-05,
605
  "loss": 2.3924,
606
  "step": 75
607
+ },
608
+ {
609
+ "epoch": 0.003939354671504471,
610
+ "grad_norm": 1.9035282135009766,
611
+ "learning_rate": 1.6543469682057106e-05,
612
+ "loss": 2.1904,
613
+ "step": 76
614
+ },
615
+ {
616
+ "epoch": 0.0039911882856032135,
617
+ "grad_norm": 1.868543028831482,
618
+ "learning_rate": 1.526708147705013e-05,
619
+ "loss": 2.3523,
620
+ "step": 77
621
+ },
622
+ {
623
+ "epoch": 0.004043021899701957,
624
+ "grad_norm": 1.9037656784057617,
625
+ "learning_rate": 1.4033009983067452e-05,
626
+ "loss": 2.3251,
627
+ "step": 78
628
+ },
629
+ {
630
+ "epoch": 0.0040948555138007,
631
+ "grad_norm": 1.8855937719345093,
632
+ "learning_rate": 1.2842758726130283e-05,
633
+ "loss": 1.974,
634
+ "step": 79
635
+ },
636
+ {
637
+ "epoch": 0.004146689127899443,
638
+ "grad_norm": 1.6533581018447876,
639
+ "learning_rate": 1.1697777844051105e-05,
640
+ "loss": 2.1961,
641
+ "step": 80
642
+ },
643
+ {
644
+ "epoch": 0.004198522741998186,
645
+ "grad_norm": 1.6351205110549927,
646
+ "learning_rate": 1.0599462319663905e-05,
647
+ "loss": 2.2121,
648
+ "step": 81
649
+ },
650
+ {
651
+ "epoch": 0.004198522741998186,
652
+ "eval_loss": 2.2391388416290283,
653
+ "eval_runtime": 1773.2182,
654
+ "eval_samples_per_second": 9.162,
655
+ "eval_steps_per_second": 1.145,
656
+ "step": 81
657
+ },
658
+ {
659
+ "epoch": 0.004250356356096929,
660
+ "grad_norm": 1.744607925415039,
661
+ "learning_rate": 9.549150281252633e-06,
662
+ "loss": 2.1732,
663
+ "step": 82
664
+ },
665
+ {
666
+ "epoch": 0.004302189970195672,
667
+ "grad_norm": 1.846276044845581,
668
+ "learning_rate": 8.548121372247918e-06,
669
+ "loss": 2.0788,
670
+ "step": 83
671
+ },
672
+ {
673
+ "epoch": 0.004354023584294415,
674
+ "grad_norm": 1.7794817686080933,
675
+ "learning_rate": 7.597595192178702e-06,
676
+ "loss": 2.2174,
677
+ "step": 84
678
+ },
679
+ {
680
+ "epoch": 0.004405857198393158,
681
+ "grad_norm": 1.8473767042160034,
682
+ "learning_rate": 6.698729810778065e-06,
683
+ "loss": 2.1947,
684
+ "step": 85
685
+ },
686
+ {
687
+ "epoch": 0.004457690812491901,
688
+ "grad_norm": 1.684167742729187,
689
+ "learning_rate": 5.852620357053651e-06,
690
+ "loss": 2.1724,
691
+ "step": 86
692
+ },
693
+ {
694
+ "epoch": 0.004509524426590644,
695
+ "grad_norm": 1.7272619009017944,
696
+ "learning_rate": 5.060297685041659e-06,
697
+ "loss": 2.2323,
698
+ "step": 87
699
+ },
700
+ {
701
+ "epoch": 0.004561358040689387,
702
+ "grad_norm": 1.6552352905273438,
703
+ "learning_rate": 4.322727117869951e-06,
704
+ "loss": 2.1764,
705
+ "step": 88
706
+ },
707
+ {
708
+ "epoch": 0.00461319165478813,
709
+ "grad_norm": 1.6339068412780762,
710
+ "learning_rate": 3.6408072716606346e-06,
711
+ "loss": 2.4096,
712
+ "step": 89
713
+ },
714
+ {
715
+ "epoch": 0.004665025268886873,
716
+ "grad_norm": 1.717753291130066,
717
+ "learning_rate": 3.0153689607045845e-06,
718
+ "loss": 2.1329,
719
+ "step": 90
720
+ },
721
+ {
722
+ "epoch": 0.004665025268886873,
723
+ "eval_loss": 2.235034465789795,
724
+ "eval_runtime": 1771.9502,
725
+ "eval_samples_per_second": 9.169,
726
+ "eval_steps_per_second": 1.146,
727
+ "step": 90
728
+ },
729
+ {
730
+ "epoch": 0.004716858882985616,
731
+ "grad_norm": 1.6244786977767944,
732
+ "learning_rate": 2.4471741852423237e-06,
733
+ "loss": 2.1637,
734
+ "step": 91
735
+ },
736
+ {
737
+ "epoch": 0.0047686924970843595,
738
+ "grad_norm": 1.8540843725204468,
739
+ "learning_rate": 1.9369152030840556e-06,
740
+ "loss": 2.1113,
741
+ "step": 92
742
+ },
743
+ {
744
+ "epoch": 0.004820526111183102,
745
+ "grad_norm": 1.5808759927749634,
746
+ "learning_rate": 1.4852136862001764e-06,
747
+ "loss": 2.3416,
748
+ "step": 93
749
+ },
750
+ {
751
+ "epoch": 0.004872359725281846,
752
+ "grad_norm": 2.3207199573516846,
753
+ "learning_rate": 1.0926199633097157e-06,
754
+ "loss": 2.2717,
755
+ "step": 94
756
+ },
757
+ {
758
+ "epoch": 0.004924193339380588,
759
+ "grad_norm": 1.8996020555496216,
760
+ "learning_rate": 7.596123493895991e-07,
761
+ "loss": 2.1846,
762
+ "step": 95
763
+ },
764
+ {
765
+ "epoch": 0.004976026953479332,
766
+ "grad_norm": 1.9061933755874634,
767
+ "learning_rate": 4.865965629214819e-07,
768
+ "loss": 2.3429,
769
+ "step": 96
770
+ },
771
+ {
772
+ "epoch": 0.005027860567578074,
773
+ "grad_norm": 1.855987310409546,
774
+ "learning_rate": 2.7390523158633554e-07,
775
+ "loss": 2.276,
776
+ "step": 97
777
+ },
778
+ {
779
+ "epoch": 0.005079694181676818,
780
+ "grad_norm": 2.0523297786712646,
781
+ "learning_rate": 1.2179748700879012e-07,
782
+ "loss": 2.0707,
783
+ "step": 98
784
+ },
785
+ {
786
+ "epoch": 0.00513152779577556,
787
+ "grad_norm": 1.991876482963562,
788
+ "learning_rate": 3.04586490452119e-08,
789
+ "loss": 2.0749,
790
+ "step": 99
791
+ },
792
+ {
793
+ "epoch": 0.00513152779577556,
794
+ "eval_loss": 2.2339484691619873,
795
+ "eval_runtime": 1772.5813,
796
+ "eval_samples_per_second": 9.166,
797
+ "eval_steps_per_second": 1.146,
798
+ "step": 99
799
+ },
800
+ {
801
+ "epoch": 0.005183361409874304,
802
+ "grad_norm": 1.7509509325027466,
803
+ "learning_rate": 0.0,
804
+ "loss": 2.2408,
805
+ "step": 100
806
  }
807
  ],
808
  "logging_steps": 1,
 
817
  "should_evaluate": false,
818
  "should_log": false,
819
  "should_save": true,
820
+ "should_training_stop": true
821
  },
822
  "attributes": {}
823
  }
824
  },
825
+ "total_flos": 7.41887283560448e+16,
826
  "train_batch_size": 8,
827
  "trial_name": null,
828
  "trial_params": null