Update README.md
Browse files
README.md
CHANGED
@@ -109,9 +109,9 @@ The following hyperparameters were used during training:
|
|
109 |
- accumulation_steps: 4
|
110 |
- total_steps: 40,712
|
111 |
- eval_freq: 10,178
|
112 |
-
- optimizer:
|
113 |
- scheduler: linear
|
114 |
- weight_decay: 0.01
|
115 |
-
- warmup_ratio:
|
116 |
- text_maxlength: 1024
|
117 |
|
|
|
109 |
- accumulation_steps: 4
|
110 |
- total_steps: 40,712
|
111 |
- eval_freq: 10,178
|
112 |
+
- optimizer: AdamW
|
113 |
- scheduler: linear
|
114 |
- weight_decay: 0.01
|
115 |
+
- warmup_ratio: 0.1
|
116 |
- text_maxlength: 1024
|
117 |
|