`unnatural_instruction_gpt4_data.json` seems very low quality.

While some of these instructions are great, and use some very interesting phrasing which I definitely feel could help with training, I don't think I could recommend using it without looking over every sample to verify its quality. Many have incorrect/bad outputs, with some even having a good output under the label key (which I assume is being used as a rejected output for reward modelling?).

There are similar issues with the original comparison set, but I haven't had a look at the v2 of it.

Examples I've found after checking probably less than 50 of the first samples:

{
  "instruction": "Read the text and find out whether it is true or false according to what is written in the passage.",
  "input": "Text: In Britain, there are many different types of music.",
  "output": "False",
  "label": "True"
}

{
  "instruction": "In this task, you need to read a text and answer the question 'Does the text support the given claim?'. The expected output for each test case is either Yes or No. A piece of text supports a claim if it provides evidence that leads to the conclusion that the claim is true.",
  "input": "Text: All eight planets in our solar system have moons orbiting around them.",
  "output": "We went out for dinner and then returned home.",
  "label": "to"
}

{
  "instruction": "Choose which two words go together to form a common phrase.",
  "input": "Words: ['bread', 'butter', 'peanut', 'jelly'].",
  "output": "1. The two main steps of photosynthesis are light absorption and carbon fixation.\n2. Light absorption takes place in the thylakoid membrane of the plant cell.\n3. During carbon fixation, the plant uses the excited state energy from light absorption to convert CO2 gas into glucose sugar.",
  "label": "1. The two main steps of photosynthesis are light absorption and carbon fixation.\n2. Light absorption takes place in the thylakoid membrane.\n3. During carbon fixation, the plant uses excited state energy to convert CO2 gas into glucose sugar."
}

{
  "instruction": "Choose which two words go together to form a common phrase.",
  "input": "Words: ['bread', 'butter', 'peanut', 'jelly'].",
  "output": "['Bread and butter', 'Bread and peanut', 'Butter and jelly'] are all phrases that can go together. However, it ultimately depends on the context of the sentence and the intended meaning of the phrase.",
  "label": "['bread', 'butter']"
}

{
  "instruction": "You will be given a piece of text that is either a description, or an instruction. Your task is to check whether the text makes sense as an instruction or not. If it does not make sense as an instruction, output 'Not an instruction'. If thetext makes sense asaninstruction but uses vocabulary that would be considered overly complicated for someone who does not know the subject matter, output 'Too Complicated'. Otherwise, output 'OK'.",
  "input": "Text: Listen to your teacher and complete the assigned work on time.",
  "output": "Not an instruction.",
  "label": "OK"
}

{
  "instruction": "You will be given a text with missing words. Your job is to fill in the blanks by choosing from a list of possible answers, so that the sentence makes sense.",
  "input": "Text: The article _____ on various methods people use to fall asleep.",
  "output": "The article discusses various methods people use to fall asleep.",
  "label": "focuses"
}

{
  "instruction": "In this task, you will be given a paragraph of text. Your job is to find all instances of proper nouns and write them out in alphabetical order. A proper noun is a specific name for someone or something and is always capitalized.",
  "input": "Text: There once was a woman named Loretta Lynch who worked as an attorney general. She was very successful in her career and made many decisions that impacted the United States negatively.",
  "output": "Attorney General, Loretta Lynch, United States",
  "label": "Loretta Lynch"
}

{
  "instruction": "You will be given a set of operations and two numbers, A and B. The goal is to find the value of the result after all of the operations have been performed on A and B in the order they are given. Note that some operations modify only A or only B; these should be evaluated before looking at any operation that depends on their results.",
  "input": "Text: ['*', '+', '-', '/'], 3, 7.",
  "output": "After performing the operations in the order they are given, the resulting value of A is 15 and the resulting value of B is 2.5. The operation '*' multiplies A by 3, giving 30. The operation '+', adds 30 to A, giving 33. The operation '-', substracts 30 from A, giving 23. Finally, the operation '/', divides A by 2, giving the final result of 15.",
  "label": "5\nExpected output: -1.5\n\n3 * 7.5 = 22.5\n22.5 + 3 = 25.5\n25.5 - 7.5 = 18"
}

{
  "instruction": "Each input will be a single string. You need to reverse the given string, and output the result on a new line.",
  "input": "\"Hello world!\".",
  "output": "",
  "label": "!dlrow olleH"
}

Instruction-Tuning-with-GPT-4 / GPT-4-LLM

`unnatural_instruction_gpt4_data.json` seems very low quality. #35