Datasets:

Modalities:
Text
Formats:
parquet
Size:
< 1K
Libraries:
Datasets
pandas
Dataset Viewer
Auto-converted to Parquet Duplicate
index
int64
0
29
words
listlengths
4
4
acronym
stringlengths
4
4
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
[ "frizzle", "sabbathaic", "misaverred", "unbone" ]
fbin
[ { "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 appropriate acronym based on the given requirements, we need to follow these steps:\n\n1. **Identify possible acronyms**: We start by considering different combinations of letters from each word while ensuring they meet all the criteria.\n \n - From \"frizzle\": Possible choi...
[ false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "" ]
{ "api_url": "http://127.0.0.1:42153", "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/TAUR-dev/M-0903_rl_reflect__1b_3args__grpo_minibs32_lr1e-6_rollout16-rl", "prompt": [ { "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. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer> (your answer) </answer>.\n\n# Problem\nYou are given a list of words. Construct an acronym that satisfies the following conditions:\n\nRequirements\n1) Length: at least 4 characters and at most the number of words provided.\n2) Read the words left to right and form the acronym by selecting a subsequence of the words (you may skip words). \n - The i-th letter of the acronym must come from a word that appears after the word used for the (i-1)-th letter. \n - You may not reorder the words, and you may not take more than one letter from the same word.\n3) If you take a letter from a word, it must be that word’s 1st, 2nd, or 3rd character only.\n\nFor example, if the list of words is: ['regales', 'hyracidae', 'scorches', 'bivium', 'ejidos', 'nonignitable', 'entryman', 'villaless']\t\nWe can take the letter \"r\" from \"regales\", the letter \"i\" comes from \"bivium\", the letter \"n\" comes from \"nonignitable\", the letter \"e\" comes from \"entryman\".\nThen a valid acronym is : <answer> rine </answer> \n\nList of words: ['frizzle' 'sabbathaic' 'misaverred' 'unbone']\n\n\nLet's think step by step.", "role": "user" } ] }
{ "backend": "litellm", "model_name": "hosted_vllm/TAUR-dev/M-0903_rl_reflect__1b_3args__grpo_minibs32_lr1e-6_rollout16-rl", "n_responses": 8 }
[ false, false, false, false, false, false, false, false ]
[ "</</the\n\n<answer>\n</\n<my\n<answer>", null, null, null, null, "fs </answer</</br\n the the ac answer", "</ answer>\n\n <\n\n\n\n( Your Answer: <nothing>\n</ answer\n\n <>\nThe reasoning\n the the non < up\n j ust\n , please your in<span></ne\n</</span>\nthe (\n your\n in the</ a\n</ to the<span>\n\n...
[ { "extraction_type": "final", "non_overlapping_spans": 2, "original_span": "</</the\n\n<answer>\n</\n<my\n<answer>", "span_end": 2311, "span_start": 2276, "total_spans_found": 2 }, { "extraction_type": "final", "non_overlapping_spans": null, "original_span": null, "span_e...
[ { "correct_answer": null, "evaluation_method": "acronym_simple", "extracted_answer": "</</the\n\n<answer>\n</\n<my\n<answer>", "extraction_result": null, "reason": "no_metadata_available" }, { "correct_answer": null, "evaluation_method": "response_processor", "extracted_answer": ...
[ [ false, false ], [], [], [], [], [ false ], [ false ], [] ]
[ [ "let the\n</ the\n<think>\n><answer>\nthinker\nthe\n<think\n<sample>\nTo solve this problem, let's break down the process into manageable steps:\n\n1) ** Step by step:\n1. First, let: Let us to solve the problem. constructing a a.\nGiven a List\n<answer> the sample.\n*\n\n\nNow you\n<think>\n\n\n\nuser\n\nuse...
[ [ { "confidence": 1, "extraction_type": "internal", "original_span": "let the\n</ the\n<think>\n><answer>\nthinker\nthe\n<think\n<sample>\nTo solve this problem, let's break down the process into manageable steps:\n\n1) ** Step by step:\n1. First, let: Let us to solve the problem. constructing...
[ [ { "correct_answer": null, "evaluation_method": "acronym_simple", "extracted_answer": "let the\n</ the\n<think>\n><answer>\nthinker\nthe\n<think\n<sample>\nTo solve this problem, let's break down the process into manageable steps:\n\n1) ** Step by step:\n1. First, let: Let us to solve the pro...
{ "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, 0, 0, 0, 0, 0, 0 ], "reflect_close": [ 0, 0, 0, 0, 0, 0, 0, 0 ], "reflect_open": [ 0, 0, 0, 0, 0, 0, 1, 1 ], "reflection_sbon": [ 0, 0, 0, 0, 0, 0, 0, 0 ], "sample_close": [ 0, 0, 0, 0, 0, 0, 0, 1 ], "sample_open": [ 5, 1, 1, 1, 1, 1, 2, 1 ], "vote_close": [ 0, 0, 0, 0, 0, 0, 0, 0 ], "vote_open": [ 0, 0, 0, 0, 0, 0, 0, 0 ], "voting": [ 0, 0, 0, 0, 0, 0, 0, 0 ] }, "total_responses": 8 }
1
[ "excurvate", "voe", "carbinyl", "caretook" ]
cocc
[ { "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 appropriate acronym based on the given requirements, we need to follow these steps:\n\n1. **Identify the total number of words**: There are 4 words in the list.\n \n List of words: ['excurvate', 'voe', 'carbinyl', 'caretook']\n\n2. **Determine the minimum length required for ...
[ false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "" ]
{ "api_url": "http://127.0.0.1:42153", "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/TAUR-dev/M-0903_rl_reflect__1b_3args__grpo_minibs32_lr1e-6_rollout16-rl", "prompt": [ { "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. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer> (your answer) </answer>.\n\n# Problem\nYou are given a list of words. Construct an acronym that satisfies the following conditions:\n\nRequirements\n1) Length: at least 4 characters and at most the number of words provided.\n2) Read the words left to right and form the acronym by selecting a subsequence of the words (you may skip words). \n - The i-th letter of the acronym must come from a word that appears after the word used for the (i-1)-th letter. \n - You may not reorder the words, and you may not take more than one letter from the same word.\n3) If you take a letter from a word, it must be that word’s 1st, 2nd, or 3rd character only.\n\nFor example, if the list of words is: ['regales', 'hyracidae', 'scorches', 'bivium', 'ejidos', 'nonignitable', 'entryman', 'villaless']\t\nWe can take the letter \"r\" from \"regales\", the letter \"i\" comes from \"bivium\", the letter \"n\" comes from \"nonignitable\", the letter \"e\" comes from \"entryman\".\nThen a valid acronym is : <answer> rine </answer> \n\nList of words: ['excurvate' 'voe' 'carbinyl' 'caretook']\n\n\nLet's think step by step.", "role": "user" } ] }
{ "backend": "litellm", "model_name": "hosted_vllm/TAUR-dev/M-0903_rl_reflect__1b_3args__grpo_minibs32_lr1e-6_rollout16-rl", "n_responses": 8 }
[ false, false, false, false, false, false, false, false ]
[ "(]> answer\n the to the is used (at to give the:<perform\n<tperform\n\n<<answer to perform, as thinking/><performing to perform to check>\n(pleaseenu/>\nthe enter to perform to perform to perform to perform to meet. explain to give step by a little answer.\n answer.<toper\n<answer\n to give.><…< perform.\n<<answe...
[ { "extraction_type": "final", "non_overlapping_spans": 1, "original_span": "(]> answer\n the to the is used (at to give the:<perform\n<tperform\n\n<<answer to perform, as thinking/><performing to perform to check>\n(pleaseenu/>\nthe enter to perform to perform to perform to perform to meet. explain to ...
[ { "correct_answer": null, "evaluation_method": "acronym_simple", "extracted_answer": "(]> answer\n the to the is used (at to give the:<perform\n<tperform\n\n<<answer to perform, as thinking/><performing to perform to check>\n(pleaseenu/>\nthe enter to perform to perform to perform to perform to meet. e...
[ [ false ], [ false ], [], [], [], [], [], [ false, false, false, false ] ]
[ [ "(]> answer\n the to the is used (at to give the:<perform\n<tperform\n\n<<answer to perform, as thinking/><performing to perform to check>\n(pleaseenu/>\nthe enter to perform to perform to perform to perform to meet. explain to give step by a little answer.\n answer.<toper\n<answer\n to give.><…< perform.\n<...
[ [ { "confidence": 1, "extraction_type": "internal", "original_span": "(]> answer\n the to the is used (at to give the:<perform\n<tperform\n\n<<answer to perform, as thinking/><performing to perform to check>\n(pleaseenu/>\nthe enter to perform to perform to perform to perform to meet. explain...
[ [ { "correct_answer": null, "evaluation_method": "acronym_simple", "extracted_answer": "(]> answer\n the to the is used (at to give the:<perform\n<tperform\n\n<<answer to perform, as thinking/><performing to perform to check>\n(pleaseenu/>\nthe enter to perform to perform to perform to perfor...
{ "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, 0, 0, 0, 0, 0, 0 ], "reflect_close": [ 0, 0, 0, 0, 0, 0, 0, 0 ], "reflect_open": [ 0, 0, 0, 0, 0, 1, 0, 1 ], "reflection_sbon": [ 0, 0, 0, 0, 0, 0, 0, 0 ], "sample_close": [ 0, 0, 0, 0, 0, 1, 0, 1 ], "sample_open": [ 1, 1, 1, 1, 1, 1, 4, 1 ], "vote_close": [ 0, 0, 0, 0, 0, 0, 0, 0 ], "vote_open": [ 0, 0, 0, 0, 0, 0, 0, 0 ], "voting": [ 0, 0, 0, 0, 0, 0, 0, 0 ] }, "total_responses": 8 }
2
[ "uncowl", "izar", "postern", "pendulation" ]
czse
[ { "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 based on the given requirements, we need to follow these steps:\n\n1. **Identify possible acronyms**: We will consider all combinations of letters taken from different words.\n \n - From \"uncowl\": Possible initials could be 'u', 'c', 'o'.\n - From \"izar\": Possib...
[ false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "" ]
{ "api_url": "http://127.0.0.1:42153", "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/TAUR-dev/M-0903_rl_reflect__1b_3args__grpo_minibs32_lr1e-6_rollout16-rl", "prompt": [ { "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. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer> (your answer) </answer>.\n\n# Problem\nYou are given a list of words. Construct an acronym that satisfies the following conditions:\n\nRequirements\n1) Length: at least 4 characters and at most the number of words provided.\n2) Read the words left to right and form the acronym by selecting a subsequence of the words (you may skip words). \n - The i-th letter of the acronym must come from a word that appears after the word used for the (i-1)-th letter. \n - You may not reorder the words, and you may not take more than one letter from the same word.\n3) If you take a letter from a word, it must be that word’s 1st, 2nd, or 3rd character only.\n\nFor example, if the list of words is: ['regales', 'hyracidae', 'scorches', 'bivium', 'ejidos', 'nonignitable', 'entryman', 'villaless']\t\nWe can take the letter \"r\" from \"regales\", the letter \"i\" comes from \"bivium\", the letter \"n\" comes from \"nonignitable\", the letter \"e\" comes from \"entryman\".\nThen a valid acronym is : <answer> rine </answer> \n\nList of words: ['uncowl' 'izar' 'postern' 'pendulation']\n\n\nLet's think step by step.", "role": "user" } ] }
{ "backend": "litellm", "model_name": "hosted_vllm/TAUR-dev/M-0903_rl_reflect__1b_3args__grpo_minibs32_lr1e-6_rollout16-rl", "n_responses": 8 }
[ false, false, false, false, false, false, false, false ]
[ null, "Now evaluate. </t. <answer.\n.</. </t. </t. </t. ></. </t. </t. </a. </t. </answer\n<p(</ </t. (.", "<think\n...\n</answer\n\n take the to see = the the the the.\n``<></\n\n the the.", "zice", "uncowling", null, null, "</\n\n..., <br many. up man. \n. of. .. . . </answer. you. be. </ answer>\n<...
[ { "extraction_type": "final", "non_overlapping_spans": null, "original_span": null, "span_end": null, "span_start": null, "total_spans_found": null }, { "extraction_type": "final", "non_overlapping_spans": 1, "original_span": "Now evaluate. </t. <answer.\n.</. </t. </t. </t. ...
[ { "correct_answer": null, "evaluation_method": "response_processor", "extracted_answer": null, "extraction_result": "{'extraction_type': 'final'}", "reason": "no_extracted_answer" }, { "correct_answer": null, "evaluation_method": "acronym_simple", "extracted_answer": "Now evaluat...
[ [], [ false ], [ false ], [ false ], [ false ], [], [], [ false ] ]
[ [], [ "Now evaluate. </t. <answer.\n.</. </t. </t. </t. ></. </t. </t. </a. </t. </answer\n<p(</ </t. (." ], [ "<think\n...\n</answer\n\n take the to see = the the the the.\n``<></\n\n the the." ], [ "zice" ], [ "uncowling" ], [], [], [ "</\n\n..., <br many. up man. \n. of....
[ [], [ { "confidence": 1, "extraction_type": "internal", "original_span": "Now evaluate. </t. <answer.\n.</. </t. </t. </t. ></. </t. </t. </a. </t. </answer\n<p(</ </t. (.", "pattern_used": "answer tag", "position": 1930, "span_end": 2028, "span_start": 1930, "s...
[ [], [ { "correct_answer": null, "evaluation_method": "acronym_simple", "extracted_answer": "Now evaluate. </t. <answer.\n.</. </t. </t. </t. ></. </t. </t. </a. </t. </answer\n<p(</ </t. (.", "reason": "no_metadata_available" } ], [ { "correct_answer": null, "ev...
{ "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, 0, 0, 0, 0, 0, 0 ], "reflect_close": [ 0, 0, 0, 0, 0, 0, 0, 0 ], "reflect_open": [ 0, 0, 0, 0, 1, 0, 0, 0 ], "reflection_sbon": [ 0, 0, 0, 0, 0, 0, 0, 0 ], "sample_close": [ 0, 0, 0, 1, 2, 0, 11, 0 ], "sample_open": [ 1, 1, 3, 1, 1, 1, 1, 1 ], "vote_close": [ 0, 0, 0, 0, 0, 0, 0, 0 ], "vote_open": [ 0, 0, 0, 0, 0, 0, 0, 0 ], "voting": [ 0, 0, 0, 0, 0, 0, 0, 0 ] }, "total_responses": 8 }
3
[ "callous", "lesser", "gibbergunyah", "piblockto" ]
cegi
[ { "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 appropriate acronym based on the given requirements, we need to follow these steps:\n\n1. **Identify the criteria**: We need to create an acronym using exactly four letters where each subsequent letter corresponds to a different word from the input list, ensuring that no repeated...
[ false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "" ]
{ "api_url": "http://127.0.0.1:42153", "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/TAUR-dev/M-0903_rl_reflect__1b_3args__grpo_minibs32_lr1e-6_rollout16-rl", "prompt": [ { "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. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer> (your answer) </answer>.\n\n# Problem\nYou are given a list of words. Construct an acronym that satisfies the following conditions:\n\nRequirements\n1) Length: at least 4 characters and at most the number of words provided.\n2) Read the words left to right and form the acronym by selecting a subsequence of the words (you may skip words). \n - The i-th letter of the acronym must come from a word that appears after the word used for the (i-1)-th letter. \n - You may not reorder the words, and you may not take more than one letter from the same word.\n3) If you take a letter from a word, it must be that word’s 1st, 2nd, or 3rd character only.\n\nFor example, if the list of words is: ['regales', 'hyracidae', 'scorches', 'bivium', 'ejidos', 'nonignitable', 'entryman', 'villaless']\t\nWe can take the letter \"r\" from \"regales\", the letter \"i\" comes from \"bivium\", the letter \"n\" comes from \"nonignitable\", the letter \"e\" comes from \"entryman\".\nThen a valid acronym is : <answer> rine </answer> \n\nList of words: ['callous' 'lesser' 'gibbergunyah' 'piblockto']\n\n\nLet's think step by step.", "role": "user" } ] }
{ "backend": "litellm", "model_name": "hosted_vllm/TAUR-dev/M-0903_rl_reflect__1b_3args__grpo_minibs32_lr1e-6_rollout16-rl", "n_responses": 8 }
[ false, false, false, false, false, false, false, false ]
[ null, null, null, null, null, null, null, null ]
[ { "extraction_type": "final", "non_overlapping_spans": null, "original_span": null, "span_end": null, "span_start": null, "total_spans_found": null }, { "extraction_type": "final", "non_overlapping_spans": null, "original_span": null, "span_end": null, "span_start": n...
[ { "correct_answer": null, "evaluation_method": "response_processor", "extracted_answer": null, "extraction_result": "{'extraction_type': 'final'}", "reason": "no_extracted_answer" }, { "correct_answer": null, "evaluation_method": "response_processor", "extracted_answer": null, ...
null
null
null
null
{ "flips_by": null, "flips_total": null, "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, 0, 0, 0, 0, 0, 0 ], "reflect_close": [ 0, 0, 1, 0, 0, 0, 0, 0 ], "reflect_open": [ 0, 0, 1, 0, 0, 0, 0, 1 ], "reflection_sbon": [ 0, 0, 0, 0, 0, 0, 0, 0 ], "sample_close": [ 0, 2, 1, 0, 1, 0, 0, 4 ], "sample_open": [ 1, 2, 1, 1, 2, 1, 1, 1 ], "vote_close": [ 0, 0, 0, 0, 0, 0, 0, 0 ], "vote_open": [ 0, 0, 0, 0, 0, 0, 0, 0 ], "voting": [ 0, 0, 0, 0, 0, 0, 0, 0 ] }, "total_responses": 8 }
4
[ "blockship", "engorge", "giantsize", "foveolae" ]
bgav
[{"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 appropriate acronym based on the given requirements, we need to(...TRUNCATED)
[ false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "" ]
{"api_url":"http://127.0.0.1:42153","backend":"litellm","chat_template_applied":true,"generation_par(...TRUNCATED)
{"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-0903_rl_reflect__1b_3args__grpo_minibs32_l(...TRUNCATED)
[ false, false, false, false, false, false, false, false ]
["the",null,"/</<answer the word that starts with the second and ends then.<paragraph, let your answ(...TRUNCATED)
[{"extraction_type":"final","non_overlapping_spans":2,"original_span":"the","span_end":531,"span_sta(...TRUNCATED)
[{"correct_answer":null,"evaluation_method":"acronym_simple","extracted_answer":"the","extraction_re(...TRUNCATED)
[ [ false, false ], [], [ false ], [], [ false, false ], [ false, false ], [], [ false, false ] ]
[["r.in.e < <then","the"],[],["/</<answer the word that starts with the second and ends then.<paragr(...TRUNCATED)
[[{"confidence":1.0,"extraction_type":"internal","original_span":"r.in.e < <then","pattern_used":"an(...TRUNCATED)
[[{"correct_answer":null,"evaluation_method":"acronym_simple","extracted_answer":"r.in.e < <then","r(...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
[ "nazarenism", "pterocarpus", "nonfrosted", "houhere" ]
ztoh
[{"content":"You like to solve problems by thinking step by step. Write out your reasoning then give(...TRUNCATED)
acronym
["<think</<answer<object></\\//d.<x my name is:.< Naz. I am going student....<em>.<6</em>.<br />\n<a(...TRUNCATED)
[ false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "" ]
{"api_url":"http://127.0.0.1:42153","backend":"litellm","chat_template_applied":true,"generation_par(...TRUNCATED)
{"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-0903_rl_reflect__1b_3args__grpo_minibs32_l(...TRUNCATED)
[ false, false, false, false, false, false, false, false ]
[ "hnc", null, ".", null, null, "on the other hand,", null, null ]
[{"extraction_type":"final","non_overlapping_spans":1,"original_span":"hnc","span_end":107,"span_sta(...TRUNCATED)
[{"correct_answer":null,"evaluation_method":"acronym_simple","extracted_answer":"hnc","extraction_re(...TRUNCATED)
[ [ false ], [], [ false, false ], [], [], [ false, false, false ], [], [] ]
[["hnc"],[],["<br\n\n\n\n\n\n\n\n<answer>\nTo construct an acronym, letthen\n<\\be< the answer\nnot\(...TRUNCATED)
[[{"confidence":1.0,"extraction_type":"internal","original_span":"hnc","pattern_used":"answer tag","(...TRUNCATED)
[[{"correct_answer":null,"evaluation_method":"acronym_simple","extracted_answer":"hnc","reason":"no_(...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
[ "requisites", "laureateship", "lilliputs", "oscitation" ]
qalc
[{"content":"You like to solve problems by thinking step by step. Write out your reasoning then give(...TRUNCATED)
acronym
["<thanager>\n\n'>\n</ \n >","<think>\n\n\n<answer\n\n\n\n\n<answer> laulis </answer>\n\n\n\n\n\n<a(...TRUNCATED)
[ false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "" ]
{"api_url":"http://127.0.0.1:42153","backend":"litellm","chat_template_applied":true,"generation_par(...TRUNCATED)
{"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-0903_rl_reflect__1b_3args__grpo_minibs32_l(...TRUNCATED)
[ false, false, false, false, false, false, false, false ]
[ null, "laulis", "regales laur", null, "constructive", null, "< \\<your answer?>)", null ]
[{"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 ], [] ]
[[],["laulis"],["<answer>\n(answer>\n will\n\n sample input:\nProblem\n\n\n regales\n (\n\n entry <(...TRUNCATED)
[[],[{"confidence":1.0,"extraction_type":"internal","original_span":"laulis","pattern_used":"answer (...TRUNCATED)
[[],[{"correct_answer":null,"evaluation_method":"acronym_simple","extracted_answer":"laulis","reason(...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
[ "reorganizers", "effeteness", "martu", "crossbreed" ]
efmr
[{"content":"You like to solve problems by thinking step by step. Write out your reasoning then give(...TRUNCATED)
acronym
["<th</</</\n></a></continue\n\n\nTo\n\n\n\n your``. I\n always<then let.then</ see.\n. i the. ithen(...TRUNCATED)
[ false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "" ]
{"api_url":"http://127.0.0.1:42153","backend":"litellm","chat_template_applied":true,"generation_par(...TRUNCATED)
{"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-0903_rl_reflect__1b_3args__grpo_minibs32_l(...TRUNCATED)
[ false, false, false, false, false, false, false, false ]
[null,null,null,null,"</</answer >\n</</ />(answer)<\\/answer>\n</plan>\n<answer>\n<answer\n<see\nto(...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 ], [], [], [] ]
[[],[],[],[],["So\n>\n(your answer)","</ >\nSee above.\n not necessary to specify all.</<answer>\n</(...TRUNCATED)
[[],[],[],[],[{"confidence":1.0,"extraction_type":"internal","original_span":"So\n>\n(your answer)",(...TRUNCATED)
[[],[],[],[],[{"correct_answer":null,"evaluation_method":"acronym_simple","extracted_answer":"So\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)
8
[ "galvanotonic", "hotpressed", "commendator", "clinoid" ]
gomc
[{"content":"You like to solve problems by thinking step by step. Write out your reasoning then give(...TRUNCATED)
acronym
["<thaver>\n :</th , villaless.\n. \n<answer\n:\n > once\n</t... as . List so. Let me break some. F(...TRUNCATED)
[ false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "" ]
{"api_url":"http://127.0.0.1:42153","backend":"litellm","chat_template_applied":true,"generation_par(...TRUNCATED)
{"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-0903_rl_reflect__1b_3args__grpo_minibs32_l(...TRUNCATED)
[ false, false, false, false, false, false, false, false ]
[ "hotpressed", null, null, null, null, null, null, null ]
[{"extraction_type":"final","non_overlapping_spans":1,"original_span":"hotpressed","span_end":429,"s(...TRUNCATED)
[{"correct_answer":null,"evaluation_method":"acronym_simple","extracted_answer":"hotpressed","extrac(...TRUNCATED)
[ [ false ], [], [], [], [], [], [], [] ]
[ [ "hotpressed" ], [], [], [], [], [], [], [] ]
[[{"confidence":1.0,"extraction_type":"internal","original_span":"hotpressed","pattern_used":"answer(...TRUNCATED)
[[{"correct_answer":null,"evaluation_method":"acronym_simple","extracted_answer":"hotpressed","reaso(...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
[ "pockier", "harpy", "queazy", "warrin" ]
oaew
[{"content":"You like to solve problems by thinking step by step. Write out your reasoning then give(...TRUNCATED)
acronym
["<think let these steps. Letch, I know personally. ,., you. you ..//\n\nIet:. the my. , the your do(...TRUNCATED)
[ false, false, false, false, false, false, false, false ]
[ "", "", "", "", "", "", "", "" ]
{"api_url":"http://127.0.0.1:42153","backend":"litellm","chat_template_applied":true,"generation_par(...TRUNCATED)
{"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-0903_rl_reflect__1b_3args__grpo_minibs32_l(...TRUNCATED)
[ false, false, false, false, false, false, false, false ]
[null,null,null,"harry",null,"answer. Let.let the first word non.ac.: r.answer. irner. <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, false, false, false ], [], [ false ], [], [] ]
[[],[],[],["let\n</answer\n\n\nLet\n\n\n the\n\n</</></</","<answer>","harpy","pockier queazy warrin(...TRUNCATED)
[[],[],[],[{"confidence":1.0,"extraction_type":"internal","original_span":"let\n</answer\n\n\nLet\n\(...TRUNCATED)
[[],[],[],[{"correct_answer":null,"evaluation_method":"acronym_simple","extracted_answer":"let\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)
End of preview. Expand in Data Studio
README.md exists but content is empty.
Downloads last month
6