Update README.md

README.md

@@ -5,11 +5,9 @@ tags:
 - generated_from_trainer
 metrics:
 - accuracy
-model-index:
-- name: PT-simple_wikipedia_LM-random-mega-small-2048-MR0.50-C1024-tk_id
-  results: []
 datasets:
 - pszemraj/simple_wikipedia_LM
+pipeline_tag: fill-mask
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mega-small-2048 on simple wikipedia
 
-MEGA for masked LM 'small' (12 layers, 512 hidden size, 2048 ctz with chunks of 1024) on the `pszemraj/simple_wikipedia_LM` dataset.
+MEGA for masked LM 'small' (12 layers, 512 hidden size, 2048 ctx in chunks of 1024) on the `pszemraj/simple_wikipedia_LM` dataset.
 It achieves the following results on the evaluation set:
 - Loss: 3.4773
 - Accuracy: 0.4591