Hugging Face's logo

Graphcore
/
deberta-base-squad

Question Answering
Transformers
PyTorch
TensorBoard
Graphcore
deberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
jimypbr commited on
Commit
176c514
•
1 Parent(s): f5c13fb

End of training

Browse files
Files changed (4) hide show
  1. all_results.json +3 -3
  2. pytorch_model.bin +1 -1
  3. train_results.json +3 -3
  4. trainer_state.json +3 -3
all_results.json CHANGED
@@ -4,8 +4,8 @@
4
  "eval_f1": 92.97352589089498,
5
  "eval_samples": 10788,
6
  "train_loss": 1.088201597354519,
7
- "train_runtime": 783.526,
8
  "train_samples": 88550,
9
- "train_samples_per_second": 226.03,
10
- "train_steps_per_second": 1.764
11
  }
 
4
  "eval_f1": 92.97352589089498,
5
  "eval_samples": 10788,
6
  "train_loss": 1.088201597354519,
7
+ "train_runtime": 749.7015,
8
  "train_samples": 88550,
9
+ "train_samples_per_second": 236.227,
10
+ "train_steps_per_second": 1.843
11
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26181949daf0a3b96f33978b8a607d3a4f8bf5308e8fb64db8072291df9a61bd
3
  size 277274547
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c53de7a6f355194542f010b25d2591fb9ca83acda557a8734b3b17ed060f8d9
3
  size 277274547
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 2.0,
3
  "train_loss": 1.088201597354519,
4
- "train_runtime": 783.526,
5
  "train_samples": 88550,
6
- "train_samples_per_second": 226.03,
7
- "train_steps_per_second": 1.764
8
  }
 
1
  {
2
  "epoch": 2.0,
3
  "train_loss": 1.088201597354519,
4
+ "train_runtime": 749.7015,
5
  "train_samples": 88550,
6
+ "train_samples_per_second": 236.227,
7
+ "train_steps_per_second": 1.843
8
  }
trainer_state.json CHANGED
@@ -840,9 +840,9 @@
840
  "step": 1382,
841
  "total_flos": 5.175834887457866e+18,
842
  "train_loss": 1.088201597354519,
843
- "train_runtime": 783.526,
844
- "train_samples_per_second": 226.03,
845
- "train_steps_per_second": 1.764
846
  }
847
  ],
848
  "max_steps": 1382,
 
840
  "step": 1382,
841
  "total_flos": 5.175834887457866e+18,
842
  "train_loss": 1.088201597354519,
843
+ "train_runtime": 749.7015,
844
+ "train_samples_per_second": 236.227,
845
+ "train_steps_per_second": 1.843
846
  }
847
  ],
848
  "max_steps": 1382,