Hugging Face's logo

lesso03
/
98d3d7f5-bec2-44e1-a24b-ce2333b65fa4

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
lesso03 commited on
Commit
82be42a
•
1 Parent(s): 914a2cd

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:a62c13a0f6c226f7d9b1d312ab87fa57cf33f48a9fd39eb23d23e3a59a6f32d8
3
  size 45118424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dd6d4990333a61755bef082a3fbf9bd19fb2522b3b89b5ed84cb21ae2a3d1b2
3
  size 45118424
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99124b306918032c2cc01eb2d00ec5d79ea0f03308292f97feeb46811d489dae
3
  size 90365754
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16dfb78ed91d1de49e2f7272ac1bcad85c1903e81059ee8269d2a4181537c77e
3
  size 90365754
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4a797e4556a00e672702ff04c6ecce740fabaca58e7ff5b6ddf14351f843364
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c659e4505005131eab7ea0ee74ff9e2fee448c1f7e5a9dc766af93a6f64c72a6
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": 0.0017014519056261343,
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": 1.9046,
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": 7257919271731200.0,
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": 0.002268602540834846,
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": 1.9046,
606
  "step": 75
607
+ },
608
+ {
609
+ "epoch": 0.0017241379310344827,
610
+ "grad_norm": 2.6128618717193604,
611
+ "learning_rate": 1.6543469682057106e-05,
612
+ "loss": 1.8579,
613
+ "step": 76
614
+ },
615
+ {
616
+ "epoch": 0.0017468239564428312,
617
+ "grad_norm": 2.6873018741607666,
618
+ "learning_rate": 1.526708147705013e-05,
619
+ "loss": 1.8461,
620
+ "step": 77
621
+ },
622
+ {
623
+ "epoch": 0.0017695099818511796,
624
+ "grad_norm": 1.5386942625045776,
625
+ "learning_rate": 1.4033009983067452e-05,
626
+ "loss": 1.8917,
627
+ "step": 78
628
+ },
629
+ {
630
+ "epoch": 0.001792196007259528,
631
+ "grad_norm": 2.0306711196899414,
632
+ "learning_rate": 1.2842758726130283e-05,
633
+ "loss": 1.883,
634
+ "step": 79
635
+ },
636
+ {
637
+ "epoch": 0.0018148820326678765,
638
+ "grad_norm": 1.8291230201721191,
639
+ "learning_rate": 1.1697777844051105e-05,
640
+ "loss": 1.8556,
641
+ "step": 80
642
+ },
643
+ {
644
+ "epoch": 0.001837568058076225,
645
+ "grad_norm": 3.1512269973754883,
646
+ "learning_rate": 1.0599462319663905e-05,
647
+ "loss": 1.9065,
648
+ "step": 81
649
+ },
650
+ {
651
+ "epoch": 0.001837568058076225,
652
+ "eval_loss": 1.8945270776748657,
653
+ "eval_runtime": 1114.5926,
654
+ "eval_samples_per_second": 33.304,
655
+ "eval_steps_per_second": 4.163,
656
+ "step": 81
657
+ },
658
+ {
659
+ "epoch": 0.0018602540834845734,
660
+ "grad_norm": 3.1626930236816406,
661
+ "learning_rate": 9.549150281252633e-06,
662
+ "loss": 1.8543,
663
+ "step": 82
664
+ },
665
+ {
666
+ "epoch": 0.0018829401088929219,
667
+ "grad_norm": 2.0213286876678467,
668
+ "learning_rate": 8.548121372247918e-06,
669
+ "loss": 1.9083,
670
+ "step": 83
671
+ },
672
+ {
673
+ "epoch": 0.0019056261343012705,
674
+ "grad_norm": 2.028878927230835,
675
+ "learning_rate": 7.597595192178702e-06,
676
+ "loss": 1.9163,
677
+ "step": 84
678
+ },
679
+ {
680
+ "epoch": 0.001928312159709619,
681
+ "grad_norm": 1.7468281984329224,
682
+ "learning_rate": 6.698729810778065e-06,
683
+ "loss": 1.8624,
684
+ "step": 85
685
+ },
686
+ {
687
+ "epoch": 0.0019509981851179674,
688
+ "grad_norm": 1.4500890970230103,
689
+ "learning_rate": 5.852620357053651e-06,
690
+ "loss": 1.8496,
691
+ "step": 86
692
+ },
693
+ {
694
+ "epoch": 0.001973684210526316,
695
+ "grad_norm": 1.5511759519577026,
696
+ "learning_rate": 5.060297685041659e-06,
697
+ "loss": 1.8577,
698
+ "step": 87
699
+ },
700
+ {
701
+ "epoch": 0.001996370235934664,
702
+ "grad_norm": 1.5159685611724854,
703
+ "learning_rate": 4.322727117869951e-06,
704
+ "loss": 1.8675,
705
+ "step": 88
706
+ },
707
+ {
708
+ "epoch": 0.0020190562613430127,
709
+ "grad_norm": 1.6526339054107666,
710
+ "learning_rate": 3.6408072716606346e-06,
711
+ "loss": 1.8536,
712
+ "step": 89
713
+ },
714
+ {
715
+ "epoch": 0.002041742286751361,
716
+ "grad_norm": 1.9124068021774292,
717
+ "learning_rate": 3.0153689607045845e-06,
718
+ "loss": 1.8886,
719
+ "step": 90
720
+ },
721
+ {
722
+ "epoch": 0.002041742286751361,
723
+ "eval_loss": 1.878859281539917,
724
+ "eval_runtime": 1114.48,
725
+ "eval_samples_per_second": 33.307,
726
+ "eval_steps_per_second": 4.163,
727
+ "step": 90
728
+ },
729
+ {
730
+ "epoch": 0.0020644283121597096,
731
+ "grad_norm": 1.4601389169692993,
732
+ "learning_rate": 2.4471741852423237e-06,
733
+ "loss": 1.8853,
734
+ "step": 91
735
+ },
736
+ {
737
+ "epoch": 0.002087114337568058,
738
+ "grad_norm": 1.3825609683990479,
739
+ "learning_rate": 1.9369152030840556e-06,
740
+ "loss": 1.9545,
741
+ "step": 92
742
+ },
743
+ {
744
+ "epoch": 0.0021098003629764065,
745
+ "grad_norm": 1.46387779712677,
746
+ "learning_rate": 1.4852136862001764e-06,
747
+ "loss": 1.9272,
748
+ "step": 93
749
+ },
750
+ {
751
+ "epoch": 0.002132486388384755,
752
+ "grad_norm": 1.3379498720169067,
753
+ "learning_rate": 1.0926199633097157e-06,
754
+ "loss": 1.8666,
755
+ "step": 94
756
+ },
757
+ {
758
+ "epoch": 0.0021551724137931034,
759
+ "grad_norm": 1.5861835479736328,
760
+ "learning_rate": 7.596123493895991e-07,
761
+ "loss": 1.8307,
762
+ "step": 95
763
+ },
764
+ {
765
+ "epoch": 0.002177858439201452,
766
+ "grad_norm": 1.2894798517227173,
767
+ "learning_rate": 4.865965629214819e-07,
768
+ "loss": 1.8439,
769
+ "step": 96
770
+ },
771
+ {
772
+ "epoch": 0.0022005444646098003,
773
+ "grad_norm": 1.3515748977661133,
774
+ "learning_rate": 2.7390523158633554e-07,
775
+ "loss": 1.852,
776
+ "step": 97
777
+ },
778
+ {
779
+ "epoch": 0.002223230490018149,
780
+ "grad_norm": 1.476943016052246,
781
+ "learning_rate": 1.2179748700879012e-07,
782
+ "loss": 1.9408,
783
+ "step": 98
784
+ },
785
+ {
786
+ "epoch": 0.002245916515426497,
787
+ "grad_norm": 1.5151393413543701,
788
+ "learning_rate": 3.04586490452119e-08,
789
+ "loss": 1.8778,
790
+ "step": 99
791
+ },
792
+ {
793
+ "epoch": 0.002245916515426497,
794
+ "eval_loss": 1.8763697147369385,
795
+ "eval_runtime": 1114.5225,
796
+ "eval_samples_per_second": 33.306,
797
+ "eval_steps_per_second": 4.163,
798
+ "step": 99
799
+ },
800
+ {
801
+ "epoch": 0.002268602540834846,
802
+ "grad_norm": 1.3483997583389282,
803
+ "learning_rate": 0.0,
804
+ "loss": 1.8508,
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": 9677225695641600.0,
826
  "train_batch_size": 8,
827
  "trial_name": null,
828
  "trial_params": null