EN3S/NLP_assignment_2

README.md

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9273
-- Accuracy: 0.6570
+- Loss: 1.0313
+- Accuracy: 0.7256
 
 ## Model description
 
@@ -50,11 +50,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.6777        | 1.0   | 39   | 0.6834          | 0.5415   |
-| 0.5929        | 2.0   | 78   | 0.6242          | 0.6354   |
-| 0.3692        | 3.0   | 117  | 0.7174          | 0.6462   |
-| 0.1572        | 4.0   | 156  | 0.9273          | 0.6570   |
-| 0.0605        | 5.0   | 195  | 1.3611          | 0.6354   |
+| 0.6499        | 1.0   | 39   | 0.6318          | 0.6245   |
+| 0.5297        | 2.0   | 78   | 0.6423          | 0.6895   |
+| 0.3409        | 3.0   | 117  | 0.7184          | 0.6931   |
+| 0.1415        | 4.0   | 156  | 0.9218          | 0.7148   |
+| 0.0985        | 5.0   | 195  | 1.0313          | 0.7256   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd20d71390a51b99907ddbda4262f8a9cc9a6edd1d1c1d8bae0a268577718382
+oid sha256:fea7a822343518cc5588fbbd4f4740020da2381f0d54605937eb5bf8dca113bf
 size 437958648