jimypbr commited on
Commit
765e7f9
1 Parent(s): 08e9699

End of training

Browse files
.gitattributes CHANGED
@@ -26,3 +26,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
26
  *.zip filter=lfs diff=lfs merge=lfs -text
27
  *.zstandard filter=lfs diff=lfs merge=lfs -text
28
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
26
  *.zip filter=lfs diff=lfs merge=lfs -text
27
  *.zstandard filter=lfs diff=lfs merge=lfs -text
28
  *tfevents* filter=lfs diff=lfs merge=lfs -text
29
+ eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text
all_results.json CHANGED
@@ -1,8 +1,11 @@
1
  {
2
  "epoch": 2.0,
 
 
 
3
  "train_loss": 1.088201597354519,
4
- "train_runtime": 719.9384,
5
  "train_samples": 88550,
6
- "train_samples_per_second": 245.993,
7
- "train_steps_per_second": 1.92
8
  }
 
1
  {
2
  "epoch": 2.0,
3
+ "eval_exact_match": 87.01040681173131,
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
  }
eval_nbest_predictions.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6db3c582affb4fc1a6cccc9f461721100b335e4094fc6f4b5708b14e49d3cd2
3
+ size 45927734
eval_predictions.json ADDED
The diff for this file is too large to render. See raw diff
 
eval_results.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "eval_exact_match": 87.01040681173131,
4
+ "eval_f1": 92.97352589089498,
5
+ "eval_samples": 10788
6
+ }
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": 719.9384,
5
  "train_samples": 88550,
6
- "train_samples_per_second": 245.993,
7
- "train_steps_per_second": 1.92
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
  }
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": 719.9384,
844
- "train_samples_per_second": 245.993,
845
- "train_steps_per_second": 1.92
846
  }
847
  ],
848
  "max_steps": 1382,
 
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,