Run
│ name: "Language Detection"
│ tags: ['model:mistral-small']
│ metrics:
│   accuracy: 1
│ Records
│   Record 1/10
│   │ input: {'sentence': 'Hello, how are you?', 'groundtruth': 'English'}
│   │ metrics:
│   │   accuracy: 1
│   │ Generations
│   │   Generation 1/3
│   │   │ output: "English"
│   │   │ scores:
│   │   │   accuracy: 1
│   │   Generation 2/3
│   │   │ output: "English"
│   │   │ scores:
│   │   │   accuracy: 1
│   │   Generation 3/3
│   │   │ output: "English"
│   │   │ scores:
│   │   │   accuracy: 1
│   Record 2/10
│   │ input: {'sentence': 'Bonjour, comment ça va?', 'groundtruth': 'French'}
│   │ metrics:
│   │   accuracy: 1
│   │ Generations
│   │   Generation 1/3
│   │   │ output: "French"
│   │   │ scores:
│   │   │   accuracy: 1
│   │   Generation 2/3
│   │   │ output: "French"
│   │   │ scores:
│   │   │   accuracy: 1
│   │   Generation 3/3
│   │   │ output: "French"
│   │   │ scores:
│   │   │   accuracy: 1
│   Record 3/10
│   │ input: {'sentence': 'Hola, ¿cómo estás?', 'groundtruth': 'Spanish'}
│   │ metrics:
│   │   accuracy: 1
│   │ Generations
│   │   Generation 1/3
│   │   │ output: "Spanish"
│   │   │ scores:
│   │   │   accuracy: 1
│   │   Generation 2/3
│   │   │ output: "Spanish"
│   │   │ scores:
│   │   │   accuracy: 1
│   │   Generation 3/3
│   │   │ output: "Spanish"
│   │   │ scores:
│   │   │   accuracy: 1
│   Record 4/10
│   │ input: {'sentence': 'Hallo, wie geht es dir?', 'groundtruth': 'German'}
│   │ metrics:
│   │   accuracy: 1
│   │ Generations
│   │   Generation 1/3
│   │   │ output: "German"
│   │   │ scores:
│   │   │   accuracy: 1
│   │   Generation 2/3
│   │   │ output: "German"
│   │   │ scores:
│   │   │   accuracy: 1
│   │   Generation 3/3
│   │   │ output: "German"
│   │   │ scores:
│   │   │   accuracy: 1
│   Record 5/10
│   │ input: {'sentence': 'Ciao, come stai?', 'groundtruth': 'Italian'}
│   │ metrics:
│   │   accuracy: 1
│   │ Generations
│   │   Generation 1/3
│   │   │ output: "Italian"
│   │   │ scores:
│   │   │   accuracy: 1
│   │   Generation 2/3
│   │   │ output: "Italian"
│   │   │ scores:
│   │   │   accuracy: 1
│   │   Generation 3/3
│   │   │ output: "Italian"
│   │   │ scores:
│   │   │   accuracy: 1
│   Record 6/10
│   │ input: {'sentence': 'こんにちは、お元気ですか？', 'groundtruth': 'Japanese'}
│   │ metrics:
│   │   accuracy: 1
│   │ Generations
│   │   Generation 1/3
│   │   │ output: "Japanese"
│   │   │ scores:
│   │   │   accuracy: 1
│   │   Generation 2/3
│   │   │ output: "Japanese"
│   │   │ scores:
│   │   │   accuracy: 1
│   │   Generation 3/3
│   │   │ output: "Japanese"
│   │   │ scores:
│   │   │   accuracy: 1
│   Record 7/10
│   │ input: {'sentence': '你好，你好吗？', 'groundtruth': 'Chinese'}
│   │ metrics:
│   │   accuracy: 1
│   │ Generations
│   │   Generation 1/3
│   │   │ output: "Chinese"
│   │   │ scores:
│   │   │   accuracy: 1
│   │   Generation 2/3
│   │   │ output: "Chinese"
│   │   │ scores:
│   │   │   accuracy: 1
│   │   Generation 3/3
│   │   │ output: "Chinese"
│   │   │ scores:
│   │   │   accuracy: 1
│   Record 8/10
│   │ input: {'sentence': 'Привет, как дела?', 'groundtruth': 'Russian'}
│   │ metrics:
│   │   accuracy: 1
│   │ Generations
│   │   Generation 1/3
│   │   │ output: "Russian"
│   │   │ scores:
│   │   │   accuracy: 1
│   │   Generation 2/3
│   │   │ output: "Russian"
│   │   │ scores:
│   │   │   accuracy: 1
│   │   Generation 3/3
│   │   │ output: "Russian"
│   │   │ scores:
│   │   │   accuracy: 1
│   Record 9/10
│   │ input: {'sentence': '안녕하세요, 어떻게 지내세요?', 'groundtruth': 'Korean'}
│   │ metrics:
│   │   accuracy: 1
│   │ Generations
│   │   Generation 1/3
│   │   │ output: "Korean"
│   │   │ scores:
│   │   │   accuracy: 1
│   │   Generation 2/3
│   │   │ output: "Korean"
│   │   │ scores:
│   │   │   accuracy: 1
│   │   Generation 3/3
│   │   │ output: "Korean"
│   │   │ scores:
│   │   │   accuracy: 1
│   Record 10/10
│   │ input: {'sentence': 'Olá, como você está?', 'groundtruth': 'Portuguese'}
│   │ metrics:
│   │   accuracy: 1
│   │ Generations
│   │   Generation 1/3
│   │   │ output: "Portuguese"
│   │   │ scores:
│   │   │   accuracy: 1
│   │   Generation 2/3
│   │   │ output: "Portuguese"
│   │   │ scores:
│   │   │   accuracy: 1
│   │   Generation 3/3
│   │   │ output: "Portuguese"
│   │   │ scores:
│   │   │   accuracy: 1
