Training complete

README.md

@@ -5,6 +5,8 @@ base_model: facebook/mbart-large-50
 tags:
 - simplification
 - generated_from_trainer
+metrics:
+- bleu
 model-index:
 - name: mbart-canciones
   results: []
@@ -16,6 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
 # mbart-canciones
 
 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: 1.4794
+- Bleu: 30.6178
+- Gen Len: 65.6891
 
 ## Model description
 
@@ -40,7 +46,14 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 0.5
+- num_epochs: 0.1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Bleu    | Gen Len |
+|:-------------:|:------:|:----:|:---------------:|:-------:|:-------:|
+| 1.6313        | 0.1000 | 3233 | 1.4794          | 30.6178 | 65.6891 |
+
 
 ### Framework versions
 

generation_config.json

@@ -1,5 +1,4 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 0,
   "decoder_start_token_id": 2,
   "early_stopping": true,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54b681376415674c22b5046ad34ed12d538ba8435536a218ec947ba497279eeb
+oid sha256:94c977fb81c131c6a3864fc2a5d9d2de97ce7cda086daddd650d0ccb11c415a9
 size 2444578688