End of training

README.md

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0543
-- Accuracy: 0.568
+- Loss: 1.0117
+- Accuracy: 0.6
 
 ## Model description
 
@@ -50,9 +50,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 125  | 1.2249          | 0.499    |
-| No log        | 2.0   | 250  | 1.0414          | 0.564    |
-| No log        | 3.0   | 375  | 1.0543          | 0.568    |
+| No log        | 1.0   | 125  | 1.1969          | 0.474    |
+| No log        | 2.0   | 250  | 1.0236          | 0.565    |
+| No log        | 3.0   | 375  | 1.0117          | 0.6      |
 
 
 ### Framework versions