Update README.md

README.md

@@ -58,10 +58,10 @@ The model is optimized to call these mobile action functions:
 Fine-tuned using Hugging Face [TRL (Transformer Reinforcement Learning)](https://huggingface.co/docs/trl) with the `SFTTrainer`.
 
 **Training Configuration**:
-- **Epochs**: 2
-- **Batch size**: 4 per device
-- **Gradient accumulation steps**: 8
-- **Learning rate**: 1e-5
+- **Epochs**: 4
+- **Batch size**: 8 per device
+- **Gradient accumulation steps**: 4
+- **Learning rate**: 5e-5
 - **Scheduler**: Cosine
 - **Max sequence length**: 997 tokens (based on longest example: 897 tokens)
 - **Optimizer**: AdamW (fused)