Hugging Face's logo

lesso05
/
7c8a96e4-2435-4ed1-9472-d8a82555d692

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
lesso05 commited on
Commit
4ba2e3f
•
1 Parent(s): 68f8981

Training in progress, step 100, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +203 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48e94eb5d1f35a84a609e8fc66b592d5e1fe9fd3d3b9828107f465206ca7a65d
3
  size 13587864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3b818fa9c963127aefdd51c4f484737e3721fa3d702cbbea52f75728cf1ff4b
3
  size 13587864
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:673c2073c63e037a0ac62f48002fde83143bab4f5cbd75651c78077c2a746d9b
3
  size 27273018
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2f343ec611b2eed0154e9ae295b48c63eedbb65606c83c3f794de2b10b8c7b0
3
  size 27273018
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0ca68467fe19a421e73f238f6b32ccc921b45fec96586b7d92691addfd48a3a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17e0ea5618c1a5f6de24fc69220ff18c7e915c4fea8c358992bacf9ea1f186dd
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": 0.12886597938144329,
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": 0.0677,
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": 2020086877519872.0,
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": 0.1718213058419244,
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": 0.0677,
606
  "step": 75
607
+ },
608
+ {
609
+ "epoch": 0.13058419243986255,
610
+ "grad_norm": 3.348130702972412,
611
+ "learning_rate": 1.6543469682057106e-05,
612
+ "loss": 0.1091,
613
+ "step": 76
614
+ },
615
+ {
616
+ "epoch": 0.1323024054982818,
617
+ "grad_norm": 6.107163906097412,
618
+ "learning_rate": 1.526708147705013e-05,
619
+ "loss": 0.5306,
620
+ "step": 77
621
+ },
622
+ {
623
+ "epoch": 0.13402061855670103,
624
+ "grad_norm": 0.3043591380119324,
625
+ "learning_rate": 1.4033009983067452e-05,
626
+ "loss": 0.0641,
627
+ "step": 78
628
+ },
629
+ {
630
+ "epoch": 0.13573883161512026,
631
+ "grad_norm": 0.302204430103302,
632
+ "learning_rate": 1.2842758726130283e-05,
633
+ "loss": 0.0642,
634
+ "step": 79
635
+ },
636
+ {
637
+ "epoch": 0.13745704467353953,
638
+ "grad_norm": 0.28447940945625305,
639
+ "learning_rate": 1.1697777844051105e-05,
640
+ "loss": 0.0613,
641
+ "step": 80
642
+ },
643
+ {
644
+ "epoch": 0.13917525773195877,
645
+ "grad_norm": 0.27646705508232117,
646
+ "learning_rate": 1.0599462319663905e-05,
647
+ "loss": 0.0605,
648
+ "step": 81
649
+ },
650
+ {
651
+ "epoch": 0.13917525773195877,
652
+ "eval_loss": 0.09266447275876999,
653
+ "eval_runtime": 8.7152,
654
+ "eval_samples_per_second": 56.224,
655
+ "eval_steps_per_second": 7.114,
656
+ "step": 81
657
+ },
658
+ {
659
+ "epoch": 0.140893470790378,
660
+ "grad_norm": 0.8577637672424316,
661
+ "learning_rate": 9.549150281252633e-06,
662
+ "loss": 0.0687,
663
+ "step": 82
664
+ },
665
+ {
666
+ "epoch": 0.14261168384879724,
667
+ "grad_norm": 0.28629401326179504,
668
+ "learning_rate": 8.548121372247918e-06,
669
+ "loss": 0.0606,
670
+ "step": 83
671
+ },
672
+ {
673
+ "epoch": 0.14432989690721648,
674
+ "grad_norm": 0.4762267768383026,
675
+ "learning_rate": 7.597595192178702e-06,
676
+ "loss": 0.0751,
677
+ "step": 84
678
+ },
679
+ {
680
+ "epoch": 0.14604810996563575,
681
+ "grad_norm": 0.2938355803489685,
682
+ "learning_rate": 6.698729810778065e-06,
683
+ "loss": 0.0586,
684
+ "step": 85
685
+ },
686
+ {
687
+ "epoch": 0.14776632302405499,
688
+ "grad_norm": 0.28194454312324524,
689
+ "learning_rate": 5.852620357053651e-06,
690
+ "loss": 0.0568,
691
+ "step": 86
692
+ },
693
+ {
694
+ "epoch": 0.14948453608247422,
695
+ "grad_norm": 0.28809523582458496,
696
+ "learning_rate": 5.060297685041659e-06,
697
+ "loss": 0.0584,
698
+ "step": 87
699
+ },
700
+ {
701
+ "epoch": 0.15120274914089346,
702
+ "grad_norm": 0.25631386041641235,
703
+ "learning_rate": 4.322727117869951e-06,
704
+ "loss": 0.0542,
705
+ "step": 88
706
+ },
707
+ {
708
+ "epoch": 0.15292096219931273,
709
+ "grad_norm": 0.3819483518600464,
710
+ "learning_rate": 3.6408072716606346e-06,
711
+ "loss": 0.0594,
712
+ "step": 89
713
+ },
714
+ {
715
+ "epoch": 0.15463917525773196,
716
+ "grad_norm": 0.467550665140152,
717
+ "learning_rate": 3.0153689607045845e-06,
718
+ "loss": 0.0749,
719
+ "step": 90
720
+ },
721
+ {
722
+ "epoch": 0.15463917525773196,
723
+ "eval_loss": 0.08718819171190262,
724
+ "eval_runtime": 8.6945,
725
+ "eval_samples_per_second": 56.358,
726
+ "eval_steps_per_second": 7.131,
727
+ "step": 90
728
+ },
729
+ {
730
+ "epoch": 0.1563573883161512,
731
+ "grad_norm": 0.3134761154651642,
732
+ "learning_rate": 2.4471741852423237e-06,
733
+ "loss": 0.0602,
734
+ "step": 91
735
+ },
736
+ {
737
+ "epoch": 0.15807560137457044,
738
+ "grad_norm": 0.268108069896698,
739
+ "learning_rate": 1.9369152030840556e-06,
740
+ "loss": 0.0575,
741
+ "step": 92
742
+ },
743
+ {
744
+ "epoch": 0.15979381443298968,
745
+ "grad_norm": 0.2512245774269104,
746
+ "learning_rate": 1.4852136862001764e-06,
747
+ "loss": 0.0544,
748
+ "step": 93
749
+ },
750
+ {
751
+ "epoch": 0.16151202749140894,
752
+ "grad_norm": 2.219799280166626,
753
+ "learning_rate": 1.0926199633097157e-06,
754
+ "loss": 0.0984,
755
+ "step": 94
756
+ },
757
+ {
758
+ "epoch": 0.16323024054982818,
759
+ "grad_norm": 0.2962862253189087,
760
+ "learning_rate": 7.596123493895991e-07,
761
+ "loss": 0.0569,
762
+ "step": 95
763
+ },
764
+ {
765
+ "epoch": 0.16494845360824742,
766
+ "grad_norm": 0.2534407079219818,
767
+ "learning_rate": 4.865965629214819e-07,
768
+ "loss": 0.0563,
769
+ "step": 96
770
+ },
771
+ {
772
+ "epoch": 0.16666666666666666,
773
+ "grad_norm": 0.30495700240135193,
774
+ "learning_rate": 2.7390523158633554e-07,
775
+ "loss": 0.0575,
776
+ "step": 97
777
+ },
778
+ {
779
+ "epoch": 0.16838487972508592,
780
+ "grad_norm": 0.5423720479011536,
781
+ "learning_rate": 1.2179748700879012e-07,
782
+ "loss": 0.0793,
783
+ "step": 98
784
+ },
785
+ {
786
+ "epoch": 0.17010309278350516,
787
+ "grad_norm": 0.25193852186203003,
788
+ "learning_rate": 3.04586490452119e-08,
789
+ "loss": 0.055,
790
+ "step": 99
791
+ },
792
+ {
793
+ "epoch": 0.17010309278350516,
794
+ "eval_loss": 0.08638428151607513,
795
+ "eval_runtime": 8.6961,
796
+ "eval_samples_per_second": 56.347,
797
+ "eval_steps_per_second": 7.13,
798
+ "step": 99
799
+ },
800
+ {
801
+ "epoch": 0.1718213058419244,
802
+ "grad_norm": 0.30860844254493713,
803
+ "learning_rate": 0.0,
804
+ "loss": 0.0568,
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": 2665681652809728.0,
826
  "train_batch_size": 8,
827
  "trial_name": null,
828
  "trial_params": null