TachyHealthResearch commited on
Commit
2cd6be7
·
1 Parent(s): 7d7b4b1

Training in progress, step 140, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71205dacc20f51f05a9bcfa2f1ab3ad7f1f0a30833e33969ab8c639a27d26769
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45db4bd8e0098b28fe5f735c570a1d39ac213e0f74fbc6509d63094930c7bf40
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc8dd3433a97375eb4aeddc3bfaae20ea72add67bf7c3ccae14919e2234955ee
3
  size 63350356
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60ea21b19a230b02fd81be2d931e7e96f6008106cbbb7b8bc858a11e30f7ea11
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:a0ea44b215605d2b833a5ba8cb7e5ee930255d3027cf7a1afb9eb3718de5d569
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5de00bd1c4d0561944b05f69e20b49da56db8e2875582d2cd83ae415d6a01f93
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08db62840dbcab25b1cc963eabefaf10f3c247ffc35b4858d5e35cab6ca752cd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:839736b31b97702e0c125f95929ada9032d07251504fab76843e29c8dc4d0fce
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": 0.054,
5
  "eval_steps": 1000,
6
- "global_step": 135,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -817,13 +817,43 @@
817
  "learning_rate": 2.0408163265306123e-05,
818
  "loss": 1.8015,
819
  "step": 135
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
820
  }
821
  ],
822
  "logging_steps": 1,
823
  "max_steps": 150,
824
  "num_train_epochs": 1,
825
  "save_steps": 5,
826
- "total_flos": 1.664593632436224e+16,
827
  "trial_name": null,
828
  "trial_params": null
829
  }
 
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,
 
817
  "learning_rate": 2.0408163265306123e-05,
818
  "loss": 1.8015,
819
  "step": 135
820
+ },
821
+ {
822
+ "epoch": 0.05,
823
+ "learning_rate": 1.9047619047619046e-05,
824
+ "loss": 1.6847,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 0.05,
829
+ "learning_rate": 1.7687074829931973e-05,
830
+ "loss": 1.6395,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 0.06,
835
+ "learning_rate": 1.6326530612244897e-05,
836
+ "loss": 1.3069,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 0.06,
841
+ "learning_rate": 1.4965986394557824e-05,
842
+ "loss": 1.7292,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 0.06,
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
  }