TachyHealthResearch commited on
Commit
3af32ab
·
1 Parent(s): 30f4d16

Training in progress, step 145, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45db4bd8e0098b28fe5f735c570a1d39ac213e0f74fbc6509d63094930c7bf40
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5105f0e2d31ebdd39420d145251c2aac83c8d585c1fc7d2c6f12b98cec8ecf2b
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60ea21b19a230b02fd81be2d931e7e96f6008106cbbb7b8bc858a11e30f7ea11
3
  size 63350356
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45fa14015d0c0559ef77773e6f538c05121db85c8048f6beff290b14baf78dc4
3
  size 63350356
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5de00bd1c4d0561944b05f69e20b49da56db8e2875582d2cd83ae415d6a01f93
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:937020f142f7106dd817cacf2dce5e6262ad06af2d2984ed591bd1b088ef841a
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 sha256:712f64b7d1dadc02aa6d708eedb0cb77553e96b6e7ae1d1f2369054965a7fb02
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 +847,43 @@
847
  "learning_rate": 1.360544217687075e-05,
848
  "loss": 1.5996,
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": 1.721331831496704e+16,
857
  "trial_name": null,
858
  "trial_params": null
859
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.058,
5
  "eval_steps": 1000,
6
+ "global_step": 145,
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": 1.5996,
849
  "step": 140
850
+ },
851
+ {
852
+ "epoch": 0.06,
853
+ "learning_rate": 1.2244897959183674e-05,
854
+ "loss": 1.5048,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 0.06,
859
+ "learning_rate": 1.08843537414966e-05,
860
+ "loss": 1.5075,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 0.06,
865
+ "learning_rate": 9.523809523809523e-06,
866
+ "loss": 1.4126,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 0.06,
871
+ "learning_rate": 8.163265306122448e-06,
872
+ "loss": 1.4858,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 0.06,
877
+ "learning_rate": 6.802721088435375e-06,
878
+ "loss": 1.4445,
879
+ "step": 145
880
  }
881
  ],
882
  "logging_steps": 1,
883
  "max_steps": 150,
884
  "num_train_epochs": 1,
885
  "save_steps": 5,
886
+ "total_flos": 1.793684630298624e+16,
887
  "trial_name": null,
888
  "trial_params": null
889
  }