doc dict | metric dict | model_response dict |
|---|---|---|
{
"choices": [
" Jared types at 52 WPM and increases it by 5 WPM, 52 + 5 = <<52+5=57>>57 WPM.\nHis average over all his measured words-per-minute is 47 + 52 + 57 = <<47+52+57=156>>156.\nHis total is 156 / 3 typing speeds = <<156/3=52>>52 WPM as Jared's average typing speed.\n#### 52"
],
"fewshot_samples": [],... | {
"extractive_match": 0
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
{
"choices": [
" Jordan has 2 children, each requiring 5 diaper changes per day, for a total of 5*2=<<2*5=10>>10 diaper changes per day.\nJordan's wife changes half of the diapers, leaving Jordan to change the other half, for a total of 10/2=<<10/2=5>>5 diaper changes per day that Jordan is responsible for.\n####... | {
"extractive_match": 1
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
{
"choices": [
" The boxes can weigh up to 5000 pounds - 3755 pounds = <<5000-3755=1245>>1245 pounds in total.\nThere can be 1245 / 15 = <<1245/15=83>>83 boxes loaded onto the truck without exceeding the bridge's weight limit.\n#### 83"
],
"fewshot_samples": [],
"fewshot_sorting_class": null,
"generation_... | {
"extractive_match": 1
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
{
"choices": [
" If Tim uses 3 blue shoeboxes, he remains with 7-3=<<7-3=4>>4 blue shoe boxes in the box.\nTim also uses 1/3 of the red shoeboxes, a total of 1/3*9=<<1/3*9=3>>3 red shoe boxes.\nTim remains with 9-3=<<9-3=6>>6 red shoeboxes.\nThe total number of red and blue shoe boxes left in Tim's box is 6+4=<<6... | {
"extractive_match": 1
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
{
"choices": [
" If the number of helmets was 20, there were 2 footballs/helmet * 20 helmets = <<20*2=40>>40 footballs\nThere were half as many robots as helmets, so in total, there were 1 robot/2 helmets * 20 helmets = <<1/2*20=10>>10 robots.\nThe total number of items in the changing room is 10 robots + 40 foot... | {
"extractive_match": 1
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
{
"choices": [
" There are 4 x 18 = <<4*18=72>>72 seats in the school auditorium.\n72 x1/4 = <<72*1/4=18>>18 seats were occupied by the administrators.\nThere were 72 - 18 = <<72-18=54>>54 seats not occupied by the administrators.\n54 x 1/3 = <<54*1/3=18>>18 seats were occupied by the parents.\nSo, 54 - 18 = <<54... | {
"extractive_match": 1
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
{
"choices": [
" The dogs have 5 dogs * 4 legs/dog = <<5*4=20>>20 legs.\nThe cats have 2 cats * 4 legs/cat = <<2*4=8>>8 legs.\nThe birds have 10 birds * 2 legs/bird = <<10*2=20>>20 legs.\nThe pets have 20 legs + 8 legs + 20 legs = <<20+8+20=48>>48 legs.\n#### 48"
],
"fewshot_samples": [],
"fewshot_sorting_c... | {
"extractive_match": 1
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
{
"choices": [
" At half the speed, the car in the slow lane travels at a speed of 1/2*60 = <<1/2*60=30>>30 miles per hour.\nTo travel 480 miles, the car in the slow lane traveling at 30 miles per hour will take 480/30 = <<480/30=16>>16 hours\n#### 16"
],
"fewshot_samples": [],
"fewshot_sorting_class": null... | {
"extractive_match": 1
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
{
"choices": [
" The price of the two clothing items totals 35 + 25 = <<35+25=60>>60 dollars before discount.\nThe total sale discount comes to 60 * 0.3 = <<60*0.3=18>>18 dollars.\nThe final sale price comes to 60 - 18 = <<60-18=42>>42 dollars.\nJoe ends up with 50 - 42 = <<50-42=8>>8 dollars change.\n#### 8"
]... | {
"extractive_match": 0
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
{
"choices": [
" He drank 8*2=<<8*2=16>>16 ounces of milk\nSo he drank 16*3=<<16*3=48>>48 calories of milk\n#### 48"
],
"fewshot_samples": [],
"fewshot_sorting_class": null,
"generation_grammar": null,
"generation_size": 256,
"gold_index": 0,
"id": "400",
"images": null,
"instruction": null,
"... | {
"extractive_match": 1
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
{
"choices": [
" Johnny invested twenty and ten dollars for a total of 20+10=<<20+10=30>>30 dollars invested\nJohnny tripled this amount of money over the year, for a total of 30*=90 dollars\n#### 90"
],
"fewshot_samples": [],
"fewshot_sorting_class": null,
"generation_grammar": null,
"generation_size":... | {
"extractive_match": 1
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
{
"choices": [
" It was 3 inches tall after the first week.\nAfter the second week, it was 2 * 3 inches = <<2*3=6>>6 inches tall.\nAfter the third week, it was 6 inches + 4 inches = <<6+4=10>>10 inches tall.\n#### 10"
],
"fewshot_samples": [],
"fewshot_sorting_class": null,
"generation_grammar": null,
"... | {
"extractive_match": 1
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
{
"choices": [
" Christina had 30 - 12 - 8 = <<30-12-8=10>>10 neutral days in the month.\nAfter the first three 8-day periods, she had 30 - 8 * 3 = 30 - 24 = <<30-8*3=6>>6 days of moods left.\nOf those days, 12 - 8 = <<12-8=4>>4 days were good.\nAfter the next 3 days with 2 good days, Christina had 4 - 2 = <<4-2=... | {
"extractive_match": 0
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
{
"choices": [
" Valerie's brother earns 2 * $5000 = $<<2*5000=10000>>10000\nTheir combined salary is $5000+$10000 = $<<5000+10000=15000>>15000\nTheir mother earn twice their combined earnings, which is 2*$15000 = $<<2*15000=30000>>30000\nThe total amount of money they all have is $15000+$30000 = $<<15000+30000=4... | {
"extractive_match": 1
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
{
"choices": [
" The tip that Ashley wants to give amounts to $15 x 1/5 = $<<15*1/5=3>>3.\nHence, she will give a total of $15 + $3 = $<<15+3=18>>18 to the delivery man.\n#### 18"
],
"fewshot_samples": [],
"fewshot_sorting_class": null,
"generation_grammar": null,
"generation_size": 256,
"gold_index":... | {
"extractive_match": 1
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
{
"choices": [
" First find the number of petunias Andy plants: 90 flowers - 40 = <<90-40=50>>50 flowers\nThen add the number of each kind of flower he plants to find the total number: 50 flowers + 90 flowers = <<50+90=140>>140 flowers\n#### 140"
],
"fewshot_samples": [],
"fewshot_sorting_class": null,
"g... | {
"extractive_match": 1
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
{
"choices": [
" He swam 20*.6=<<20*.6=12>>12 miles.\nThat took him 12/2=<<12/2=6>>6 hours.\nSo he rested 6/2=<<6/2=3>>3 hours.\nHe then swam the remaining 20-12=<<20-12=8>>8 miles.\nHis pace was 2/2=<<2/2=1>>1 mph.\nSo it took him 8/1=<<8/1=8>>8 hours.\nSo in total, he took 6+3+8=<<6+3+8=17>>17 hours.\n#### 17"
... | {
"extractive_match": 1
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
{
"choices": [
" Joan is 20 + 5 = <<20+5=25>>25 years old.\nMary is 25 – 2 = <<25-2=23>>23 years old.\nTherefore, the sum of their ages is 20 + 25 + 23 = <<20+25+23=68>>68.\n#### 68"
],
"fewshot_samples": [],
"fewshot_sorting_class": null,
"generation_grammar": null,
"generation_size": 256,
"gold_inde... | {
"extractive_match": 1
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
{
"choices": [
" He chews 4 pieces of gum a day so over 30 days he will chew 4*30 = <<4*30=120>>120 pieces of gum\nEach pack of gum holds 15 pieces and he needs 120 pieces for the month so he will need 120/15 = <<120/15=8>>8 packs of gum\n#### 8"
],
"fewshot_samples": [],
"fewshot_sorting_class": null,
"g... | {
"extractive_match": 1
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
{
"choices": [
" Jean has 30 - 2 = <<30-2=28>>28 lollipops\nJean can fill up 28 / 2 = <<28/2=14>>14 bags with lollipops\n#### 14"
],
"fewshot_samples": [],
"fewshot_sorting_class": null,
"generation_grammar": null,
"generation_size": 256,
"gold_index": 0,
"id": "55",
"images": null,
"instruction... | {
"extractive_match": 1
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
{
"choices": [
" She has 12 hours for her activities because 7 + 5 = <<7+5=12>>12\nAfter reading, she has 9 hours left because 12 - 3 = <<12-3=9>>9\nShe spends 3 hours playing video games because 9 x (1/3) = <<9*(1/3)=3>>3\nAfter video games she has 6 hours left for soccer because 9 - 3 = <<6=6>>6\nThe proportion... | {
"extractive_match": 0
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
{
"choices": [
" If there were 80 Japanese, the number of Chinese was 240-80=<<240-80=160>>160.\nSince there were 60 boys in the Chinese team, there were 160-60 = 100 girls in the Chinese team.\n#### 100"
],
"fewshot_samples": [],
"fewshot_sorting_class": null,
"generation_grammar": null,
"generation_si... | {
"extractive_match": 1
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
{
"choices": [
" If he purchases jewelry, he will make a profit of 2.5% which is $5000*(2.5/100) = $<<5000*(2.5/100)=125>>125\nIf he purchases electronic gadgets, he will make a profit of 1.2% which is $8000*(1.2/100) = $<<8000*(1.2/100)=96>>96\nIf he wants to maximize profit, since $125 > $96, he will choose to ... | {
"extractive_match": 0
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
{
"choices": [
" Each school has sent 1 girls’ basketball team + 1 boys’ basketball team = <<1+1=2>>2 teams.\nSo each school has sent 2 teams * 5 players per team = <<2*5=10>>10 players.\nThey have also each sent 2 teams * 1 coach per team = <<2*1=2>>2 coaches.\nIn total, each school has sent 10 players + 2 coach... | {
"extractive_match": 0
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
{
"choices": [
" The hotel room is 1500*.2=$<<1500*.2=300>>300 more expensive per night than normal\nSo they paid 1500+300=$<<1500+300=1800>>1800 per night\nThat means she paid 1800*3=$<<1800*3=5400>>5400\nThe plane tickets cost 5000*2=$<<5000*2=10000>>10,000\nSo the total cost is 10,000+5400=$<<10000+5400=15400>... | {
"extractive_match": 1
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
{
"choices": [
" He rents his car 10*3=<<10*3=30>>30 hour a month\nSo he makes 25*30=$<<25*30=750>>750 a month\nThat means he has a profit of 750-500=$<<750-500=250>>250 a month\n#### 250"
],
"fewshot_samples": [],
"fewshot_sorting_class": null,
"generation_grammar": null,
"generation_size": 256,
"gol... | {
"extractive_match": 1
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
{
"choices": [
" In the first group of workers, each produces 6 toys * 10 hours = <<6*10=60>>60 toys over their shift.\nThis is a total of 60 toys * 2 workers = <<60*2=120>>120 toys.\nIn the second group of workers, each produces 4 toys * 10 hours = <<4*10=40>>40 toys over their shift.\nThis is a total of 40 toys... | {
"extractive_match": 0
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
{
"choices": [
" The number of female porcupines in the park is 3/5*50 = <<3/5*50=30>>30.\nIn a month, the 30 female porcupines give birth to 30*4 = <<30*4=120>>120 new babies.\nAfter a year, with 12 months, the total number of new porcupines in the park is 120*12 = <<120*12=1440>>1440\nThe total population of po... | {
"extractive_match": 0
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
{
"choices": [
" Jasper has 4/2= <<4/2=2>>2 tubes of blue paint\nJasper has 3*3=<<3*3=9>>9 tubes of yellow paint\nJasper has a total of 2+9 =<<2+9=11>>11 tubes of paint\n#### 11"
],
"fewshot_samples": [],
"fewshot_sorting_class": null,
"generation_grammar": null,
"generation_size": 256,
"gold_index": ... | {
"extractive_match": 1
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
{
"choices": [
" The monthly interest is $100 x 2/100 = $<<100*2/100=2>>2.\nAfter 3 months, the total interest amount to $2 x 3 = $<<2*3=6>>6.\nTherefore, Mandy should give Benedict a total of $100 + $6 = $<<100+6=106>>106.\n#### 106"
],
"fewshot_samples": [],
"fewshot_sorting_class": null,
"generation_gr... | {
"extractive_match": 1
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
{
"choices": [
" The first scene has twice the number of lines as his solo song, so it has 2 * 54 = <<2*54=108>>108 lines.\nA third of them are Sean’s lines, so he has to memorize 108 / 3 = <<108/3=36>>36 lines.\nThe second scene has 54 + 6 = <<54+6=60>>60 lines.\nFour fifths of the second scene’s lines are Sean’... | {
"extractive_match": 1
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
{
"choices": [
" There will be 30 kids and he wants each kid to have 4 servings so that's 30*4 = <<30*4=120>>120 jello cups\n1 box of jello makes 10 jello cups and he needs to make 120 jello cups so he needs 120/10 = <<120/10=12>>12 boxes of jello\nEach box of jello is $1.25 and he needs 12 boxes so he will spend... | {
"extractive_match": 1
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
{
"choices": [
" Josh can eat 2 x 2 = <<2*2=4>>4 slices a day.\nTogether, Abby and Josh can eat 2 + 4 = <<2+4=6>>6 slices a day.\nSo, a loaf of bread will last for 24/6 = <<24/6=4>>4 days.\n#### 4"
],
"fewshot_samples": [],
"fewshot_sorting_class": null,
"generation_grammar": null,
"generation_size": 25... | {
"extractive_match": 1
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
{
"choices": [
" 5 degrees an hour for 10 hours 5*10=<<5*10=50>>50 degrees\nthe pyramid is 32 degrees from the ground so 32+50=<<32+50=82>>82 degrees\n#### 82"
],
"fewshot_samples": [],
"fewshot_sorting_class": null,
"generation_grammar": null,
"generation_size": 256,
"gold_index": 0,
"id": "562",
... | {
"extractive_match": 0
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
{
"choices": [
" He walked 4/2=<<4/2=2>>2 miles there before turning around\nSo in total he walked 2+2+4=<<2+2+4=8>>8 miles, he walked 2 miles to the halfway point than 2 miles home.\nThat means it took him 8/4=<<8/4=2>>2 hours\n#### 2"
],
"fewshot_samples": [],
"fewshot_sorting_class": null,
"generation_... | {
"extractive_match": 0
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
{
"choices": [
" If Sally Thirtytwo is 8 years old, same as Sally four, their total age 8+8 = <<8+8=16>>16 years.\nGranny red is two times as old as Sally four, meaning Granny red is 2*8 = <<2*8=16>>16 years old.\nSally Thirtytwo, Sally four, and Sally red are 16+16 = <<32=32>>32 years old.\nSally two is three ye... | {
"extractive_match": 1
} | {
"argmax_logits_eq_gold": [],
"input": "<|im_start|>system\n## Metadata\n\nKnowledge Cutoff Date: June 2025\nToday Date: 24 October 2025\nReasoning Mode: /think\n\n## Custom Instructions\n\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face. Your role as an assistant involves thoroughly exploring... |
End of preview. Expand in Data Studio
Dataset Card for Evaluation run of SmolLM3-SFT-GSM8K
Dataset automatically created during the evaluation run of model SmolLM3-SFT-GSM8K.
The dataset is composed of 1 configuration, each one corresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An additional configuration "results" store all the aggregated results of the run.
To load the details from a run, you can for instance do the following:
from datasets import load_dataset
data = load_dataset("simon-artzet/details_SmolLM3-SFT-GSM8K_private",
"results",
split="train")
Latest results
These are the latest results from run 2025-10-24T14:29:02.418397(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the "latest" split for each eval):
{
"all": {
"extractive_match": 0.6876421531463229,
"extractive_match_stderr": 0.012765850404191413
},
"lighteval|gsm8k|0": {
"extractive_match": 0.6876421531463229,
"extractive_match_stderr": 0.012765850404191413
}
}
Dataset Details
Dataset Description
- Curated by: [More Information Needed]
- Funded by [optional]: [More Information Needed]
- Shared by [optional]: [More Information Needed]
- Language(s) (NLP): [More Information Needed]
- License: [More Information Needed]
Dataset Sources [optional]
- Repository: [More Information Needed]
- Paper [optional]: [More Information Needed]
- Demo [optional]: [More Information Needed]
Uses
Direct Use
[More Information Needed]
Out-of-Scope Use
[More Information Needed]
Dataset Structure
[More Information Needed]
Dataset Creation
Curation Rationale
[More Information Needed]
Source Data
Data Collection and Processing
[More Information Needed]
Who are the source data producers?
[More Information Needed]
Annotations [optional]
Annotation process
[More Information Needed]
Who are the annotators?
[More Information Needed]
Personal and Sensitive Information
[More Information Needed]
Bias, Risks, and Limitations
[More Information Needed]
Recommendations
Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.
Citation [optional]
BibTeX:
[More Information Needed]
APA:
[More Information Needed]
Glossary [optional]
[More Information Needed]
More Information [optional]
[More Information Needed]
Dataset Card Authors [optional]
[More Information Needed]
Dataset Card Contact
[More Information Needed]
- Downloads last month
- 5