lesso04 commited on
Commit
f6972b8
·
verified ·
1 Parent(s): 9ef759e

Training in progress, step 100, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f32b21467a29485c7b2128b4a71b1d47284c09cde5d76664b7ae4b6ee1daaaa4
3
  size 13587864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:392458195deaf29deac0e8f49a4c35e66d5e1917ced08b252272ec11110075ec
3
  size 13587864
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ceb14edd1c39d45d959f38ce4377987ac6cd4755d0603854e0ed8f9605f3711
3
  size 27273018
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91ce86cfcc4e5ba09b8d46ccd340487eb392860485e1857d663a610bf31c2610
3
  size 27273018
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:509f56cf0ca61682fbd67e154f38de895f0045bcf99ce0b8c283801f600a9995
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3fc4c3cde966a5ba6198ed3f341925d10d079007e1b3f4975cb373b1e4db6de
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": 0.004940711462450593,
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": 1.0939,
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": 1548039084834816.0,
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": 0.006587615283267457,
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": 1.0939,
606
  "step": 75
607
+ },
608
+ {
609
+ "epoch": 0.005006587615283268,
610
+ "grad_norm": 2.774831533432007,
611
+ "learning_rate": 1.6543469682057106e-05,
612
+ "loss": 0.7907,
613
+ "step": 76
614
+ },
615
+ {
616
+ "epoch": 0.005072463768115942,
617
+ "grad_norm": 1.4862602949142456,
618
+ "learning_rate": 1.526708147705013e-05,
619
+ "loss": 0.6863,
620
+ "step": 77
621
+ },
622
+ {
623
+ "epoch": 0.005138339920948616,
624
+ "grad_norm": 2.5560407638549805,
625
+ "learning_rate": 1.4033009983067452e-05,
626
+ "loss": 0.7421,
627
+ "step": 78
628
+ },
629
+ {
630
+ "epoch": 0.005204216073781291,
631
+ "grad_norm": 3.1836204528808594,
632
+ "learning_rate": 1.2842758726130283e-05,
633
+ "loss": 0.7768,
634
+ "step": 79
635
+ },
636
+ {
637
+ "epoch": 0.005270092226613966,
638
+ "grad_norm": 1.9725606441497803,
639
+ "learning_rate": 1.1697777844051105e-05,
640
+ "loss": 0.7135,
641
+ "step": 80
642
+ },
643
+ {
644
+ "epoch": 0.005335968379446641,
645
+ "grad_norm": 1.8420541286468506,
646
+ "learning_rate": 1.0599462319663905e-05,
647
+ "loss": 0.7451,
648
+ "step": 81
649
+ },
650
+ {
651
+ "epoch": 0.005335968379446641,
652
+ "eval_loss": 0.7732530832290649,
653
+ "eval_runtime": 184.4371,
654
+ "eval_samples_per_second": 69.314,
655
+ "eval_steps_per_second": 8.664,
656
+ "step": 81
657
+ },
658
+ {
659
+ "epoch": 0.005401844532279315,
660
+ "grad_norm": 1.9438694715499878,
661
+ "learning_rate": 9.549150281252633e-06,
662
+ "loss": 0.7781,
663
+ "step": 82
664
+ },
665
+ {
666
+ "epoch": 0.005467720685111989,
667
+ "grad_norm": 1.7922385931015015,
668
+ "learning_rate": 8.548121372247918e-06,
669
+ "loss": 0.6667,
670
+ "step": 83
671
+ },
672
+ {
673
+ "epoch": 0.005533596837944664,
674
+ "grad_norm": 1.500645637512207,
675
+ "learning_rate": 7.597595192178702e-06,
676
+ "loss": 0.6971,
677
+ "step": 84
678
+ },
679
+ {
680
+ "epoch": 0.005599472990777339,
681
+ "grad_norm": 3.3169381618499756,
682
+ "learning_rate": 6.698729810778065e-06,
683
+ "loss": 0.7024,
684
+ "step": 85
685
+ },
686
+ {
687
+ "epoch": 0.005665349143610013,
688
+ "grad_norm": 2.3479697704315186,
689
+ "learning_rate": 5.852620357053651e-06,
690
+ "loss": 0.6829,
691
+ "step": 86
692
+ },
693
+ {
694
+ "epoch": 0.005731225296442688,
695
+ "grad_norm": 1.7033846378326416,
696
+ "learning_rate": 5.060297685041659e-06,
697
+ "loss": 0.6208,
698
+ "step": 87
699
+ },
700
+ {
701
+ "epoch": 0.005797101449275362,
702
+ "grad_norm": 2.391817569732666,
703
+ "learning_rate": 4.322727117869951e-06,
704
+ "loss": 0.7019,
705
+ "step": 88
706
+ },
707
+ {
708
+ "epoch": 0.005862977602108037,
709
+ "grad_norm": 2.0309882164001465,
710
+ "learning_rate": 3.6408072716606346e-06,
711
+ "loss": 0.7454,
712
+ "step": 89
713
+ },
714
+ {
715
+ "epoch": 0.005928853754940711,
716
+ "grad_norm": 2.8557684421539307,
717
+ "learning_rate": 3.0153689607045845e-06,
718
+ "loss": 0.763,
719
+ "step": 90
720
+ },
721
+ {
722
+ "epoch": 0.005928853754940711,
723
+ "eval_loss": 0.748928427696228,
724
+ "eval_runtime": 184.3653,
725
+ "eval_samples_per_second": 69.341,
726
+ "eval_steps_per_second": 8.668,
727
+ "step": 90
728
+ },
729
+ {
730
+ "epoch": 0.005994729907773386,
731
+ "grad_norm": 1.738196611404419,
732
+ "learning_rate": 2.4471741852423237e-06,
733
+ "loss": 0.6203,
734
+ "step": 91
735
+ },
736
+ {
737
+ "epoch": 0.006060606060606061,
738
+ "grad_norm": 3.5670719146728516,
739
+ "learning_rate": 1.9369152030840556e-06,
740
+ "loss": 0.8929,
741
+ "step": 92
742
+ },
743
+ {
744
+ "epoch": 0.006126482213438735,
745
+ "grad_norm": 2.1231579780578613,
746
+ "learning_rate": 1.4852136862001764e-06,
747
+ "loss": 0.6805,
748
+ "step": 93
749
+ },
750
+ {
751
+ "epoch": 0.00619235836627141,
752
+ "grad_norm": 1.6460092067718506,
753
+ "learning_rate": 1.0926199633097157e-06,
754
+ "loss": 0.7208,
755
+ "step": 94
756
+ },
757
+ {
758
+ "epoch": 0.006258234519104084,
759
+ "grad_norm": 3.6686792373657227,
760
+ "learning_rate": 7.596123493895991e-07,
761
+ "loss": 0.7887,
762
+ "step": 95
763
+ },
764
+ {
765
+ "epoch": 0.006324110671936759,
766
+ "grad_norm": 2.6409358978271484,
767
+ "learning_rate": 4.865965629214819e-07,
768
+ "loss": 0.7277,
769
+ "step": 96
770
+ },
771
+ {
772
+ "epoch": 0.006389986824769434,
773
+ "grad_norm": 1.6902509927749634,
774
+ "learning_rate": 2.7390523158633554e-07,
775
+ "loss": 0.5849,
776
+ "step": 97
777
+ },
778
+ {
779
+ "epoch": 0.006455862977602108,
780
+ "grad_norm": 1.3296384811401367,
781
+ "learning_rate": 1.2179748700879012e-07,
782
+ "loss": 0.5937,
783
+ "step": 98
784
+ },
785
+ {
786
+ "epoch": 0.006521739130434782,
787
+ "grad_norm": 3.772615671157837,
788
+ "learning_rate": 3.04586490452119e-08,
789
+ "loss": 0.8282,
790
+ "step": 99
791
+ },
792
+ {
793
+ "epoch": 0.006521739130434782,
794
+ "eval_loss": 0.7452791929244995,
795
+ "eval_runtime": 184.1886,
796
+ "eval_samples_per_second": 69.407,
797
+ "eval_steps_per_second": 8.676,
798
+ "step": 99
799
+ },
800
+ {
801
+ "epoch": 0.006587615283267457,
802
+ "grad_norm": 1.7011206150054932,
803
+ "learning_rate": 0.0,
804
+ "loss": 0.6518,
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": 2047854394736640.0,
826
  "train_batch_size": 8,
827
  "trial_name": null,
828
  "trial_params": null