metadata
license: mit
language:
- en
tags:
- t5
model-index:
- name: metro_t0_base
results:
- task:
type: natural-language-inference
dataset:
type: super_glue
name: RTE
config: rte
split: validation
metrics:
- type: accuracy
value: 61.6245487364621
- task:
type: natural-language-inference
dataset:
type: super_glue
name: CB
config: cb
split: validation
metrics:
- type: accuracy
value: 46.54761904761905
- task:
type: natural-language-inference
dataset:
type: anli
name: ANLI R1
split: dev_r1
metrics:
- type: accuracy
value: 32.12
- task:
type: natural-language-inference
dataset:
type: anli
name: ANLI R2
split: dev_r2
metrics:
- type: accuracy
value: 33.599999999999994
- task:
type: natural-language-inference
dataset:
type: anli
name: ANLI R3
split: dev_r3
metrics:
- type: accuracy
value: 33.833333333333336
- task:
type: coreference-resolution
dataset:
type: super_glue
name: WSC
config: wsc.fixed
split: validation
metrics:
- type: accuracy
value: 56.82692307692308
- task:
type: coreference-resolution
dataset:
type: winogrande
name: Winogrande XL
config: winogrande_xl
split: validation
metrics:
- type: accuracy
value: 50.87608524072613
- task:
type: multiple-choice-qa
dataset:
type: super_glue
name: COPA
config: copa
split: validation
metrics:
- type: accuracy
value: 75.25
- task:
type: multiple-choice-qa
dataset:
type: story_cloze
name: StoryCloze 2016
config: '2016'
split: validation
metrics:
- type: accuracy
value: 82.44788882950294
- task:
type: multiple-choice-qa
dataset:
type: hellaswag
name: HellaSwag
split: validation
metrics:
- type: accuracy
value: 39.84266082453695
- task:
type: word-sense-disambiguation
dataset:
type: super_glue
name: WiC
config: wic
split: validation
metrics:
- type: accuracy
value: 62.88401253918495