llm-slice
/

blm-gpt2s-90M-s42

babylm-baseline

Model card Files Files and versions

Kessbitz commited on Aug 19

Commit

2bcd5dd

·

verified ·

1 Parent(s): 98f49fa

Update README.md

Files changed (1) hide show

README.md +1 -2

README.md CHANGED Viewed

@@ -174,10 +174,9 @@ The metrics were chosen based on the advice of the papers the tasks come from.
 ### Hyperparameters
-**TODO: UPDATE**
 | Hyperparameter | MNLI, RTE, QQP, MRPC, BoolQ, MultiRC | WSC |
-| --- | --- | --- | --- |
 | Learning Rate | 3\*10<sup>-5</sup> | 3\*10<sup>-5</sup> |
 | Batch Size | 16 | 16 |
 | Epochs | 10 | 30 |

 ### Hyperparameters
 | Hyperparameter | MNLI, RTE, QQP, MRPC, BoolQ, MultiRC | WSC |
+| --- | --- | --- |
 | Learning Rate | 3\*10<sup>-5</sup> | 3\*10<sup>-5</sup> |
 | Batch Size | 16 | 16 |
 | Epochs | 10 | 30 |