Training complete

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: facebook/mbart-large-50
+base_model: october-sd/mbart-large-50-finetuned-mr-sum
 tags:
 - summarization
 - generated_from_trainer
@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mbart-large-50-finetuned-mr-sum
 
-This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on the None dataset.
+This model is a fine-tuned version of [october-sd/mbart-large-50-finetuned-mr-sum](https://huggingface.co/october-sd/mbart-large-50-finetuned-mr-sum) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.7550
+- Loss: 1.9896
 
 ## Model description
 
@@ -41,6 +41,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
 - num_epochs: 2
 - mixed_precision_training: Native AMP
 
@@ -48,8 +49,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.6974        | 1.0   | 3605 | 1.8238          |
-| 1.8756        | 2.0   | 7210 | 1.7550          |
+| 1.5989        | 1.0   | 3605 | 1.9562          |
+| 1.1384        | 2.0   | 7210 | 1.9896          |
 
 
 ### Framework versions