google-play-sentiment-analysis

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [neuralmind/bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4513
-- Accuracy: 0.475
+- Loss: 3.1514
+- Accuracy: 0.4623
 
 ## Model description
 
@@ -43,15 +43,17 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3.0
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 250  | 1.2596          | 0.4663   |
-| 1.1909        | 2.0   | 500  | 1.2813          | 0.4843   |
-| 1.1909        | 3.0   | 750  | 1.4513          | 0.475    |
+| No log        | 1.0   | 250  | 1.9720          | 0.4263   |
+| 0.518         | 2.0   | 500  | 2.1792          | 0.4647   |
+| 0.518         | 3.0   | 750  | 2.6638          | 0.4383   |
+| 0.2242        | 4.0   | 1000 | 2.9686          | 0.462    |
+| 0.2242        | 5.0   | 1250 | 3.1514          | 0.4623   |
 
 
 ### Framework versions