Fix table layout

README.md

@@ -113,12 +113,12 @@ We closel follow the training procedure layed out in [Flamingo](https://arxiv.or
 
 The model is trained on the following data mixture of openly accessible data:
 
-| Data Source | Type of Data | Number of Tokens in Source | Number of Images in Source | Epochs | Effective Proportion in Number of Tokens |
-|-------------|----------------------------|------------|----------------------------|--------|
-| PMD | Image-Text Pairs | TODO | TODO | 3 | 73.85% |
-| LAION | Image-Text Pairs | TODO | TODO | 1 | 6.15% |
-| OBELISC | Unstructured Multimodal Web Documents | TODO | TODO | 3 | 2.82% |
-| Wikipedia | Unstructured Multimodal Web Documents | TODO | TODO | 1 | 17.18% |
+| Data Source | Type of Data                             | Number of Tokens in Source | Number of Images in Source | Epochs | Effective Proportion in Number of Tokens |
+|-------------|-----------------------------------------|---------------------------|---------------------------|--------|-----------------------------------------|
+| PMD         | Image-Text Pairs                         | TODO                      | TODO                      | 3      | 73.85%                                  |
+| LAION       | Image-Text Pairs                         | TODO                      | TODO                      | 1      | 6.15%                                   |
+| OBELISC     | Unstructured Multimodal Web Documents    | TODO                      | TODO                      | 3      | 2.82%                                   |
+| Wikipedia   | Unstructured Multimodal Web Documents    | TODO                      | TODO                      | 1      | 17.18%                                  |
 
 For multimodal web documents, we feed the model sequences corresponding to the succession of text paragraphs and images.
 For image-text pairs, we form the training sequences by packing images with their captions.