Update README.md

README.md

@@ -45,7 +45,7 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 
  - Trained for one epoch on SlimOrca-Dedup
  - Learning rate: 1e-5
- - Cosine learning rate decay to 0
+ - Cosine learning rate decay
  - Optimizer: AdamW
  - Batch size: 256
  - Trained with FP32