File size: 3,508 Bytes
4106f13 7c06aef 4106f13 7c06aef 4106f13 7c06aef 4106f13 b1e5b40 98c6811 4106f13 7c06aef 4106f13 7c06aef 4106f13 7c06aef 4106f13 b0aa389 4106f13 7c06aef 4106f13 549360a 4106f13 7c06aef 4106f13 549360a b0aa389 7c06aef b0aa389 549360a b0aa389 549360a 7c06aef 549360a 4106f13 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 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 96 97 98 99 100 101 102 103 104 105 106 107 108 |
import { Column } from 'primereact/column'
import ScoreField from './ScoreField'
const scoreBodyTemplate = (field, options = {}) => {
const { minScore = 0, maxScore = 1, machineTranslatedMetrics = [] } = options
return rowData => {
const score = rowData[field]
const isMachineTranslated = machineTranslatedMetrics.includes(field)
return ScoreField(score, minScore, maxScore, isMachineTranslated)
}
}
const ScoreColumns = (machineTranslatedMetrics = []) => [
<Column
field='average'
header='Proficiency'
headerTooltip='Language Proficiency Score (average of the scores for each task, after min-max normalization)'
sortable
body={scoreBodyTemplate('average', { minScore: 0.2, maxScore: 0.5, machineTranslatedMetrics })}
style={{ minWidth: '5rem', maxWidth: '10rem' }}
/>,
<Column
field='translation_from_bleu'
header='Translation (from)'
headerTooltip='Translation performance from a language to all other languages (spBLEU score on a sample of the FLORES+ benchmark)'
sortable
body={scoreBodyTemplate('translation_from_bleu', {
minScore: 0,
maxScore: 0.5,
machineTranslatedMetrics
})}
style={{ minWidth: '5rem', maxWidth: '10rem' }}
/>,
<Column
field='translation_to_bleu'
header='Translation (to)'
headerTooltip='Translation performance from all other languages to a language (spBLEU score on a sample of the FLORES+ benchmark)'
sortable
body={scoreBodyTemplate('translation_to_bleu', {
minScore: 0,
maxScore: 0.5,
machineTranslatedMetrics
})}
style={{ minWidth: '5rem', maxWidth: '10rem' }}
/>,
<Column
field='classification_accuracy'
header='Classification'
headerTooltip='Classification performance (accuracy on a sample of the SIB-200 / FLORES+ classification benchmark)'
sortable
body={scoreBodyTemplate('classification_accuracy', {
minScore: 0,
maxScore: 0.5,
machineTranslatedMetrics
})}
style={{ minWidth: '5rem', maxWidth: '10rem' }}
/>,
// <Column
// field='language_modeling_chrf'
// header='Language Modeling'
// sortable
// body={scoreBodyTemplate('language_modeling_chrf', {
// minScore: 0.8,
// maxScore: 1
// })}
// style={{ minWidth: '5rem', maxWidth: '10rem' }}
// />,
<Column
field='mmlu_accuracy'
header='Q&A'
headerTooltip='Question Answering performance (accuracy on a sample of multilingual versions of the MMLU benchmark)'
sortable
body={scoreBodyTemplate('mmlu_accuracy', {
minScore: 0,
maxScore: 1,
machineTranslatedMetrics
})}
style={{ minWidth: '5rem', maxWidth: '10rem' }}
/>,
<Column
field='arc_accuracy'
header='Advanced Q&A'
headerTooltip='Advanced Question Answering performance (accuracy on a sample of multilingual versions of the ARC-Easy benchmark)'
sortable
body={scoreBodyTemplate('arc_accuracy', {
minScore: 0,
maxScore: 1,
machineTranslatedMetrics
})}
style={{ minWidth: '5rem', maxWidth: '10rem' }}
/>,
<Column
field='mgsm_accuracy'
header='Math'
headerTooltip='Math Problem Solving performance (accuracy on a sample of multilingual versions of the GSM8K benchmark)'
sortable
body={scoreBodyTemplate('mgsm_accuracy', {
minScore: 0,
maxScore: 1,
machineTranslatedMetrics
})}
style={{ minWidth: '5rem', maxWidth: '10rem' }}
/>,
]
export default ScoreColumns
|