Hugging Face's logo

lesso05
/
1485ef98-e631-4c52-872b-6c2d449dfeaa

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
lesso05 commited on
Commit
e51fe49
·
verified ·
1 Parent(s): f8d86d3

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:f4b012c3392ca50cbde85a4b57cd230091947ff0c8d257d1a0f5d9796131ff05
3
  size 13587864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb07e5a1fa11422d8f88b8898e5a4e04828e18b29a89e582c266036aa7c7df60
3
  size 13587864
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0497e4eec48d4b1791d79fb8fcec7105c909c23d6936f8f359a319df8b35cccc
3
  size 27273018
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a98cb641d01c4635b475d3dc611e9b98a0e5ddcdaee205b5c7ef30073197043
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:ea3bdb271ebcebab2ce74db08d6e71f0c43ddaaf8cbf5667dcbcccbfbe9ab5c9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6494166deaeb52bf4807e3f66ec3fc16564cf84c62cbb099b461f476e1d8fd3
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:feed204db996a9f7ac3167cc4686c04dccd6605b9b2a7d539da6ff57c605983d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:beccfaf9bab963f178f24d893fd68585ea073339edab1cdcc5698c989a1dd81e
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": 0.390625,
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": 3.5721239031346067e-06,
605
  "loss": 2.6401,
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": 1534155326226432.0,
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": 0.5208333333333334,
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": 3.5721239031346067e-06,
605
  "loss": 2.6401,
606
  "step": 75
607
+ },
608
+ {
609
+ "epoch": 0.3958333333333333,
610
+ "grad_norm": 0.6095809936523438,
611
+ "learning_rate": 3.308693936411421e-06,
612
+ "loss": 2.7599,
613
+ "step": 76
614
+ },
615
+ {
616
+ "epoch": 0.4010416666666667,
617
+ "grad_norm": 0.5742631554603577,
618
+ "learning_rate": 3.0534162954100264e-06,
619
+ "loss": 2.6972,
620
+ "step": 77
621
+ },
622
+ {
623
+ "epoch": 0.40625,
624
+ "grad_norm": 0.5903258919715881,
625
+ "learning_rate": 2.8066019966134907e-06,
626
+ "loss": 2.6778,
627
+ "step": 78
628
+ },
629
+ {
630
+ "epoch": 0.4114583333333333,
631
+ "grad_norm": 0.603958010673523,
632
+ "learning_rate": 2.5685517452260566e-06,
633
+ "loss": 2.665,
634
+ "step": 79
635
+ },
636
+ {
637
+ "epoch": 0.4166666666666667,
638
+ "grad_norm": 0.613657534122467,
639
+ "learning_rate": 2.339555568810221e-06,
640
+ "loss": 2.7079,
641
+ "step": 80
642
+ },
643
+ {
644
+ "epoch": 0.421875,
645
+ "grad_norm": 0.6130823493003845,
646
+ "learning_rate": 2.119892463932781e-06,
647
+ "loss": 2.7365,
648
+ "step": 81
649
+ },
650
+ {
651
+ "epoch": 0.421875,
652
+ "eval_loss": 2.718648672103882,
653
+ "eval_runtime": 2.1208,
654
+ "eval_samples_per_second": 76.385,
655
+ "eval_steps_per_second": 9.902,
656
+ "step": 81
657
+ },
658
+ {
659
+ "epoch": 0.4270833333333333,
660
+ "grad_norm": 0.5892557501792908,
661
+ "learning_rate": 1.9098300562505266e-06,
662
+ "loss": 2.7435,
663
+ "step": 82
664
+ },
665
+ {
666
+ "epoch": 0.4322916666666667,
667
+ "grad_norm": 0.6382349133491516,
668
+ "learning_rate": 1.709624274449584e-06,
669
+ "loss": 2.7304,
670
+ "step": 83
671
+ },
672
+ {
673
+ "epoch": 0.4375,
674
+ "grad_norm": 0.6454895734786987,
675
+ "learning_rate": 1.5195190384357405e-06,
676
+ "loss": 2.7867,
677
+ "step": 84
678
+ },
679
+ {
680
+ "epoch": 0.4427083333333333,
681
+ "grad_norm": 0.5571866035461426,
682
+ "learning_rate": 1.339745962155613e-06,
683
+ "loss": 2.6963,
684
+ "step": 85
685
+ },
686
+ {
687
+ "epoch": 0.4479166666666667,
688
+ "grad_norm": 0.544607937335968,
689
+ "learning_rate": 1.1705240714107301e-06,
690
+ "loss": 2.6594,
691
+ "step": 86
692
+ },
693
+ {
694
+ "epoch": 0.453125,
695
+ "grad_norm": 0.5853146314620972,
696
+ "learning_rate": 1.012059537008332e-06,
697
+ "loss": 2.6857,
698
+ "step": 87
699
+ },
700
+ {
701
+ "epoch": 0.4583333333333333,
702
+ "grad_norm": 0.5569471716880798,
703
+ "learning_rate": 8.645454235739903e-07,
704
+ "loss": 2.6542,
705
+ "step": 88
706
+ },
707
+ {
708
+ "epoch": 0.4635416666666667,
709
+ "grad_norm": 0.5549748539924622,
710
+ "learning_rate": 7.281614543321269e-07,
711
+ "loss": 2.7433,
712
+ "step": 89
713
+ },
714
+ {
715
+ "epoch": 0.46875,
716
+ "grad_norm": 0.584230899810791,
717
+ "learning_rate": 6.030737921409169e-07,
718
+ "loss": 2.7141,
719
+ "step": 90
720
+ },
721
+ {
722
+ "epoch": 0.46875,
723
+ "eval_loss": 2.7120678424835205,
724
+ "eval_runtime": 2.1462,
725
+ "eval_samples_per_second": 75.483,
726
+ "eval_steps_per_second": 9.785,
727
+ "step": 90
728
+ },
729
+ {
730
+ "epoch": 0.4739583333333333,
731
+ "grad_norm": 0.5945222973823547,
732
+ "learning_rate": 4.894348370484648e-07,
733
+ "loss": 2.7239,
734
+ "step": 91
735
+ },
736
+ {
737
+ "epoch": 0.4791666666666667,
738
+ "grad_norm": 0.6125372052192688,
739
+ "learning_rate": 3.8738304061681107e-07,
740
+ "loss": 2.6631,
741
+ "step": 92
742
+ },
743
+ {
744
+ "epoch": 0.484375,
745
+ "grad_norm": 0.5539056658744812,
746
+ "learning_rate": 2.970427372400353e-07,
747
+ "loss": 2.6647,
748
+ "step": 93
749
+ },
750
+ {
751
+ "epoch": 0.4895833333333333,
752
+ "grad_norm": 0.5954320430755615,
753
+ "learning_rate": 2.1852399266194312e-07,
754
+ "loss": 2.7845,
755
+ "step": 94
756
+ },
757
+ {
758
+ "epoch": 0.4947916666666667,
759
+ "grad_norm": 0.5771157145500183,
760
+ "learning_rate": 1.519224698779198e-07,
761
+ "loss": 2.7396,
762
+ "step": 95
763
+ },
764
+ {
765
+ "epoch": 0.5,
766
+ "grad_norm": 0.5784287452697754,
767
+ "learning_rate": 9.731931258429638e-08,
768
+ "loss": 2.6544,
769
+ "step": 96
770
+ },
771
+ {
772
+ "epoch": 0.5052083333333334,
773
+ "grad_norm": 0.5514799952507019,
774
+ "learning_rate": 5.4781046317267103e-08,
775
+ "loss": 2.7321,
776
+ "step": 97
777
+ },
778
+ {
779
+ "epoch": 0.5104166666666666,
780
+ "grad_norm": 0.5833736658096313,
781
+ "learning_rate": 2.4359497401758026e-08,
782
+ "loss": 2.763,
783
+ "step": 98
784
+ },
785
+ {
786
+ "epoch": 0.515625,
787
+ "grad_norm": 0.5531443357467651,
788
+ "learning_rate": 6.091729809042379e-09,
789
+ "loss": 2.7092,
790
+ "step": 99
791
+ },
792
+ {
793
+ "epoch": 0.515625,
794
+ "eval_loss": 2.711505651473999,
795
+ "eval_runtime": 2.1245,
796
+ "eval_samples_per_second": 76.254,
797
+ "eval_steps_per_second": 9.885,
798
+ "step": 99
799
+ },
800
+ {
801
+ "epoch": 0.5208333333333334,
802
+ "grad_norm": 0.5679538249969482,
803
+ "learning_rate": 0.0,
804
+ "loss": 2.6643,
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": 2027028756824064.0,
826
  "train_batch_size": 8,
827
  "trial_name": null,
828
  "trial_params": null