Training complete

README.md

@@ -17,23 +17,23 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mbart-neutralization
 
-This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on the Spanish Gender Neutralization dataset ([somosnlp-hackathon-2022/neutral-es](https://huggingface.co/datasets/somosnlp-hackathon-2022/neutral-es)).
+This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0107
-- Bleu: 98.3768
-- Gen Len: 33.5417
+- Loss: 2.8182
+- Bleu: 5.9775
+- Gen Len: 123.4146
 
 ## Model description
 
-This model is based on mbart-50 and uses the Spanish Gender Neutralization dataset to translate sentences from current Spanish to inclusive Spanish.
+More information needed
 
 ## Intended uses & limitations
 
-Mbart-neutralization was created in the context of a class exercice.
+More information needed
 
 ## Training and evaluation data
 
-The training and evaluation data used in our model stays the same as the training and evaluation data of the Spanish Gender Neutralization dataset.
+More information needed
 
 ## Training procedure
 
@@ -50,10 +50,10 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
-|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
-| No log        | 1.0   | 440  | 0.0190          | 99.0039 | 18.7292 |
-| 0.2249        | 2.0   | 880  | 0.0107          | 98.3768 | 33.5417 |
+| Training Loss | Epoch | Step | Validation Loss | Bleu   | Gen Len  |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|
+| No log        | 1.0   | 92   | 3.0994          | 3.5838 | 103.2244 |
+| No log        | 2.0   | 184  | 2.8182          | 5.9775 | 123.4146 |
 
 
 ### Framework versions