leofn3/racismo_update

README.md

@@ -3,8 +3,6 @@ license: other
 base_model: PORTULAN/albertina-ptbr
 tags:
 - generated_from_trainer
-widget:
-- text: "Negra melodia que vem do sangue do coração"
 metrics:
 - accuracy
 model-index:
@@ -19,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [PORTULAN/albertina-ptbr](https://huggingface.co/PORTULAN/albertina-ptbr) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0501
-- Accuracy: 0.9874
+- Loss: 0.0036
+- Accuracy: 0.9989
 
 ## Model description
 
@@ -40,24 +38,26 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 4
-- eval_batch_size: 4
+- train_batch_size: 2
+- eval_batch_size: 2
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 4
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 199  | 0.1769          | 0.9371   |
-| No log        | 2.0   | 398  | 0.0501          | 0.9874   |
+| No log        | 1.0   | 468  | 0.2304          | 0.9583   |
+| 0.7037        | 2.0   | 936  | 0.0847          | 0.9840   |
+| 0.256         | 3.0   | 1404 | 0.0075          | 0.9979   |
+| 0.0759        | 4.0   | 1872 | 0.0036          | 0.9989   |
 
 
 ### Framework versions
 
-- Transformers 4.31.0
+- Transformers 4.32.1
 - Pytorch 2.0.1+cu118
 - Datasets 2.14.4
 - Tokenizers 0.13.3