End of training

README.md

@@ -19,12 +19,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [BSC-TeMU/roberta-base-bne](https://huggingface.co/BSC-TeMU/roberta-base-bne) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4065
-- Accuracy: 0.8527
-- F1-score: 0.7826
-- Precision: 0.7945
-- Recall: 0.7727
-- Auc: 0.7727
+- Loss: 0.3567
+- Accuracy: 0.8396
+- F1-score: 0.7752
+- Precision: 0.7713
+- Recall: 0.7794
+- Auc: 0.7794
 
 ## Model description
 
@@ -43,9 +43,9 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 32
-- eval_batch_size: 32
+- learning_rate: 3e-05
+- train_batch_size: 64
+- eval_batch_size: 64
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -55,8 +55,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1-score | Precision | Recall | Auc    |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:---------:|:------:|:------:|
-| 0.3296        | 1.0   | 77   | 0.3456          | 0.8543   | 0.7671   | 0.8142    | 0.7408 | 0.7408 |
-| 0.1555        | 2.0   | 154  | 0.4065          | 0.8527   | 0.7826   | 0.7945    | 0.7727 | 0.7727 |
+| 0.4074        | 1.0   | 39   | 0.3802          | 0.8347   | 0.7643   | 0.7649    | 0.7636 | 0.7636 |
+| 0.297         | 2.0   | 78   | 0.3567          | 0.8396   | 0.7752   | 0.7713    | 0.7794 | 0.7794 |
 
 
 ### Framework versions