system HF staff commited on
Commit
814bcdc
1 Parent(s): 73b0424

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -0
README.md ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ ## bert-base-uncased fine-tuned with TextAttack on the rotten_tomatoes dataset
2
+
3
+ This `bert-base-uncased` model was fine-tuned for sequence classificationusing TextAttack
4
+ and the rotten_tomatoes dataset loaded using the `nlp` library. The model was fine-tuned
5
+ for 10 epochs with a batch size of 16, 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 0.875234521575985, as measured by the
9
+ eval set accuracy, found after 4 epochs.
10
+
11
+ For more information, check out [TextAttack on Github](https://github.com/QData/TextAttack).