Training complete

README.md

@@ -21,10 +21,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [PlanTL-GOB-ES/roberta-large-bne](https://huggingface.co/PlanTL-GOB-ES/roberta-large-bne) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0769
-- Precision: 0.9838
-- Recall: 0.9865
-- F1: 0.9852
+- Loss: 0.0721
+- Precision: 0.9821
+- Recall: 0.9856
+- F1: 0.9838
 - Accuracy: 0.9845
 
 ## Model description
@@ -56,13 +56,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.2146        | 1.0   | 603  | 0.0843          | 0.9781    | 0.9805 | 0.9793 | 0.9786   |
-| 0.0322        | 2.0   | 1206 | 0.0714          | 0.9837    | 0.9849 | 0.9843 | 0.9837   |
-| 0.0147        | 3.0   | 1809 | 0.0769          | 0.9838    | 0.9865 | 0.9852 | 0.9845   |
+| 0.2213        | 1.0   | 603  | 0.0835          | 0.9761    | 0.9807 | 0.9784 | 0.9800   |
+| 0.0336        | 2.0   | 1206 | 0.0756          | 0.9794    | 0.9832 | 0.9813 | 0.9808   |
+| 0.0147        | 3.0   | 1809 | 0.0721          | 0.9821    | 0.9856 | 0.9838 | 0.9845   |
 
 
 ### Framework versions
 
 - Transformers 4.44.2
-- Pytorch 2.4.1+cu121
+- Pytorch 2.5.0+cu121
 - Tokenizers 0.19.1

runs/Oct28_10-19-38_4226ec852e37/events.out.tfevents.1730111007.4226ec852e37.2246.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e93a67006237f4efbe596a86207730849317fb799e476ffe46de65237a45174
-size 8589
+oid sha256:43d0941ac509627ce3eb4abb331dce165d8967a2c241254067f4734b1af61650
+size 9415