Skip to content

GitLab

Switch branch/tag
Find file Normal viewHistoryPermalink
t0_eval.yaml 3.13 KB
Newer Older
lintangsutawika's avatar
can now process a benchmark that uses promptsource  
lintangsutawika committed
1 
group: t0_eval
lintangsutawika's avatar
added benchmark configs  
lintangsutawika committed
2 
task:
lintangsutawika's avatar
update and fixes  
lintangsutawika committed
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26 
  # Coreference Resolution
  - dataset_path: super_glue
    dataset_name: wsc.fixed
    use_prompt: promptsource:*
    training_split: train
    validation_split: validation
    metric_list:
      - metric: exact_match
        aggregation: mean
        higher_is_better: true
        ignore_case: true
        ignore_punctuation: true
  # Coreference Resolution
  - dataset_path: winogrande
    dataset_name: winogrande_xl
    use_prompt: promptsource:*
    training_split: train
    validation_split: validation
    metric_list:
      - metric: exact_match
        aggregation: mean
        higher_is_better: true
        ignore_case: true
        ignore_punctuation: true
lintangsutawika's avatar
can now process a benchmark that uses promptsource  
lintangsutawika committed
27
28 
  # Natural Language Inference
  - dataset_path: super_glue
lintangsutawika's avatar
added benchmark configs  
lintangsutawika committed
29 
    dataset_name: cb
lintangsutawika's avatar
can now process a benchmark that uses promptsource  
lintangsutawika committed
30
31
32 
    use_prompt: promptsource:*
    training_split: train
    validation_split: validation
lintangsutawika's avatar
update on metrics and delet files  
lintangsutawika committed
33 
    output_type: greedy_until
lintangsutawika's avatar
can now process a benchmark that uses promptsource  
lintangsutawika committed
34
35
36
37
38
39 
    metric_list:
      - metric: exact_match
        aggregation: mean
        higher_is_better: true
        ignore_case: true
        ignore_punctuation: true
lintangsutawika's avatar
update and fixes  
lintangsutawika committed
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95 
  - dataset_path: super_glue
    dataset_name: rte
    use_prompt: promptsource:*
    training_split: train
    validation_split: validation
    metric_list:
      - metric: exact_match
        aggregation: mean
        higher_is_better: true
        ignore_case: true
        ignore_punctuation: true
  - task: anli_r1
    dataset_path: anli
    use_prompt: promptsource:*
    training_split: train_r1
    validation_split: dev_r1
    metric_list:
      - metric: exact_match
        aggregation: mean
        higher_is_better: true
        ignore_case: true
        ignore_punctuation: true
  - task: anli_r2
    dataset_path: anli
    use_prompt: promptsource:*
    training_split: train_r2
    validation_split: dev_r2
    metric_list:
      - metric: exact_match
        aggregation: mean
        higher_is_better: true
        ignore_case: true
        ignore_punctuation: true
  - task: anli_r3
    dataset_path: anli
    use_prompt: promptsource:*
    training_split: train_r3
    validation_split: dev_r3
    metric_list:
      - metric: exact_match
        aggregation: mean
        higher_is_better: true
        ignore_case: true
        ignore_punctuation: true
  # Sentence Completion
  - dataset_path: super_glue
    dataset_name: copa
    use_prompt: promptsource:*
    training_split: train
    validation_split: validation
    metric_list:
      - metric: exact_match
        aggregation: mean
        higher_is_better: true
        ignore_case: true
        ignore_punctuation: true
lintangsutawika's avatar
can now process a benchmark that uses promptsource  
lintangsutawika committed
96 
  # Natural Language Inference
lintangsutawika's avatar
update and fixes  
lintangsutawika committed
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118 
  - dataset_path: hellaswag
    use_prompt: promptsource:*
    training_split: train
    validation_split: validation
    metric_list:
      - metric: exact_match
        aggregation: mean
        higher_is_better: true
        ignore_case: true
        ignore_punctuation: true
  # Word Sense Disambiguation
  - dataset_path: super_glue
    dataset_name: wic
    use_prompt: promptsource:*
    training_split: train
    validation_split: validation
    metric_list:
      - metric: exact_match
        aggregation: mean
        higher_is_better: true
        ignore_case: true
        ignore_punctuation: true