Update README.md

README.md

@@ -64,13 +64,18 @@ def get_reward(prompt, completion):
 
 ## Training Details
 
-The reward model was trained using:
-- Learning rate: 3 × 10⁻⁶
-- Gradient norm threshold: 1.0
-- Learning rate schedule: Linear
-- Batch size (effective): 256
-- Max token length: 2,048
-- Number of epochs: 1
+The reward model was trained with the following settings:
+- Base model: SmolTulu-1.7b-Instruct 
+- Mixed precision: bfloat16
+- Learning rate: 4e-5
+- Effective batch size: 4
+- Maximum sequence length: 2048 tokens
+- Maximum prompt length: 2048 tokens
+- Training epochs: 1  
+- Training data: Tulu 3 8B preference mixture
+- Evaluation data: UltraFeedback (cleaned)
+- Gradient checkpointing enabled
+- DeepSpeed Zero-3 for memory optimization
 
 ## Citation