Update README.md

README.md

@@ -79,7 +79,7 @@ The masking procedure used is the standard one for Bert-style training:
 
 ### Pretraining
 
-The model was trained with 8 A100 80GB on 300B tokens, with an effective batch size of 1M tokens. The sequence length used was 1000 tokens. The Adam optimizer [38] was used with a learning rate schedule, and standard values for exponential decay rates and epsilon constants, β1 = 0.9, β2 = 0.999 and ε=1e-8. During a first warmup period, the learning rate was increased linearly between 5e-5 and 1e-4 over 16k steps before decreasing following a square root decay until the end of training.
+The model was trained with 128 A100 80GB on 300B tokens, with an effective batch size of 1M tokens. The sequence length used was 1000 tokens. The Adam optimizer [38] was used with a learning rate schedule, and standard values for exponential decay rates and epsilon constants, β1 = 0.9, β2 = 0.999 and ε=1e-8. During a first warmup period, the learning rate was increased linearly between 5e-5 and 1e-4 over 16k steps before decreasing following a square root decay until the end of training.
 
 
 ### BibTeX entry and citation info