Dataset Viewer
Auto-converted to Parquet Duplicate
index
int64
0
29
words
listlengths
7
7
acronym
stringlengths
7
7
prompt
listlengths
2
2
task_source
stringclasses
1 value
model_responses__example_annotation
listlengths
8
8
model_responses__example_annotation__finish_reason_length_flags
listlengths
8
8
model_responses__example_annotation__length_partial_responses
listlengths
8
8
prompt__example_annotation__metadata
dict
model_responses__example_annotation__metadata
dict
model_responses__example_annotation__eval_is_correct
listlengths
8
8
model_responses__example_annotation__eval_extracted_answers
listlengths
8
8
model_responses__example_annotation__eval_extraction_metadata
listlengths
8
8
model_responses__example_annotation__eval_evaluation_metadata
listlengths
8
8
model_responses__example_annotation__internal_answers__eval_is_correct
listlengths
8
8
model_responses__example_annotation__internal_answers__eval_extracted_answers
listlengths
8
8
model_responses__example_annotation__internal_answers__eval_extraction_metadata
listlengths
8
8
model_responses__example_annotation__internal_answers__eval_evaluation_metadata
listlengths
8
8
model_responses__example_annotation__metrics
dict
0
[ "tpke", "giddying", "cassock", "overcall", "altamira", "confounds", "kinsfolk" ]
kgsvlck
[ { "content": "You like to solve problems by thinking step by step. Write out your reasoning then give your answer in \"<answer>\n(your answer)\n</answer>\". You always end with </answer>, you never ever end without giving an answer.", "role": "system" }, { "content": "Answer the following problem. E...
acronym
[ "<think>\n<sample>\nTo construct an acronym from the given list of words while satisfying all the requirements, we need to follow these steps:\n\n1. **Identify the Words**: The list of words is ['tpke', 'giddying', 'cassock', 'overcall', 'altamira', 'confounds', 'kinsfolk'].\n2. **Determine the Acronym Length**: We...
[ false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "" ]
{ "api_url": "http://127.0.0.1:56413", "backend": "litellm", "chat_template_applied": true, "generation_params": { "chat_template_applied": true, "max_tokens": 4096, "n": 3, "repetition_penalty": 1.1, "temperature": 0.7, "top_k": 20, "top_p": 0.8 }, "model_name": "hosted_vllm/TAU...
{ "backend": "litellm", "model_name": "hosted_vllm/TAUR-dev/M-SFT_V2_RUN-rl", "n_responses": 8 }
[ false, false, false, false, false, false, false, false ]
[ "</>\n\n\n</\n<answer>\n>\n<answer>\n>\n<", null, null, "(g\n\n<span>\n</span>\n<answer>\n \nif in", null, "tgc", null, "(the answer) see" ]
[ { "extraction_type": "final", "non_overlapping_spans": 3, "original_span": "</>\n\n\n</\n<answer>\n>\n<answer>\n>\n<", "span_end": 1647, "span_start": 1612, "total_spans_found": 3 }, { "extraction_type": "final", "non_overlapping_spans": null, "original_span": null, "span...
[ { "correct_answer": null, "evaluation_method": "acronym_simple", "extracted_answer": "</>\n\n\n</\n<answer>\n>\n<answer>\n>\n<", "extraction_result": null, "reason": "no_metadata_available" }, { "correct_answer": null, "evaluation_method": "response_processor", "extracted_answer"...
[ [ false, false, false ], [], [], [ false, false, false, false ], [], [ false ], [], [ false, false, false, false, false ] ]
[ [ "tje the the the of the on the the the the the the the the the the the the the the of the the o the the the the the the the of the of of of the of the of the o of the of of of of n. <\n\n <answer>\n (tp</answer\n</(answer>\n\ntpve\nacronym\ntp \ntp\n\n<><the\nof\ntp\n\n<>(tp\nanswer\n<answer>\n(tpkokes\ntp\...
[ [ { "confidence": 1, "extraction_type": "internal", "original_span": "tje the the the of the on the the the the the the the the the the the the the the of the the o the the the the the the the of the of of of the of the of the o of the of of of of n. <\n\n <answer>\n (tp</answer\n</(answer>\n...
[ [ { "correct_answer": null, "evaluation_method": "acronym_simple", "extracted_answer": "tje the the the of the on the the the the the the the the the the the the the the of the the o the the the the the the the of the of of of the of the of the o of the of of of of n. <\n\n <answer>\n (tp</an...
{ "flips_by": [ 0, 0, 0, 0, 0, 0, 0, 0 ], "flips_total": 0, "num_correct": 0, "pass_at_n": 0, "percent_correct": 0, "skill_count": { "answer_revision": [ 0, 0, 0, 0, 0, 0, 0, 0 ], "best_of_n": [ 0, 0, ...
1
[ "emotionality", "directeur", "stephanion", "hurtful", "pendulum", "considerably", "nother" ]
ederent
[{"content":"You like to solve problems by thinking step by step. Write out your reasoning then give(...TRUNCATED)
acronym
["<think>\n<sample>\nTo construct an acronym based on the given criteria, we need to follow these st(...TRUNCATED)
[ false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "" ]
{"api_url":"http://127.0.0.1:56413","backend":"litellm","chat_template_applied":true,"generation_par(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/TAUR-dev/M-SFT_V2_RUN-rl", "n_responses": 8 }
[ false, false, false, false, false, false, false, false ]
["a>\n</ine the\n</\nword\n</answer the > <answer >\n the now the answer in this format here the the(...TRUNCATED)
[{"extraction_type":"final","non_overlapping_spans":2,"original_span":"a>\n</ine the\n</\nword\n</an(...TRUNCATED)
[{"correct_answer":null,"evaluation_method":"acronym_simple","extracted_answer":"a>\n</ine the\n</\n(...TRUNCATED)
[ [ false, false ], [], [], [], [], [ false ], [ false, false ], [] ]
[["</ in the answer</</ the the next</ the","a>\n</ine the\n</\nword\n</answer the > <answer >\n the(...TRUNCATED)
[[{"confidence":1.0,"extraction_type":"internal","original_span":"</ in the answer</</ the the next<(...TRUNCATED)
[[{"correct_answer":null,"evaluation_method":"acronym_simple","extracted_answer":"</ in the answer</(...TRUNCATED)
{"flips_by":[0,0,0,0,0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"s(...TRUNCATED)
2
[ "underscript", "extrasterile", "beslime", "emotionist", "soloth", "alsike", "event" ]
nteelae
[{"content":"You like to solve problems by thinking step by step. Write out your reasoning then give(...TRUNCATED)
acronym
["<think>\n<sample>\nTo construct an acronym based on the given criteria, we need to follow these st(...TRUNCATED)
[ false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "" ]
{"api_url":"http://127.0.0.1:56413","backend":"litellm","chat_template_applied":true,"generation_par(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/TAUR-dev/M-SFT_V2_RUN-rl", "n_responses": 8 }
[ false, false, false, false, false, false, false, false ]
[null,null,null,null,null,"Aswer??? am. is. . \n</ as the is an then. in the. >. \n</</answer\n \n(...TRUNCATED)
[{"extraction_type":"final","non_overlapping_spans":null,"original_span":null,"span_end":null,"span_(...TRUNCATED)
[{"correct_answer":null,"evaluation_method":"response_processor","extracted_answer":null,"extraction(...TRUNCATED)
[ [], [], [], [], [], [ false ], [ false ], [] ]
[[],[],[],[],[],["Aswer??? am. is. . \n</ as the is an then. in the. >. \n</</answer\n \n is\n\n t(...TRUNCATED)
[[],[],[],[],[],[{"confidence":1.0,"extraction_type":"internal","original_span":"Aswer??? am. is. . (...TRUNCATED)
[[],[],[],[],[],[{"correct_answer":null,"evaluation_method":"acronym_simple","extracted_answer":"Asw(...TRUNCATED)
{"flips_by":[0,0,0,0,0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"s(...TRUNCATED)
3
[ "pasmo", "residual", "trochius", "scats", "yird", "cateye", "noneugenical" ]
psrcico
[{"content":"You like to solve problems by thinking step by step. Write out your reasoning then give(...TRUNCATED)
acronym
["<think>\n<sample>\nTo construct an acronym from the given list of words while satisfying all the r(...TRUNCATED)
[ false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "" ]
{"api_url":"http://127.0.0.1:56413","backend":"litellm","chat_template_applied":true,"generation_par(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/TAUR-dev/M-SFT_V2_RUN-rl", "n_responses": 8 }
[ false, false, false, false, false, false, false, false ]
[null,null,null,null,"> the </>]\n</\n></<study=> study see \n=> \n\n >< study/",null,"United Stat(...TRUNCATED)
[{"extraction_type":"final","non_overlapping_spans":null,"original_span":null,"span_end":null,"span_(...TRUNCATED)
[{"correct_answer":null,"evaluation_method":"response_processor","extracted_answer":null,"extraction(...TRUNCATED)
[[],[],[],[],[false,false,false],[],[false,false,false,false,false,false],[false,false,false,false,f(...TRUNCATED)
[[],[],[],[],["<delay>","</<answer/> \n</answer\n. \n</answer\n</ \n</ \n \n</answer\n \n</ an(...TRUNCATED)
[[],[],[],[],[{"confidence":1.0,"extraction_type":"internal","original_span":"<delay>","pattern_used(...TRUNCATED)
[[],[],[],[],[{"correct_answer":null,"evaluation_method":"acronym_simple","extracted_answer":"<delay(...TRUNCATED)
{"flips_by":[0,0,0,0,0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"s(...TRUNCATED)
4
[ "cutters", "caseum", "pachycholia", "vorticellum", "albiflorous", "reflectorize", "hypothecater" ]
ccpvaeh
[{"content":"You like to solve problems by thinking step by step. Write out your reasoning then give(...TRUNCATED)
acronym
["<think>\n<sample>\nTo construct an acronym from the given list of words while satisfying all the r(...TRUNCATED)
[ false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "" ]
{"api_url":"http://127.0.0.1:56413","backend":"litellm","chat_template_applied":true,"generation_par(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/TAUR-dev/M-SFT_V2_RUN-rl", "n_responses": 8 }
[ false, false, false, false, false, false, false, false ]
["</sample>\nIn</\n\n here the","constructed… </answer < answer the… the. </answer give</ answer(...TRUNCATED)
[{"extraction_type":"final","non_overlapping_spans":1,"original_span":"</sample>\nIn</\n\n here the"(...TRUNCATED)
[{"correct_answer":null,"evaluation_method":"acronym_simple","extracted_answer":"</sample>\nIn</\n\n(...TRUNCATED)
[[false],[false,false,false,false,false,false,false],[false],[false],[false],[false,false,false,fals(...TRUNCATED)
[["</sample>\nIn</\n\n here the"],["</reason","I'll do it.","Ithink","I'll do them.\nV.\nthink about(...TRUNCATED)
[[{"confidence":1.0,"extraction_type":"internal","original_span":"</sample>\nIn</\n\n here the","pat(...TRUNCATED)
[[{"correct_answer":null,"evaluation_method":"acronym_simple","extracted_answer":"</sample>\nIn</\n\(...TRUNCATED)
{"flips_by":[0,0,0,0,0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"s(...TRUNCATED)
5
[ "impanated", "sprayful", "nondeformed", "phorone", "fleckering", "plutarchic", "casate" ]
psohfps
[{"content":"You like to solve problems by thinking step by step. Write out your reasoning then give(...TRUNCATED)
acronym
["<think\n(letweuser\n </ answer:\n\n let ( this? 0\n our list ( ( answer> we </answer (...TRUNCATED)
[ false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "" ]
{"api_url":"http://127.0.0.1:56413","backend":"litellm","chat_template_applied":true,"generation_par(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/TAUR-dev/M-SFT_V2_RUN-rl", "n_responses": 8 }
[ false, false, false, false, false, false, false, false ]
["answer<<answer<answer< answer\n\n<< answer< answer<< answer<<< answer<answer< answer< answer< answ(...TRUNCATED)
[{"extraction_type":"final","non_overlapping_spans":8,"original_span":"answer<<answer<answer< answer(...TRUNCATED)
[{"correct_answer":null,"evaluation_method":"acronym_simple","extracted_answer":"answer<<answer<answ(...TRUNCATED)
[[false,false,false,false,false,false,false,false],[false,false,false,false],[],[],[false],[],[false(...TRUNCATED)
[["in this process , </answer\n gives\n\n\n </ answer\n\n . in \n< answer> < as in\n. \n(se\n (...TRUNCATED)
[[{"confidence":1.0,"extraction_type":"internal","original_span":"in this process , </answer\n gives(...TRUNCATED)
[[{"correct_answer":null,"evaluation_method":"acronym_simple","extracted_answer":"in this process , (...TRUNCATED)
{"flips_by":[0,0,0,0,0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"s(...TRUNCATED)
6
[ "zymogen", "mitigation", "kamikazes", "acron", "amydon", "semiputrid", "unfrozen" ]
yimamen
[{"content":"You like to solve problems by thinking step by step. Write out your reasoning then give(...TRUNCATED)
acronym
["<th> acman? >\n- (??\n... \n<answer \nthe the. // \nThe otherwise your\n. \n reorderwords. you(...TRUNCATED)
[ false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "" ]
{"api_url":"http://127.0.0.1:56413","backend":"litellm","chat_template_applied":true,"generation_par(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/TAUR-dev/M-SFT_V2_RUN-rl", "n_responses": 8 }
[ false, false, false, false, false, false, false, false ]
["y'm.,. \nthen\n</ answer\nthe.\n<//to. you. in. you\n\n<answer\n.\n \nthat.\n<answer>","(ay).",nu(...TRUNCATED)
[{"extraction_type":"final","non_overlapping_spans":1,"original_span":"y'm.,. \nthen\n</ answer\nth(...TRUNCATED)
[{"correct_answer":null,"evaluation_method":"acronym_simple","extracted_answer":"y'm.,. \nthen\n</ (...TRUNCATED)
[ [ false ], [ false, false ], [], [], [ false ], [ false ], [ false, false, false ], [] ]
[["y'm.,. \nthen\n</ answer\nthe.\n<//to. you. in. you\n\n<answer\n.\n \nthat.\n<answer>"],["<answe(...TRUNCATED)
[[{"confidence":1.0,"extraction_type":"internal","original_span":"y'm.,. \nthen\n</ answer\nthe.\n<(...TRUNCATED)
[[{"correct_answer":null,"evaluation_method":"acronym_simple","extracted_answer":"y'm.,. \nthen\n</(...TRUNCATED)
{"flips_by":[0,0,0,0,0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"s(...TRUNCATED)
7
[ "skiagrams", "manifoldly", "sidecars", "azotes", "contendere", "raid", "dewworm" ]
knizoid
[{"content":"You like to solve problems by thinking step by step. Write out your reasoning then give(...TRUNCATED)
acronym
["<think>\nreason\nthe any you...\nwho another...>\n<answer> skiems </... \n<answer> skiats.</</answ(...TRUNCATED)
[ false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "" ]
{"api_url":"http://127.0.0.1:56413","backend":"litellm","chat_template_applied":true,"generation_par(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/TAUR-dev/M-SFT_V2_RUN-rl", "n_responses": 8 }
[ false, false, false, false, false, false, false, false ]
[ "skiems </... \n<answer> skiats.</", null, null, null, null, "</ answer>", null, null ]
[{"extraction_type":"final","non_overlapping_spans":1,"original_span":"skiems </... \n<answer> skiat(...TRUNCATED)
[{"correct_answer":null,"evaluation_method":"acronym_simple","extracted_answer":"skiems </... \n<ans(...TRUNCATED)
[ [ false ], [], [], [], [], [ false, false ], [], [] ]
[["skiems </... \n<answer> skiats.</"],[],[],[],[],["</&\n] #<answer\nsth, ]< answer\n, # # # # # # (...TRUNCATED)
[[{"confidence":1.0,"extraction_type":"internal","original_span":"skiems </... \n<answer> skiats.</"(...TRUNCATED)
[[{"correct_answer":null,"evaluation_method":"acronym_simple","extracted_answer":"skiems </... \n<an(...TRUNCATED)
{"flips_by":[0,0,0,0,0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"s(...TRUNCATED)
8
[ "jacksmelt", "aediles", "distender", "preovulatory", "gussies", "latticinii", "bootblacks" ]
aadputo
[{"content":"You like to solve problems by thinking step by step. Write out your reasoning then give(...TRUNCATED)
acronym
["<think</Leteverstep\n\npass meanwhile, let usbe go the!\n\nlet}give on\n\n by a\n\n :\n\n<answe(...TRUNCATED)
[ false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "" ]
{"api_url":"http://127.0.0.1:56413","backend":"litellm","chat_template_applied":true,"generation_par(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/TAUR-dev/M-SFT_V2_RUN-rl", "n_responses": 8 }
[ false, false, false, false, false, false, false, false ]
[null,"</\n answer>\n (... they\n \n're\n<answer>\nto>\n( your\n>\n(we're\n)[/](answer\n\n]\n(answer(...TRUNCATED)
[{"extraction_type":"final","non_overlapping_spans":null,"original_span":null,"span_end":null,"span_(...TRUNCATED)
[{"correct_answer":null,"evaluation_method":"response_processor","extracted_answer":null,"extraction(...TRUNCATED)
[ [], [ false, false, false ], [], [ false, false ], [], [], [], [] ]
[[],[">\n<answer>\"xam\">\nanswer>\n<answer>\nthe\nine\n\n>\n < (answer>\n\n</ non\n our t>\n<answer(...TRUNCATED)
[[],[{"confidence":1.0,"extraction_type":"internal","original_span":">\n<answer>\"xam\">\nanswer>\n<(...TRUNCATED)
[[],[{"correct_answer":null,"evaluation_method":"acronym_simple","extracted_answer":">\n<answer>\"xa(...TRUNCATED)
{"flips_by":[0,0,0,0,0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"s(...TRUNCATED)
9
[ "brocade", "lightwort", "upstruggle", "tortrixes", "philadelphus", "tim", "uptrill" ]
rgsrpiu
[{"content":"You like to solve problems by thinking step by step. Write out your reasoning then give(...TRUNCATED)
acronym
["<th>\n<accumulator>\nFirst\n\n\n the. let me\n\n\n.","<think\nupstr\nletste\n\n<answer>\n \n\n Thi(...TRUNCATED)
[ false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "" ]
{"api_url":"http://127.0.0.1:56413","backend":"litellm","chat_template_applied":true,"generation_par(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/TAUR-dev/M-SFT_V2_RUN-rl", "n_responses": 8 }
[ false, false, false, false, false, false, false, false ]
[null,"</ let\n< the\n</ they\n</\n</\nthe\n</ answer\n\n\n</\nanswer>\n</\n let\n> . answer\nthat\n(...TRUNCATED)
[{"extraction_type":"final","non_overlapping_spans":null,"original_span":null,"span_end":null,"span_(...TRUNCATED)
[{"correct_answer":null,"evaluation_method":"response_processor","extracted_answer":null,"extraction(...TRUNCATED)
[[],[false,false,false,false,false,false,false,false,false,false,false,false,false],[false],[],[fals(...TRUNCATED)
[[],["Think\nBrother\n'<'><'>\"'\n(...\n)</...\n...\n</...\n...\n...\n...\n...\n``'\n...\n<''\"\n(..(...TRUNCATED)
[[],[{"confidence":1.0,"extraction_type":"internal","original_span":"Think\nBrother\n'<'><'>\"'\n(..(...TRUNCATED)
[[],[{"correct_answer":null,"evaluation_method":"acronym_simple","extracted_answer":"Think\nBrother\(...TRUNCATED)
{"flips_by":[0,0,0,0,0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"s(...TRUNCATED)
End of preview. Expand in Data Studio
README.md exists but content is empty.
Downloads last month
6