update model card README.md

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [IIC/roberta-base-spanish-squades](https://huggingface.co/IIC/roberta-base-spanish-squades) on the becasv2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.7840
+- Loss: 2.4358
 
 ## Model description
 
@@ -35,25 +35,23 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 3e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 11
+- eval_batch_size: 11
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 8
+- num_epochs: 6
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 5    | 1.9356          |
-| No log        | 2.0   | 10   | 1.7489          |
-| No log        | 3.0   | 15   | 2.0573          |
-| No log        | 4.0   | 20   | 2.3975          |
-| No log        | 5.0   | 25   | 2.6796          |
-| No log        | 6.0   | 30   | 2.7238          |
-| No log        | 7.0   | 35   | 2.7616          |
-| No log        | 8.0   | 40   | 2.7840          |
+| No log        | 1.0   | 6    | 1.8825          |
+| No log        | 2.0   | 12   | 1.7787          |
+| No log        | 3.0   | 18   | 2.0521          |
+| No log        | 4.0   | 24   | 2.2991          |
+| No log        | 5.0   | 30   | 2.4029          |
+| No log        | 6.0   | 36   | 2.4358          |
 
 
 ### Framework versions