Update README.md

README.md

@@ -1,20 +1,25 @@
 ---
 license: mit
-base_model: facebook/bart-large-cnn
+base_model: facebook/mbart-large-50
 tags:
-- text2text-generation
 - generated_from_trainer
+metrics:
+- bleu
 model-index:
-- name: modelo_simplificacion_bart
+- name: mbart-simplificacion
   results: []
+datasets:
+- crrodrvi/lectura_dificil_facil
+language:
+- es
+pipeline_tag: text2text-generation
 ---
-
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-
 # modelo_simplificacion_bart
 
-This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on the None dataset.
+This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on the lectura_dificl_facil dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.9828 
+- Bleu: 9.1817
 
 ## Model description
 
@@ -33,24 +38,27 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 5.6e-05
 - train_batch_size: 4
 - eval_batch_size: 4
 - seed: 42
-- gradient_accumulation_steps: 16
-- total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
-- num_epochs: 1
+- num_epochs: 3
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss | Bleu   | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
+| No log        | 1.0   | 109  | 3.1239          | 8.7241 | 29.2727 |
+| No log        | 2.0   | 218  | 3.0680          | 7.3130 | 23.9432 |
+| No log        | 3.0   | 327  | 2.9828          | 9.1817 | 28.5000 |
+
 
 
 ### Framework versions
 
-- Transformers 4.42.4
-- Pytorch 2.3.1+cu121
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
 - Datasets 2.20.0
 - Tokenizers 0.19.1