Hugging Face's logo

lesso11
/
aef29f45-8cbf-4b56-9293-9e56126f889e

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
lesso11 commited on
Commit
33df139
•
1 Parent(s): 1211351

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 sha256:08e8f236ddc10d222b452de6add8c677dadee23ccf4fc5bcb9ea3cf2ce3d9a63
3
  size 767856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eda950d1b0d21244c0faa8b6de5b16dae368a9f2dc91f0abeb165a97a246355e
3
  size 767856
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:547db67dff947af01503691e9c9cb4bb33f39e71f280016ee6de23e93b44192e
3
  size 1601338
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecf95593eaa7e0b936d9a34d66c25b6921b819b5d1b68e92e853d3858ec65ee1
3
  size 1601338
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:918745a6ed2ec5b68116d4c4abbbcd68f28310827cc74e2c6f42fa8fb9df5afa
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f140d69a5a4a0bf3b26b9d3aba9c27a88cd6aa8c433272320d770918ce7003f1
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": 0.19710906701708278,
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": 7.0153,
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": 35701618900992.0,
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": 0.2628120893561104,
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": 7.0153,
606
  "step": 75
607
+ },
608
+ {
609
+ "epoch": 0.19973718791064388,
610
+ "grad_norm": 3.0247833728790283,
611
+ "learning_rate": 1.6543469682057106e-05,
612
+ "loss": 6.9312,
613
+ "step": 76
614
+ },
615
+ {
616
+ "epoch": 0.202365308804205,
617
+ "grad_norm": 3.42531418800354,
618
+ "learning_rate": 1.526708147705013e-05,
619
+ "loss": 6.4775,
620
+ "step": 77
621
+ },
622
+ {
623
+ "epoch": 0.2049934296977661,
624
+ "grad_norm": 3.9694366455078125,
625
+ "learning_rate": 1.4033009983067452e-05,
626
+ "loss": 7.1735,
627
+ "step": 78
628
+ },
629
+ {
630
+ "epoch": 0.2076215505913272,
631
+ "grad_norm": 3.074192523956299,
632
+ "learning_rate": 1.2842758726130283e-05,
633
+ "loss": 7.3444,
634
+ "step": 79
635
+ },
636
+ {
637
+ "epoch": 0.2102496714848883,
638
+ "grad_norm": 3.740687847137451,
639
+ "learning_rate": 1.1697777844051105e-05,
640
+ "loss": 6.5621,
641
+ "step": 80
642
+ },
643
+ {
644
+ "epoch": 0.21287779237844942,
645
+ "grad_norm": 3.3163349628448486,
646
+ "learning_rate": 1.0599462319663905e-05,
647
+ "loss": 6.883,
648
+ "step": 81
649
+ },
650
+ {
651
+ "epoch": 0.21287779237844942,
652
+ "eval_loss": 6.806041240692139,
653
+ "eval_runtime": 7.8241,
654
+ "eval_samples_per_second": 41.027,
655
+ "eval_steps_per_second": 5.24,
656
+ "step": 81
657
+ },
658
+ {
659
+ "epoch": 0.21550591327201052,
660
+ "grad_norm": 3.510040283203125,
661
+ "learning_rate": 9.549150281252633e-06,
662
+ "loss": 6.4147,
663
+ "step": 82
664
+ },
665
+ {
666
+ "epoch": 0.21813403416557162,
667
+ "grad_norm": 3.3240206241607666,
668
+ "learning_rate": 8.548121372247918e-06,
669
+ "loss": 6.5435,
670
+ "step": 83
671
+ },
672
+ {
673
+ "epoch": 0.22076215505913271,
674
+ "grad_norm": 3.137699604034424,
675
+ "learning_rate": 7.597595192178702e-06,
676
+ "loss": 6.5122,
677
+ "step": 84
678
+ },
679
+ {
680
+ "epoch": 0.2233902759526938,
681
+ "grad_norm": 3.389455795288086,
682
+ "learning_rate": 6.698729810778065e-06,
683
+ "loss": 6.9796,
684
+ "step": 85
685
+ },
686
+ {
687
+ "epoch": 0.22601839684625494,
688
+ "grad_norm": 4.588552951812744,
689
+ "learning_rate": 5.852620357053651e-06,
690
+ "loss": 6.7471,
691
+ "step": 86
692
+ },
693
+ {
694
+ "epoch": 0.22864651773981604,
695
+ "grad_norm": 3.3164541721343994,
696
+ "learning_rate": 5.060297685041659e-06,
697
+ "loss": 7.0089,
698
+ "step": 87
699
+ },
700
+ {
701
+ "epoch": 0.23127463863337713,
702
+ "grad_norm": 4.035533905029297,
703
+ "learning_rate": 4.322727117869951e-06,
704
+ "loss": 6.8038,
705
+ "step": 88
706
+ },
707
+ {
708
+ "epoch": 0.23390275952693823,
709
+ "grad_norm": 3.418544292449951,
710
+ "learning_rate": 3.6408072716606346e-06,
711
+ "loss": 6.3053,
712
+ "step": 89
713
+ },
714
+ {
715
+ "epoch": 0.23653088042049936,
716
+ "grad_norm": 3.443645477294922,
717
+ "learning_rate": 3.0153689607045845e-06,
718
+ "loss": 7.12,
719
+ "step": 90
720
+ },
721
+ {
722
+ "epoch": 0.23653088042049936,
723
+ "eval_loss": 6.798569679260254,
724
+ "eval_runtime": 7.8396,
725
+ "eval_samples_per_second": 40.946,
726
+ "eval_steps_per_second": 5.23,
727
+ "step": 90
728
+ },
729
+ {
730
+ "epoch": 0.23915900131406045,
731
+ "grad_norm": 3.201587677001953,
732
+ "learning_rate": 2.4471741852423237e-06,
733
+ "loss": 6.7507,
734
+ "step": 91
735
+ },
736
+ {
737
+ "epoch": 0.24178712220762155,
738
+ "grad_norm": 3.0061752796173096,
739
+ "learning_rate": 1.9369152030840556e-06,
740
+ "loss": 6.8862,
741
+ "step": 92
742
+ },
743
+ {
744
+ "epoch": 0.24441524310118265,
745
+ "grad_norm": 2.538280963897705,
746
+ "learning_rate": 1.4852136862001764e-06,
747
+ "loss": 7.023,
748
+ "step": 93
749
+ },
750
+ {
751
+ "epoch": 0.24704336399474375,
752
+ "grad_norm": 3.575631856918335,
753
+ "learning_rate": 1.0926199633097157e-06,
754
+ "loss": 7.1501,
755
+ "step": 94
756
+ },
757
+ {
758
+ "epoch": 0.24967148488830487,
759
+ "grad_norm": 3.6927804946899414,
760
+ "learning_rate": 7.596123493895991e-07,
761
+ "loss": 6.4113,
762
+ "step": 95
763
+ },
764
+ {
765
+ "epoch": 0.25229960578186594,
766
+ "grad_norm": 3.6118414402008057,
767
+ "learning_rate": 4.865965629214819e-07,
768
+ "loss": 6.7738,
769
+ "step": 96
770
+ },
771
+ {
772
+ "epoch": 0.25492772667542707,
773
+ "grad_norm": 4.216277122497559,
774
+ "learning_rate": 2.7390523158633554e-07,
775
+ "loss": 6.6602,
776
+ "step": 97
777
+ },
778
+ {
779
+ "epoch": 0.2575558475689882,
780
+ "grad_norm": 3.5179567337036133,
781
+ "learning_rate": 1.2179748700879012e-07,
782
+ "loss": 6.7022,
783
+ "step": 98
784
+ },
785
+ {
786
+ "epoch": 0.26018396846254926,
787
+ "grad_norm": 4.385186195373535,
788
+ "learning_rate": 3.04586490452119e-08,
789
+ "loss": 6.6645,
790
+ "step": 99
791
+ },
792
+ {
793
+ "epoch": 0.26018396846254926,
794
+ "eval_loss": 6.796245098114014,
795
+ "eval_runtime": 7.8349,
796
+ "eval_samples_per_second": 40.97,
797
+ "eval_steps_per_second": 5.233,
798
+ "step": 99
799
+ },
800
+ {
801
+ "epoch": 0.2628120893561104,
802
+ "grad_norm": 3.6011836528778076,
803
+ "learning_rate": 0.0,
804
+ "loss": 6.8888,
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": 47104417333248.0,
826
  "train_batch_size": 8,
827
  "trial_name": null,
828
  "trial_params": null