Update README.md

README.md

@@ -21,15 +21,15 @@ model-index:
       type: other
     metrics:
     - type: meteor
-      value: 0.261
+      value: 0.267
     - type: bleu
-      value: 0.208
+      value: 0.185
     - type: cider
-      value: 0.072
+      value: 0.086
     - type: capture
-      value: 0.565
+      value: 0.576
     - type: rouge-l
-      value: 0.280
+      value: 0.287
 ---
 # Florence-2 DOCCI-FT LoRA Adapter
 
@@ -81,14 +81,15 @@ Note: Make sure you have the required libraries installed: transformers, peft, e
 
 ## Evaluation results
 
-Our LoRA adapter shows significant improvements over the base Florence-2 model across all metrics for MORE_DETAILED_CAPTION tag:
+Our LoRA adapter shows improvements over the base Florence-2 model across all metrics for MORE_DETAILED_CAPTION tag for 1000 images on the foundation-multimodal-models/DetailCaps-4870 dataset:
 
 | Metric  | Base Model | Adapted Model | Improvement |
 |---------|------------|---------------|-------------|
-| METEOR  | 0.205      | 0.261         | +27.3%      |
-| BLEU    | 0.124      | 0.208         | +67.7%      |
-| CIDEr   | 0.023      | 0.072         | +213.0%     |
-| CAPTURE | 0.529      | 0.565         | +6.8%       |
-| ROUGE-L | 0.265      | 0.280         | +5.7%       |
+| METEOR  | 0.213      | 0.267         | +25.4%      |
+| BLEU    | 0.110      | 0.185         | +68.2%      |
+| CIDEr   | 0.031      | 0.086         | +177.4%     |
+| CAPTURE | 0.546      | 0.576         | +5.5%       |
+| ROUGE-L | 0.275      | 0.287         | +4.4%       |
 
-These results demonstrate that our LoRA adapter significantly enhances the image captioning capabilities of the Florence-2 base model, particularly in generating more detailed and accurate captions.
+
+These results demonstrate that our LoRA adapter enhances the image captioning capabilities of the Florence-2 base model, particularly in generating more detailed and accurate captions.