Update README.md

README.md

@@ -24,7 +24,7 @@ This model was fine-tuned using **Optuna-based hyperparameter optimization** on
 
 ---
 
-<img src="https://cdn-uploads.huggingface.co/production/uploads/64e8ea3892d9db9a93580fe3/xp0S8cYIVbb8xJ0sGH7qw.png" alt="Poster" width="750"/>
+<img src="https://cdn-uploads.huggingface.co/production/uploads/64e8ea3892d9db9a93580fe3/xp0S8cYIVbb8xJ0sGH7qw.png" alt="Poster" width="600"/>
 
 ### Supported Tasks
 
@@ -35,14 +35,8 @@ This model was fine-tuned using **Optuna-based hyperparameter optimization** on
 
 ---
 
-## Training Details
 
-### Data
-
-* The recipe is dataset-agnostic. 
-
-
-### Hyperparameter Search Space
+## Hyperparameter Search Space
 
 The Optuna study explored:
 
@@ -50,14 +44,14 @@ The Optuna study explored:
 * **Weight decay:** Uniform(0.0, 0.3)
 * **Per device train batch size:** Choice([8, 16, 32])
 
-### Optimization Objective
+## Optimization Objective
 
 The pipeline optimizes:
 
 * **Metric:** Validation accuracy (can switch to F1, loss, or task-specific metrics)
 * **Direction:** Maximize
 
-### Best Trial Example (MRPC)
+## Best Trial Example (MRPC)
 
 | Hyperparameter      | Best Value |
 | ------------------- | ---------- |