End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [pierreguillou/gpt2-small-portuguese](https://huggingface.co/pierreguillou/gpt2-small-portuguese) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.3158
+- Loss: 4.1675
 
 ## Model description
 
@@ -48,16 +48,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 3.489         | 1.0   | 38   | 4.1621          |
-| 3.3342        | 2.0   | 76   | 4.1957          |
-| 3.2612        | 3.0   | 114  | 4.2147          |
-| 3.1731        | 4.0   | 152  | 4.2456          |
-| 3.077         | 5.0   | 190  | 4.2690          |
-| 3.0259        | 6.0   | 228  | 4.2881          |
-| 2.9368        | 7.0   | 266  | 4.2997          |
-| 2.9735        | 8.0   | 304  | 4.3109          |
-| 2.9558        | 9.0   | 342  | 4.3141          |
-| 2.9048        | 10.0  | 380  | 4.3158          |
+| 4.0373        | 1.0   | 38   | 4.1597          |
+| 3.8691        | 2.0   | 76   | 4.1377          |
+| 3.8037        | 3.0   | 114  | 4.1324          |
+| 3.6804        | 4.0   | 152  | 4.1339          |
+| 3.5658        | 5.0   | 190  | 4.1412          |
+| 3.4922        | 6.0   | 228  | 4.1479          |
+| 3.379         | 7.0   | 266  | 4.1537          |
+| 3.4002        | 8.0   | 304  | 4.1620          |
+| 3.3623        | 9.0   | 342  | 4.1654          |
+| 3.3001        | 10.0  | 380  | 4.1675          |
 
 
 ### Framework versions