Update README.md

Update training setup. 8 days on V3-512

README.md

@@ -16,7 +16,7 @@ This is an unofficial implementation of [ALIGN](https://arxiv.org/abs/2102.05918
 
 It's developed by Kakao Brain to validate the performance of COYO-700M dataset on a large-scale model.
 
-The training took about 10 days on TPU V3-1024 with `batch_size=64k`.
+The training took about 8 days on TPU V3-512.
 
 ## Model Date
 
@@ -34,10 +34,10 @@ This model is trained on [COYO-700M](https://github.com/kakaobrain/coyo-dataset)
 
 # Evaluation results
 
-|                                |  Dataset   | ImageNet | Flickr30k |         | MsCOCO  |         |
-|--------------------------------|:----------:|:--------:|:---------:|:-------:|:-------:|:-------:|
-|                                |            |   KNN    |  I2T R@1  | T2I R@1 | I2T R@1 | T2I R@1 |
-| ALIGN-L2-Large(Google)         | ALIGN 1.8B |   76.4   |   88.6    |  75.7   |  58.6   |  45.6   |
-| ALIGN-B7-Base(Google)          | ALIGN 1.8B |   69.3   |     -     |    -    |  55.4   |  41.7   |
-| COYO-ALIGN-B7-Base(Kakao Brain) | COYO-700M  |   68.6   |   88.1    |  73.2   |  61.2   |  43.1   |
+|                                  |  Dataset   | ImageNet | Flickr30k |         | MsCOCO  |         |
+|----------------------------------|:----------:|:--------:|:---------:|:-------:|:-------:|:-------:|
+|                                  |            |   KNN    |  I2T R@1  | T2I R@1 | I2T R@1 | T2I R@1 |
+| ALIGN-L2-Large(Google)           | ALIGN 1.8B |   76.4   |   88.6    |  75.7   |  58.6   |  45.6   |
+| ALIGN-B7-Base(Google)            | ALIGN 1.8B |   69.3   |     -     |    -    |  55.4   |  41.7   |
+| COYO-ALIGN-B7-Base(Kakao Brain)  | COYO-700M  |   68.6   |   88.1    |  73.2   |  61.2   |  43.1   |