Training complete

README.md

@@ -1,4 +1,5 @@
 ---
+library_name: transformers
 license: mit
 base_model: facebook/mbart-large-50
 tags:
@@ -18,9 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 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: 0.0220
-- Bleu: 98.2132
-- Gen Len: 18.5417
+- Loss: 0.0134
+- Bleu: 98.9481
+- Gen Len: 18.6354
 
 ## Model description
 
@@ -43,7 +44,7 @@ The following hyperparameters were used during training:
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- optimizer: Use 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: 2
 
@@ -51,13 +52,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
-| No log        | 1.0   | 440  | 0.0490          | 96.2659 | 19.0104 |
-| 0.2462        | 2.0   | 880  | 0.0220          | 98.2132 | 18.5417 |
+| No log        | 1.0   | 440  | 0.0162          | 97.6428 | 18.5417 |
+| 0.2252        | 2.0   | 880  | 0.0134          | 98.9481 | 18.6354 |
 
 
 ### Framework versions
 
-- Transformers 4.38.1
-- Pytorch 2.1.0+cu121
-- Datasets 2.17.1
-- Tokenizers 0.15.2
+- Transformers 4.47.1
+- Pytorch 2.5.1+cu121
+- Datasets 3.2.0
+- Tokenizers 0.21.0

generation_config.json

@@ -7,5 +7,5 @@
   "max_length": 200,
   "num_beams": 5,
   "pad_token_id": 1,
-  "transformers_version": "4.38.1"
+  "transformers_version": "4.47.1"
 }