Update README.md

README.md

@@ -8,7 +8,7 @@ datasets:
 
 This repo contains summaries of several sets of experiments comparing a number of optimizers with and without caution (https://huggingface.co/papers/2411.16085) enabled.
 
-The runs were all performed training for 200 epochs from scratch on the `timm` 'mini-imagenet' dataset, a 100 class subset of imagenet with same image sizes as originals.
+The runs were all performed training a smaller ViT (`vit_wee_patch16_reg1_gap_256`) for 200 epochs (10M samples seen) from scratch on the `timm` 'mini-imagenet' dataset, a 100 class subset of imagenet with same image sizes as originals.
 
 So far I have results for `adamw` and `laprop` but have some `mars` on the way. You can find full results in sub-folders by optimizer names. In all of these runs, the experiments with 'c' prefix in the name have caution enabled.