Joelito kapllan commited on
Commit
ad772b7
1 Parent(s): bfd5c75

The learning rate was not displayed as it should. (#3)

Browse files

- The learning rate was not displayed as it should. (63053d899584b078dbed07890799f338927b78ef)


Co-authored-by: kapllan <[email protected]>

Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -86,7 +86,7 @@ For further details see [Niklaus et al. 2023](https://arxiv.org/abs/2306.02069?u
86
  - batche size: 512 samples
87
  - Number of steps: 1M/500K for the base/large model
88
  - Warm-up steps for the first 5\% of the total training steps
89
- - Learning rate: (linearly increasing up to) $1e\!-\!4$
90
  - Word masking: increased 20/30\% masking rate for base/large models respectively
91
 
92
  ## Evaluation
 
86
  - batche size: 512 samples
87
  - Number of steps: 1M/500K for the base/large model
88
  - Warm-up steps for the first 5\% of the total training steps
89
+ - Learning rate: (linearly increasing up to) 1e-4
90
  - Word masking: increased 20/30\% masking rate for base/large models respectively
91
 
92
  ## Evaluation