Update README.md

README.md

@@ -108,10 +108,11 @@ torchrun # with necessary torchrun information for distributed training\
 - 500K academic-task-oriented VQA data mixture.
 - 50K GPT-4V data mixture.
 - 40K ShareGPT data.
+- 20K COCO Caption data.
 
 #### Speeds, Sizes, Times [optional]
 
-The training cost is ~50-60 hours on 8 x 8 NVIDIA A100-SXM4-80GB (may vary due to hardware differences). 
+The training cost is 30-40 hours on 8 x 8 NVIDIA A100-SXM4-80GB (may vary due to hardware differences). 
 
 [More Information Needed]