christinacdl commited on
Commit
d8cd242
1 Parent(s): 1354db4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -71,7 +71,7 @@ The following hyperparameters were used during training:
71
  - max_grad_norm: 1.0
72
  - seed: 42
73
  - optimizer: adamw_torch_fused
74
- - max_steps: -1
75
  - warmup_ratio: 0
76
  - group_by_length: True
77
  - max_seq_length: 512
 
71
  - max_grad_norm: 1.0
72
  - seed: 42
73
  - optimizer: adamw_torch_fused
74
+ - weight decay: 0.01
75
  - warmup_ratio: 0
76
  - group_by_length: True
77
  - max_seq_length: 512