system HF staff commited on
Commit
ceac895
1 Parent(s): 103a5d3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -0
README.md ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ## roberta-base fine-tuned with TextAttack on the glue dataset
2
+
3
+ This `roberta-base` model was fine-tuned for sequence classification using TextAttack
4
+ and the glue dataset loaded using the `nlp` library. The model was fine-tuned
5
+ for 5 epochs with a batch size of 32, a learning
6
+ rate of 2e-05, and a maximum sequence length of 128.
7
+ Since this was a classification task, the model was trained with a cross-entropy loss function.
8
+ The best score the model achieved on this task was 0.850431447746884, as measured by the
9
+ eval set accuracy, found after 1 epoch.
10
+
11
+ For more information, check out [TextAttack on Github](https://github.com/QData/TextAttack).