ChainForge/chainforge/oaievals/multistep-word-problems.cforge

{"flow": {"nodes": [{"width": 312, "height": 311, "id": "prompt-multistep-word-problems", "type": "prompt", "data": {"prompt": "{prompt}", "n": 1, "llms": [{"key": "aa3c0f03-22bd-416e-af4d-4bf5c4278c99", "settings": {"system_msg": "Solve the following questions. Answer with either a single whole number or a simple fraction. If units are used in the question, make sure the answer is in the same units used in the question, though do not include the units in the answer. Do not include additional text or explanation in your answer. You are a helpful assistant.", "temperature": 1, "functions": [], "function_call": "", "top_p": 1, "stop": [], "presence_penalty": 0, "frequency_penalty": 0}, "name": "GPT3.5", "emoji": "\ud83d\ude42", "model": "gpt-3.5-turbo", "base_model": "gpt-3.5-turbo", "temp": 1, "formData": {"shortname": "GPT3.5", "model": "gpt-3.5-turbo", "system_msg": "Solve the following questions. Answer with either a single whole number or a simple fraction. If units are used in the question, make sure the answer is in the same units used in the question, though do not include the units in the answer. Do not include additional text or explanation in your answer. You are a helpful assistant.", "temperature": 1, "functions": "", "function_call": "", "top_p": 1, "stop": "", "presence_penalty": 0, "frequency_penalty": 0}}]}, "position": {"x": 448, "y": 224}, "selected": false, "positionAbsolute": {"x": 448, "y": 224}, "dragging": false}, {"width": 333, "height": 182, "id": "eval-multistep-word-problems", "type": "evaluator", "data": {"code": "function evaluate(response) {\n\tlet ideal = response.meta['Ideal'];\n\treturn response.text.startsWith(ideal);\n}", "language": "javascript"}, "position": {"x": 820, "y": 150}, "positionAbsolute": {"x": 820, "y": 150}}, {"width": 228, "height": 196, "id": "vis-multistep-word-problems", "type": "vis", "data": {"input": "eval-multistep-word-problems"}, "position": {"x": 1200, "y": 250}, "positionAbsolute": {"x": 1200, "y": 250}}, {"width": 302, "height": 260, "id": "inspect-multistep-word-problems", "type": "inspect", "data": {"input": "prompt-multistep-word-problems"}, "position": {"x": 820, "y": 400}, "positionAbsolute": {"x": 820, "y": 400}}, {"width": 423, "height": 417, "id": "table-multistep-word-problems", "type": "table", "data": {"rows": [{"prompt": "Sarah has 23 apples, and she wants to divide them among her 5 friends such that each will get an equal amount of apples and she gets to keep twice as many as she hands out to each friend. How many apples are left over?", "ideal": "2"}, {"prompt": "A store is offering a 25% discount on a jacket that originally costs $120. The store is also offering another 20% discount on pants that cost half of the jacket. Jane has $200. How much will she have after buying both the jacket and the pants?", "ideal": "62"}, {"prompt": "A recipe calls for 1/2 cup of sugar. John wants to make half of the recipe, but also another recipe which will take three times as much sugar as full first recipe. If John only has enough sugar to make the second recipe in full but still wants to make half of the first recipe, what fraction of the second recipe can John make?", "ideal": "5/6"}, {"prompt": "There are two circles. The second circle has twice the circumference of the first circle. The diameter of both circles add up to 20. What is the diameter of the first circle?", "ideal": "20/3"}, {"prompt": "If a bank account has an annual interest rate of 10% and a starting balance of $1,000, how much interest will be earned after 3 years?", "ideal": "331"}, {"prompt": "In a standard deck of 52 playing cards, what is the probability of drawing an ace, a spade, or a red face card?", "ideal": "11/26"}, {"prompt": "A train travels at a constant and max speed of 100 km/h until it reaches 5/10 of its journey, at which point it slows down to 50km/h. If the journey distance is as far as it can travel at max speed in 2 hour, how long will it take to complete the trip?", "ideal": "3"}, {"prompt": "There are 2.54 cm in an inch. How many inches are in three lengths added together, where the first length is two times the second length which is three times as long as the third length which is 5.08 cm", "ideal": "20"}, {"prompt": "In a juice recipe, the ratio of oranges to apples is 3:5, the ratio of pears to apples is 6:2. How much total fruit do you need if you have 6 oranges?", "ideal": "46"}, {"prompt": "In a right-angled triangle, the two shorter sides total up to 7 cm in length, with one side being 3/4 the length of the other. What is the length of the hypotenuse?", "ideal": "5"}, {"prompt": "The test scores of students are: 59,35, 60, 70, 80, 85, 90, 95. What is the median test score?", "ideal": "75"}, {"prompt": "In a class of 14 students with 8 girls and 6 boys, a committee of 4 students is to be chosen where there must be an equal number of boys and girls on each committee. How many different ways can the committee be formed?", "ideal": "420"}, {"prompt": "A farmer has a rectangular plot of land that measures 200 meters by 400 meters. He wants to divide the plot into smaller equal-sized square sections. Each square section must have the highest side length that is a power of 2. How many square sections will there be in total?", "ideal": "1250"}, {"prompt": "If the number of people who had the flu is given by the function f(t) = t^2 - t, where t is the number of days, and hospitals will be overrun when there are 20 people with the flu, at what day will the hospitals be overrun?", "ideal": "5"}, {"prompt": "A pharaoh has ordered the construction of a pyramid with a square base, and a height coincidentally the same as the total area of the base. The base will be made of 25 square blocks that will fit perfectly together with no gaps, each with a side length of 2 metres. What is the volume of the pyramid?", "ideal": "10000/3"}], "columns": [{"key": "prompt", "header": "Prompt"}, {"key": "ideal", "header": "Ideal"}]}, "position": {"x": -16, "y": 160}, "selected": false, "positionAbsolute": {"x": -16, "y": 160}, "dragging": false}], "edges": [{"source": "prompt-multistep-word-problems", "sourceHandle": "prompt", "target": "eval-multistep-word-problems", "targetHandle": "responseBatch", "interactionWidth": 100, "markerEnd": {"type": "arrow", "width": "22px", "height": "22px"}, "id": "reactflow__edge-prompt-1686756357355prompt-eval-1686756357355responseBatch"}, {"source": "prompt-multistep-word-problems", "sourceHandle": "prompt", "target": "inspect-multistep-word-problems", "targetHandle": "input", "interactionWidth": 100, "markerEnd": {"type": "arrow", "width": "22px", "height": "22px"}, "id": "reactflow__edge-prompt-1686756357355prompt-inspect-1686756357355input"}, {"source": "eval-multistep-word-problems", "sourceHandle": "output", "target": "vis-multistep-word-problems", "targetHandle": "input", "interactionWidth": 100, "markerEnd": {"type": "arrow", "width": "22px", "height": "22px"}, "id": "reactflow__edge-eval-1686756357355output-vis-1686756357355input"}, {"source": "table-multistep-word-problems", "sourceHandle": "Prompt", "target": "prompt-multistep-word-problems", "targetHandle": "prompt", "interactionWidth": 100, "markerEnd": {"type": "arrow", "width": "22px", "height": "22px"}, "id": "reactflow__edge-table-1686756385002Prompt-prompt-1686756357355prompt"}], "viewport": {"x": 144, "y": 37, "zoom": 1}}, "cache": {"eval-1686756357355.json": {}, "inspect-1686756357355.json": {}, "prompt-1686756357355.json": {}, "table-1686756385002.json": {}, "vis-1686756357355.json": {}}}