Training complete

README.md

@@ -4,6 +4,8 @@ base_model: facebook/mbart-large-50
 tags:
 - simplification
 - generated_from_trainer
+metrics:
+- bleu
 model-index:
 - name: mbart-neutralization
   results: []
@@ -15,6 +17,10 @@ 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 an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0156
+- Bleu: 96.6775
+- Gen Len: 18.4271
 
 ## Model description
 
@@ -41,6 +47,14 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - num_epochs: 2
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
+| No log        | 1.0   | 440  | 0.0235          | 97.6289 | 18.4792 |
+| 0.0472        | 2.0   | 880  | 0.0156          | 96.6775 | 18.4271 |
+
+
 ### Framework versions
 
 - Transformers 4.37.2

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:b5bfc0f037d795808a0c17a2683d008872d7d055cf3643fa8186442e0ed411fc
+oid sha256:1557183e69cff0fe8f273a16c860dc2b69ca3238658a0930f3dc52ef69839cae
 size 2444578688