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 [amberoad/bert-multilingual-passage-reranking-msmarco](https://huggingface.co/amberoad/bert-multilingual-passage-reranking-msmarco) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 7.4707
-- Accuracy: 0.0012
+- Loss: 0.9181
+- Accuracy: 0.8626
 
 ## Model description
 
@@ -50,9 +50,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step   | Validation Loss | Accuracy |
 |:-------------:|:-----:|:------:|:---------------:|:--------:|
-| 7.6625        | 1.0   | 99361  | 7.8706          | 0.0007   |
-| 7.6633        | 2.0   | 198722 | 7.9447          | 0.0006   |
-| 7.299         | 3.0   | 298083 | 7.4707          | 0.0012   |
+| 0.9646        | 1.0   | 152248 | 1.3476          | 0.7807   |
+| 0.611         | 2.0   | 304496 | 1.0336          | 0.8401   |
+| 0.4423        | 3.0   | 456744 | 0.9181          | 0.8626   |
 
 
 ### Framework versions