diagonalge commited on
Commit
1e506e5
1 Parent(s): 8d00fa8

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 sha256:3bcb30213c268b08c544b2c7db8161f621672109ce6ac437fbf66b545997526d
3
  size 101752088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:700019b4cc90c4ccfef934b93e7efafea436715bfa2b61c858bf365343c1ba32
3
  size 101752088
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0645116a7c0984cadcde7eccc2e07e2cf29f24691185e9c2bb5c66a51d9adad
3
  size 52046596
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0f3c0fa37a780786a00d26a44a81dd51da3cfd5944375cd956a61dc2b87e71e
3
  size 52046596
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0580e74248926dc2cb618fc9ab207371e56a1f66f91fbcaaa73e7d0342f25366
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83927fe0efc06382dff96f72c027c114b9cfb264f5d9c65a1275f1784c3318fa
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb97b24f34ff3e53eec5be9cf35c1a7161c58dbc2fed7dda160fb3eb64e5f353
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
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": 0.011328592107747499,
5
  "eval_steps": 25,
6
- "global_step": 90,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -669,6 +669,84 @@
669
  "learning_rate": 6.030737921409169e-06,
670
  "loss": 0.0975,
671
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
672
  }
673
  ],
674
  "logging_steps": 1,
@@ -683,12 +761,12 @@
683
  "should_evaluate": false,
684
  "should_log": false,
685
  "should_save": true,
686
- "should_training_stop": false
687
  },
688
  "attributes": {}
689
  }
690
  },
691
- "total_flos": 5.92684561465344e+16,
692
  "train_batch_size": 2,
693
  "trial_name": null,
694
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.012587324564163886,
5
  "eval_steps": 25,
6
+ "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
669
  "learning_rate": 6.030737921409169e-06,
670
  "loss": 0.0975,
671
  "step": 90
672
+ },
673
+ {
674
+ "epoch": 0.011454465353389138,
675
+ "grad_norm": 0.0066988165490329266,
676
+ "learning_rate": 4.8943483704846475e-06,
677
+ "loss": 0.0004,
678
+ "step": 91
679
+ },
680
+ {
681
+ "epoch": 0.011580338599030775,
682
+ "grad_norm": 0.0022131705190986395,
683
+ "learning_rate": 3.873830406168111e-06,
684
+ "loss": 0.0004,
685
+ "step": 92
686
+ },
687
+ {
688
+ "epoch": 0.011706211844672415,
689
+ "grad_norm": 0.01956171914935112,
690
+ "learning_rate": 2.970427372400353e-06,
691
+ "loss": 0.0015,
692
+ "step": 93
693
+ },
694
+ {
695
+ "epoch": 0.011832085090314054,
696
+ "grad_norm": 0.0475313700735569,
697
+ "learning_rate": 2.1852399266194314e-06,
698
+ "loss": 0.0016,
699
+ "step": 94
700
+ },
701
+ {
702
+ "epoch": 0.011957958335955693,
703
+ "grad_norm": 3.4122633934020996,
704
+ "learning_rate": 1.5192246987791981e-06,
705
+ "loss": 0.7071,
706
+ "step": 95
707
+ },
708
+ {
709
+ "epoch": 0.01208383158159733,
710
+ "grad_norm": 0.13446319103240967,
711
+ "learning_rate": 9.731931258429638e-07,
712
+ "loss": 0.0256,
713
+ "step": 96
714
+ },
715
+ {
716
+ "epoch": 0.01220970482723897,
717
+ "grad_norm": 0.10620174556970596,
718
+ "learning_rate": 5.478104631726711e-07,
719
+ "loss": 0.0039,
720
+ "step": 97
721
+ },
722
+ {
723
+ "epoch": 0.01233557807288061,
724
+ "grad_norm": 0.5097644329071045,
725
+ "learning_rate": 2.4359497401758024e-07,
726
+ "loss": 0.0671,
727
+ "step": 98
728
+ },
729
+ {
730
+ "epoch": 0.012461451318522249,
731
+ "grad_norm": 1.6247103214263916,
732
+ "learning_rate": 6.09172980904238e-08,
733
+ "loss": 0.0878,
734
+ "step": 99
735
+ },
736
+ {
737
+ "epoch": 0.012587324564163886,
738
+ "grad_norm": 0.002280471846461296,
739
+ "learning_rate": 0.0,
740
+ "loss": 0.0001,
741
+ "step": 100
742
+ },
743
+ {
744
+ "epoch": 0.012587324564163886,
745
+ "eval_loss": NaN,
746
+ "eval_runtime": 3565.9397,
747
+ "eval_samples_per_second": 0.938,
748
+ "eval_steps_per_second": 0.469,
749
+ "step": 100
750
  }
751
  ],
752
  "logging_steps": 1,
 
761
  "should_evaluate": false,
762
  "should_log": false,
763
  "should_save": true,
764
+ "should_training_stop": true
765
  },
766
  "attributes": {}
767
  }
768
  },
769
+ "total_flos": 6.5853840162816e+16,
770
  "train_batch_size": 2,
771
  "trial_name": null,
772
  "trial_params": null