Update README.md

README.md

@@ -12,7 +12,7 @@ model-index:
         dataset:
           type: amazon-reviews-multi
           name: amazon_reviews_multi
-          split: test
+          split: Dev
         metrics:
           - type: accuracy
             value: .80
@@ -102,18 +102,17 @@ The following hyperparameters were used during training:
 + optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 + num_epochs: 5
 
+## Accuracy
 
-### Training results
+The finetuned model was evaluated on the French test set of `amazon_reviews_multi`.
+- Accuracy (exact) is the exact match on the number of stars.
+- Accuracy (off-by-1) is the percentage of reviews where the number of stars the model predicts differs by a maximum of 1 from the number given by the human reviewer. 
 
-| Epoch | Training Loss | Validation Loss | Accuracy |
-|:-----:|:-------------:|:---------------:|:--------:|
-|   1   |      123      |       123       |    123   |
-|   2   |      123      |       123       |    123   |
-|   3   |      231      |       123       |    123   |
-|   4   |      123      |       123       |    123   |
-|   5   |      123      |       123       |    123   |
+| Split | Accuracy (exact) | Accuracy (off-by-1) |
+| -------- | ---------------------- | ------------------- |
+| Dev set  | 56.96%                 | 85.50%
+| Test set | 57.36%                 | 85.58%
 
-## Results
 
 
 # Framework versions