update model card README.md

README.md

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bernhardtandy/music_CLM](https://huggingface.co/bernhardtandy/music_CLM) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.9631
+- Loss: 3.1293
 
 ## Model description
 
@@ -42,7 +42,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 1000
-- num_epochs: 3
+- num_epochs: 2
 - mixed_precision_training: Native AMP
 
 ### Training results