Hugging Face's logo

lesso01
/
d31b7bd2-26f5-4953-a736-c12b149775f4

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
lesso01 commited on
Commit
5468aa4
•
1 Parent(s): 6fc158c

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 sha256:5b8cbe3d7be413bd5c9511e8ede138bc854ff4cffb7ba570b9630ab0854a8ff7
3
  size 50624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8793ec5cc00edf489781b7263da0492106d31c5b7e6deecdbfb7bfc184070c0
3
  size 50624
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:94bef94344ec67c8862602bcf3c73365e5d4ba014caab4d789681ee7ee982d3d
3
  size 118090
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c665419f5d780fa6193faf8d212deedbc34655dd8ab301aafde05a61884cc1ba
3
  size 118090
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9418a68e5819dc4b84034984f04774a6cc7da23a601f4d1f77e1c7bf288f18ec
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b90bb01bd18cd5ed9c3ad0e7c720f1f4ed6be5aab64ae39643b6cbe6410d3d3
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": 0.5836575875486382,
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": 10.357,
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": 5491756892160.0,
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": 0.7782101167315175,
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": 10.357,
606
  "step": 75
607
+ },
608
+ {
609
+ "epoch": 0.5914396887159533,
610
+ "grad_norm": 0.0,
611
+ "learning_rate": 1.6543469682057106e-05,
612
+ "loss": 0.0,
613
+ "step": 76
614
+ },
615
+ {
616
+ "epoch": 0.5992217898832685,
617
+ "grad_norm": 0.4258427619934082,
618
+ "learning_rate": 1.526708147705013e-05,
619
+ "loss": 10.3103,
620
+ "step": 77
621
+ },
622
+ {
623
+ "epoch": 0.6070038910505836,
624
+ "grad_norm": 0.3290005326271057,
625
+ "learning_rate": 1.4033009983067452e-05,
626
+ "loss": 10.3019,
627
+ "step": 78
628
+ },
629
+ {
630
+ "epoch": 0.6147859922178989,
631
+ "grad_norm": 0.16638368368148804,
632
+ "learning_rate": 1.2842758726130283e-05,
633
+ "loss": 10.3301,
634
+ "step": 79
635
+ },
636
+ {
637
+ "epoch": 0.622568093385214,
638
+ "grad_norm": 0.0,
639
+ "learning_rate": 1.1697777844051105e-05,
640
+ "loss": 0.0,
641
+ "step": 80
642
+ },
643
+ {
644
+ "epoch": 0.6303501945525292,
645
+ "grad_norm": 0.20695820450782776,
646
+ "learning_rate": 1.0599462319663905e-05,
647
+ "loss": 10.3287,
648
+ "step": 81
649
+ },
650
+ {
651
+ "epoch": 0.6303501945525292,
652
+ "eval_loss": NaN,
653
+ "eval_runtime": 0.4656,
654
+ "eval_samples_per_second": 231.97,
655
+ "eval_steps_per_second": 30.07,
656
+ "step": 81
657
+ },
658
+ {
659
+ "epoch": 0.6381322957198443,
660
+ "grad_norm": 0.28333377838134766,
661
+ "learning_rate": 9.549150281252633e-06,
662
+ "loss": 10.3335,
663
+ "step": 82
664
+ },
665
+ {
666
+ "epoch": 0.6459143968871596,
667
+ "grad_norm": 0.0,
668
+ "learning_rate": 8.548121372247918e-06,
669
+ "loss": 0.0,
670
+ "step": 83
671
+ },
672
+ {
673
+ "epoch": 0.6536964980544747,
674
+ "grad_norm": 0.0,
675
+ "learning_rate": 7.597595192178702e-06,
676
+ "loss": 0.0,
677
+ "step": 84
678
+ },
679
+ {
680
+ "epoch": 0.6614785992217899,
681
+ "grad_norm": 0.22484956681728363,
682
+ "learning_rate": 6.698729810778065e-06,
683
+ "loss": 10.3235,
684
+ "step": 85
685
+ },
686
+ {
687
+ "epoch": 0.669260700389105,
688
+ "grad_norm": 0.15221866965293884,
689
+ "learning_rate": 5.852620357053651e-06,
690
+ "loss": 10.3531,
691
+ "step": 86
692
+ },
693
+ {
694
+ "epoch": 0.6770428015564203,
695
+ "grad_norm": 0.12713178992271423,
696
+ "learning_rate": 5.060297685041659e-06,
697
+ "loss": 10.3367,
698
+ "step": 87
699
+ },
700
+ {
701
+ "epoch": 0.6848249027237354,
702
+ "grad_norm": 0.17537634074687958,
703
+ "learning_rate": 4.322727117869951e-06,
704
+ "loss": 10.3255,
705
+ "step": 88
706
+ },
707
+ {
708
+ "epoch": 0.6926070038910506,
709
+ "grad_norm": 0.1998535841703415,
710
+ "learning_rate": 3.6408072716606346e-06,
711
+ "loss": 10.3831,
712
+ "step": 89
713
+ },
714
+ {
715
+ "epoch": 0.7003891050583657,
716
+ "grad_norm": 0.1796063929796219,
717
+ "learning_rate": 3.0153689607045845e-06,
718
+ "loss": 10.3197,
719
+ "step": 90
720
+ },
721
+ {
722
+ "epoch": 0.7003891050583657,
723
+ "eval_loss": NaN,
724
+ "eval_runtime": 0.4096,
725
+ "eval_samples_per_second": 263.683,
726
+ "eval_steps_per_second": 34.181,
727
+ "step": 90
728
+ },
729
+ {
730
+ "epoch": 0.708171206225681,
731
+ "grad_norm": 0.20497995615005493,
732
+ "learning_rate": 2.4471741852423237e-06,
733
+ "loss": 10.3191,
734
+ "step": 91
735
+ },
736
+ {
737
+ "epoch": 0.7159533073929961,
738
+ "grad_norm": 0.4476834833621979,
739
+ "learning_rate": 1.9369152030840556e-06,
740
+ "loss": 10.3319,
741
+ "step": 92
742
+ },
743
+ {
744
+ "epoch": 0.7237354085603113,
745
+ "grad_norm": 0.5001630187034607,
746
+ "learning_rate": 1.4852136862001764e-06,
747
+ "loss": 10.2647,
748
+ "step": 93
749
+ },
750
+ {
751
+ "epoch": 0.7315175097276264,
752
+ "grad_norm": 0.3534506857395172,
753
+ "learning_rate": 1.0926199633097157e-06,
754
+ "loss": 10.2811,
755
+ "step": 94
756
+ },
757
+ {
758
+ "epoch": 0.7392996108949417,
759
+ "grad_norm": 0.32725393772125244,
760
+ "learning_rate": 7.596123493895991e-07,
761
+ "loss": 10.3196,
762
+ "step": 95
763
+ },
764
+ {
765
+ "epoch": 0.7470817120622568,
766
+ "grad_norm": 0.1588638424873352,
767
+ "learning_rate": 4.865965629214819e-07,
768
+ "loss": 10.354,
769
+ "step": 96
770
+ },
771
+ {
772
+ "epoch": 0.754863813229572,
773
+ "grad_norm": 0.3359444737434387,
774
+ "learning_rate": 2.7390523158633554e-07,
775
+ "loss": 10.3324,
776
+ "step": 97
777
+ },
778
+ {
779
+ "epoch": 0.7626459143968871,
780
+ "grad_norm": 0.0,
781
+ "learning_rate": 1.2179748700879012e-07,
782
+ "loss": 0.0,
783
+ "step": 98
784
+ },
785
+ {
786
+ "epoch": 0.7704280155642024,
787
+ "grad_norm": 0.1817806214094162,
788
+ "learning_rate": 3.04586490452119e-08,
789
+ "loss": 10.3151,
790
+ "step": 99
791
+ },
792
+ {
793
+ "epoch": 0.7704280155642024,
794
+ "eval_loss": NaN,
795
+ "eval_runtime": 0.3852,
796
+ "eval_samples_per_second": 280.368,
797
+ "eval_steps_per_second": 36.344,
798
+ "step": 99
799
+ },
800
+ {
801
+ "epoch": 0.7782101167315175,
802
+ "grad_norm": 0.19820758700370789,
803
+ "learning_rate": 0.0,
804
+ "loss": 10.3539,
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": 7400796192768.0,
826
  "train_batch_size": 8,
827
  "trial_name": null,
828
  "trial_params": null