Hugging Face's logo

lesso01
/
b890da7f-865b-4f11-80c0-9395d138e88e

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
lesso01 commited on
Commit
99e9e7c
·
verified ·
1 Parent(s): 431720e

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 sha256:1fcfc3ee95215c0c20d581f3f1423d9ecaa76f00b70e323ee8e10885047a79b8
3
  size 13587864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81fd5c587260b492013b40be2b69d4e1435035df2689d019a639577bec862be3
3
  size 13587864
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f015b0dd6ff9416a388857a4fb06c33f225dbedd7fd8ec088e600654f70a063
3
  size 27273018
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7358b0a609ae9d602955f2590eeb3b1b0fc4e954b8adfa05a1e1b6fb9eddf45a
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:adf907df125d736a55f06d03d9cdedce0bb4c3f9baece6cc712d35b7fc7e8fd7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92ab9f9317ccfa383747f4568e471a4cf9036ffdca498f6d204c3baa9fb9f46b
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": 0.11177347242921014,
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": 0.2092,
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": 1041281895628800.0,
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": 0.14903129657228018,
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": 0.2092,
606
  "step": 75
607
+ },
608
+ {
609
+ "epoch": 0.11326378539493294,
610
+ "grad_norm": 0.7134643197059631,
611
+ "learning_rate": 1.6543469682057106e-05,
612
+ "loss": 0.2253,
613
+ "step": 76
614
+ },
615
+ {
616
+ "epoch": 0.11475409836065574,
617
+ "grad_norm": 1.2007724046707153,
618
+ "learning_rate": 1.526708147705013e-05,
619
+ "loss": 0.2773,
620
+ "step": 77
621
+ },
622
+ {
623
+ "epoch": 0.11624441132637854,
624
+ "grad_norm": 0.9633266925811768,
625
+ "learning_rate": 1.4033009983067452e-05,
626
+ "loss": 0.3331,
627
+ "step": 78
628
+ },
629
+ {
630
+ "epoch": 0.11773472429210134,
631
+ "grad_norm": 1.1672801971435547,
632
+ "learning_rate": 1.2842758726130283e-05,
633
+ "loss": 0.3208,
634
+ "step": 79
635
+ },
636
+ {
637
+ "epoch": 0.11922503725782414,
638
+ "grad_norm": 0.9459627270698547,
639
+ "learning_rate": 1.1697777844051105e-05,
640
+ "loss": 0.2231,
641
+ "step": 80
642
+ },
643
+ {
644
+ "epoch": 0.12071535022354694,
645
+ "grad_norm": 1.0871282815933228,
646
+ "learning_rate": 1.0599462319663905e-05,
647
+ "loss": 0.366,
648
+ "step": 81
649
+ },
650
+ {
651
+ "epoch": 0.12071535022354694,
652
+ "eval_loss": 0.2640610635280609,
653
+ "eval_runtime": 2.7126,
654
+ "eval_samples_per_second": 208.285,
655
+ "eval_steps_per_second": 26.174,
656
+ "step": 81
657
+ },
658
+ {
659
+ "epoch": 0.12220566318926974,
660
+ "grad_norm": 0.8887442350387573,
661
+ "learning_rate": 9.549150281252633e-06,
662
+ "loss": 0.172,
663
+ "step": 82
664
+ },
665
+ {
666
+ "epoch": 0.12369597615499255,
667
+ "grad_norm": 0.8635609149932861,
668
+ "learning_rate": 8.548121372247918e-06,
669
+ "loss": 0.2841,
670
+ "step": 83
671
+ },
672
+ {
673
+ "epoch": 0.12518628912071536,
674
+ "grad_norm": 0.701813817024231,
675
+ "learning_rate": 7.597595192178702e-06,
676
+ "loss": 0.159,
677
+ "step": 84
678
+ },
679
+ {
680
+ "epoch": 0.12667660208643816,
681
+ "grad_norm": 1.2554618120193481,
682
+ "learning_rate": 6.698729810778065e-06,
683
+ "loss": 0.3869,
684
+ "step": 85
685
+ },
686
+ {
687
+ "epoch": 0.12816691505216096,
688
+ "grad_norm": 0.7576965689659119,
689
+ "learning_rate": 5.852620357053651e-06,
690
+ "loss": 0.2828,
691
+ "step": 86
692
+ },
693
+ {
694
+ "epoch": 0.12965722801788376,
695
+ "grad_norm": 0.8593026995658875,
696
+ "learning_rate": 5.060297685041659e-06,
697
+ "loss": 0.1677,
698
+ "step": 87
699
+ },
700
+ {
701
+ "epoch": 0.13114754098360656,
702
+ "grad_norm": 0.8234618902206421,
703
+ "learning_rate": 4.322727117869951e-06,
704
+ "loss": 0.2902,
705
+ "step": 88
706
+ },
707
+ {
708
+ "epoch": 0.13263785394932937,
709
+ "grad_norm": 1.0881298780441284,
710
+ "learning_rate": 3.6408072716606346e-06,
711
+ "loss": 0.2905,
712
+ "step": 89
713
+ },
714
+ {
715
+ "epoch": 0.13412816691505217,
716
+ "grad_norm": 0.7025581002235413,
717
+ "learning_rate": 3.0153689607045845e-06,
718
+ "loss": 0.2656,
719
+ "step": 90
720
+ },
721
+ {
722
+ "epoch": 0.13412816691505217,
723
+ "eval_loss": 0.25454258918762207,
724
+ "eval_runtime": 2.7005,
725
+ "eval_samples_per_second": 209.222,
726
+ "eval_steps_per_second": 26.292,
727
+ "step": 90
728
+ },
729
+ {
730
+ "epoch": 0.13561847988077497,
731
+ "grad_norm": 0.595646321773529,
732
+ "learning_rate": 2.4471741852423237e-06,
733
+ "loss": 0.1637,
734
+ "step": 91
735
+ },
736
+ {
737
+ "epoch": 0.13710879284649777,
738
+ "grad_norm": 0.8875901699066162,
739
+ "learning_rate": 1.9369152030840556e-06,
740
+ "loss": 0.1471,
741
+ "step": 92
742
+ },
743
+ {
744
+ "epoch": 0.13859910581222057,
745
+ "grad_norm": 0.6628938317298889,
746
+ "learning_rate": 1.4852136862001764e-06,
747
+ "loss": 0.2461,
748
+ "step": 93
749
+ },
750
+ {
751
+ "epoch": 0.14008941877794337,
752
+ "grad_norm": 1.1476900577545166,
753
+ "learning_rate": 1.0926199633097157e-06,
754
+ "loss": 0.2747,
755
+ "step": 94
756
+ },
757
+ {
758
+ "epoch": 0.14157973174366617,
759
+ "grad_norm": 0.841936469078064,
760
+ "learning_rate": 7.596123493895991e-07,
761
+ "loss": 0.1956,
762
+ "step": 95
763
+ },
764
+ {
765
+ "epoch": 0.14307004470938897,
766
+ "grad_norm": 0.7711091637611389,
767
+ "learning_rate": 4.865965629214819e-07,
768
+ "loss": 0.1328,
769
+ "step": 96
770
+ },
771
+ {
772
+ "epoch": 0.14456035767511177,
773
+ "grad_norm": 1.0483628511428833,
774
+ "learning_rate": 2.7390523158633554e-07,
775
+ "loss": 0.2153,
776
+ "step": 97
777
+ },
778
+ {
779
+ "epoch": 0.14605067064083457,
780
+ "grad_norm": 0.7784842848777771,
781
+ "learning_rate": 1.2179748700879012e-07,
782
+ "loss": 0.1979,
783
+ "step": 98
784
+ },
785
+ {
786
+ "epoch": 0.14754098360655737,
787
+ "grad_norm": 0.7276144027709961,
788
+ "learning_rate": 3.04586490452119e-08,
789
+ "loss": 0.2163,
790
+ "step": 99
791
+ },
792
+ {
793
+ "epoch": 0.14754098360655737,
794
+ "eval_loss": 0.25341349840164185,
795
+ "eval_runtime": 2.6609,
796
+ "eval_samples_per_second": 212.333,
797
+ "eval_steps_per_second": 26.683,
798
+ "step": 99
799
+ },
800
+ {
801
+ "epoch": 0.14903129657228018,
802
+ "grad_norm": 1.0174576044082642,
803
+ "learning_rate": 0.0,
804
+ "loss": 0.2102,
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": 1388375860838400.0,
826
  "train_batch_size": 8,
827
  "trial_name": null,
828
  "trial_params": null