Update README.md

Loaded the best model manually because Trainer chose a worse model. The parameter load_best_model_at_end=True did not work.

README.md

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5759
-- Accuracy: 0.87
+- Loss: 0.4989
+- Accuracy: 0.91
 
 ## Model description