GOREExperiment's picture
Model trained.
b4bcb5c
|
raw
history blame
367 Bytes
metadata
language:
  - fr
tags:
  - nli
metrics:
  - f1

Eval results

We obtain the following results on validation and test sets:

Set F1micro F1macro
validation 69.2 69.3
test 69.8 69.9