_longbench2_incontext.yaml 239 Bytes
Newer Older
Janna's avatar
Janna committed
1
2
3
4
5
6
7
8
9
10
11
group: longbench2_incontext
group_alias: "Long In-context Learning"
task:
  - longbench2_user_guide
  - longbench2_translate
  - longbench2_many_shot
aggregate_metric_list:
  - metric: acc
    weight_by_size: True
metadata:
  version: 0.0