MoritzLaurer HF staff commited on
Commit
4b15c4c
1 Parent(s): a708ccc
Files changed (1) hide show
  1. README.md +9 -5
README.md CHANGED
@@ -51,12 +51,16 @@ training_args = TrainingArguments(
51
 
52
  ### Eval results
53
  The model was evaluated using the test sets for MultiNLI and ANLI and the dev set for Fever-NLI
54
- dataset | accuracy
55
  -------|---------
56
- mnli_m/mm | 0.903/0.903
57
- fever-nli | 0.777
58
- anli-all | 0.579
59
- anli-r3 | 0.495
 
 
 
 
60
 
61
  ## Limitations and bias
62
  Please consult the original DeBERTa paper and literature on different NLI datasets for potential biases.
 
51
 
52
  ### Eval results
53
  The model was evaluated using the test sets for MultiNLI and ANLI and the dev set for Fever-NLI
54
+ dataset | accuracy
55
  -------|---------
56
+ mnli_m/mm | 0.903/0.903
57
+ fever-nli | 0.777
58
+ anli-all | 0.579
59
+ anli-r3 | 0.495
60
+
61
+ accuracy (balanced) | F1 (weighted) | precision | recall | accuracy (not balanced)
62
+ -------|---------|----------|---------|----------
63
+ 0.745 | 0.773 | 0.772 | 0.771 | 0.771
64
 
65
  ## Limitations and bias
66
  Please consult the original DeBERTa paper and literature on different NLI datasets for potential biases.