Update README.md

README.md

@@ -42,7 +42,6 @@ The fine-tuning process for Phi-3.5-mini-instruct-o1 employed the following tech
 - **Compute Type:** BF16
 - **Context Length:** 2048 tokens
 - **Optimizer:** AdamW with cosine learning rate scheduling
-- **Model Freezing:** Two trainable layers frozen
 - **Additional Enhancement:** NEFTune with alpha 5
 
 This fine-tuning approach was designed to efficiently adapt the model while maintaining its generalization capabilities and computational efficiency.