TachyHealthResearch commited on
Commit
d8f597c
1 Parent(s): c9d427f

Training in progress, step 150, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5700e75aedd836722315a2c637c8f75ca8370d0dfa88cc4580ff8fe5a9f37fa5
3
  size 75012288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f49598723d8c65b7f6b5645c5a07f36db4679055c387465cb717c054f54d515e
3
  size 75012288
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:613aa481d37097de3af43e8bfa4a424fc42d0e26cc1f8774020cfe2b5bf15281
3
  size 38034724
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85bac65930f267247f044f6c70a029246ba89f8f917fe1796bf0c7621d66d613
3
  size 38034724
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54d19fc9cad9609a6172c82e6d0d91c418c97728872a9b499c73ea8cd6f52e82
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b8fb474d85aef0f57c5c82e36b87ff9ecbc12ff5a856d932e9b2940d26914d2
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:839736b31b97702e0c125f95929ada9032d07251504fab76843e29c8dc4d0fce
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:194456d3c9e165255d5406a0f3f62973b0bede79d91784f72431350783e27ae7
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": 0.056,
5
  "eval_steps": 1000,
6
- "global_step": 140,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -847,13 +847,73 @@
847
  "learning_rate": 1.360544217687075e-05,
848
  "loss": 1.9262,
849
  "step": 140
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
850
  }
851
  ],
852
  "logging_steps": 1,
853
  "max_steps": 150,
854
  "num_train_epochs": 1,
855
  "save_steps": 5,
856
- "total_flos": 7515861863497728.0,
857
  "trial_name": null,
858
  "trial_params": null
859
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.06,
5
  "eval_steps": 1000,
6
+ "global_step": 150,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
847
  "learning_rate": 1.360544217687075e-05,
848
  "loss": 1.9262,
849
  "step": 140
850
+ },
851
+ {
852
+ "epoch": 0.06,
853
+ "learning_rate": 1.2244897959183674e-05,
854
+ "loss": 1.8739,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 0.06,
859
+ "learning_rate": 1.08843537414966e-05,
860
+ "loss": 1.8307,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 0.06,
865
+ "learning_rate": 9.523809523809523e-06,
866
+ "loss": 1.8247,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 0.06,
871
+ "learning_rate": 8.163265306122448e-06,
872
+ "loss": 1.8952,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 0.06,
877
+ "learning_rate": 6.802721088435375e-06,
878
+ "loss": 1.8041,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 0.06,
883
+ "learning_rate": 5.4421768707483e-06,
884
+ "loss": 1.8557,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 0.06,
889
+ "learning_rate": 4.081632653061224e-06,
890
+ "loss": 1.9398,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 0.06,
895
+ "learning_rate": 2.72108843537415e-06,
896
+ "loss": 1.944,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 0.06,
901
+ "learning_rate": 1.360544217687075e-06,
902
+ "loss": 2.0813,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 0.06,
907
+ "learning_rate": 0.0,
908
+ "loss": 1.8519,
909
+ "step": 150
910
  }
911
  ],
912
  "logging_steps": 1,
913
  "max_steps": 150,
914
  "num_train_epochs": 1,
915
  "save_steps": 5,
916
+ "total_flos": 8125557976793088.0,
917
  "trial_name": null,
918
  "trial_params": null
919
  }