question stringlengths 687 756 | answer stringclasses 1
value | task_config stringclasses 1
value | task_source stringclasses 1
value | prompt listlengths 1 1 | model_responses listlengths 0 0 | model_responses__eval_is_correct listlengths 0 0 | all_other_columns stringlengths 162 231 | original_split stringclasses 1
value | acronym stringlengths 4 4 | formed_acronym stringlengths 4 4 | word_count int64 4 8 | words listlengths 4 8 | model_responses__best_of_n_atags listlengths 4 4 | model_responses__best_of_n_atags__finish_reason_length_flags listlengths 4 4 | model_responses__best_of_n_atags__length_partial_responses listlengths 4 4 | prompt__best_of_n_atags__metadata dict | model_responses__best_of_n_atags__metadata dict | model_responses__best_of_n_atags__eval_is_correct listlengths 4 4 | model_responses__best_of_n_atags__eval_extracted_answers listlengths 4 4 | model_responses__best_of_n_atags__eval_extraction_metadata stringlengths 120 625 | model_responses__best_of_n_atags__eval_evaluation_metadata stringlengths 425 846 | model_responses__best_of_n_atags__internal_answers__eval_is_correct listlengths 4 4 ⌀ | model_responses__best_of_n_atags__internal_answers__eval_extracted_answers listlengths 4 4 ⌀ | model_responses__best_of_n_atags__internal_answers__eval_extraction_metadata stringlengths 195 5.78k ⌀ | model_responses__best_of_n_atags__internal_answers__eval_evaluation_metadata stringlengths 142 5.75k ⌀ | model_responses__best_of_n_atags__metrics dict | eval_date stringdate 2025-10-27 00:00:00 2025-10-27 00:00:00 | split stringclasses 1
value | revision_name stringclasses 1
value | model_path stringclasses 1
value | checkpoint_step int64 0 0 | stage_name stringclasses 1
value | stage_number int64 1 1 | timestamp stringdate 2025-10-27 12:13:18 2025-10-27 12:13:18 | eval_repo_id stringclasses 1
value |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer> (your answer) </answer>.
### Problem
You are given a list of words. Construct an acronym that satisfies the following conditions:
1) is at least 4 characters
2) uses the first letter... | acronym_4o | acronym | [
{
"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\n\n\nYou are given a list of words. Construct an acronym that satisfies the following conditions:\n\n1) is at least 4 charac... | [] | [] | {"acronym": "they", "words": ["treating", "hurricane", "exhibits", "yours"], "word_count": 4, "formed_acronym": "they", "task_config": "acronym_4o", "task_source": "acronym"} | test | they | they | 4 | [
"treating",
"hurricane",
"exhibits",
"yours"
] | [
"<think>\nI need to create an acronym based on the given list of words. Let me look at the requirements:\n\n1. The acronym must be at least 4 characters long.\n2. It should use the first letter of at least 4 words from the list.\n3. Only the first letters of these selected words should be used.\n4. The resulting ac... | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {
"api_url": "http://10.32.37.28:9080/v1",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 16384,
"n": 1,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8
},
"model_name": "hosted_vll... | {
"backend": "litellm",
"model_name": "hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only",
"n_responses": 4
} | [
false,
false,
false,
false
] | [
"idea",
"the",
null,
"idea"
] | [{"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 3159, "span_end": 3165, "original_span": "idea"}, {"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 7864, "span_end": 7869, "original_span": "the"}, {"extraction_type": "final"}, ... | [{"is_correct": false, "error": "Constraint violations: violates_character_position_constraint", "answer_block": "idea", "final_answer": "idea", "length": 4}, {"is_correct": false, "error": "Constraint violations: invalid_length", "answer_block": "the", "final_answer": "the", "length": 3}, {"evaluation_method": "respon... | [
[
false
],
[
false
],
[],
[
true,
false
]
] | [
[
"idea"
],
[
"the"
],
[],
[
"they",
"idea"
]
] | [[{"pattern_used": "answer tag", "confidence": 1.0, "position": 3159, "span_text": "idea", "extraction_type": "internal", "span_start": 3159, "span_end": 3165, "original_span": "idea"}], [{"pattern_used": "answer tag", "confidence": 1.0, "position": 7864, "span_text": "the", "extraction_type": "internal", "span_start":... | [[{"is_correct": false, "error": "Constraint violations: violates_character_position_constraint", "answer_block": "idea", "final_answer": "idea", "length": 4}], [{"is_correct": false, "error": "Constraint violations: invalid_length", "answer_block": "the", "final_answer": "the", "length": 3}], [], [{"is_correct": true,... | {
"flips_by": [
0,
0,
0,
1
],
"flips_total": 1,
"num_correct": 0,
"pass_at_n": 0,
"percent_correct": 0,
"skill_count": {
"answer_revision": [
0,
0,
0,
0
],
"best_of_n": [
0,
0,
0,
0
],
"reflect_close": [
0,
0,
... | 2025-10-27 | test | main | TAUR-dev/M-R1_distilled_baseline_cd3args_only | 0 | eval_0 | 1 | 2025-10-27T12:13:18.576220 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-acronym_4o-eval_0 | |
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED) | acronym_4o | acronym | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"acronym\": \"when\", \"words\": [\"whether\", \"hooked\", \"enables\", \"next\"], \"word_count\"(...TRUNCATED) | test | when | when | 4 | [
"whether",
"hooked",
"enables",
"next"
] | ["<think>\nFirst, I need to understand the requirements for constructing an acronym based on the giv(...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {"api_url":"http://10.32.37.28:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED) | {"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only","n_res(...TRUNCATED) | [
false,
false,
false,
false
] | [
"hooked enables",
"(your answer)",
"whene",
"(your answer)"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 3, \"non_overlapping_spans\": 3, \"span_st(...TRUNCATED) | "[{\"is_correct\": false, \"error\": \"Constraint violations: not_valid_english_word, invalid_length(...TRUNCATED) | [
[
false,
false,
false
],
[
false,
false
],
[
false,
false,
false
],
[
false
]
] | [["idea","idea","hooked enables"],["idea","(your answer)"],["(your answer)","whene","whene"],["(your(...TRUNCATED) | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 4975, \"span_text\": \"idea(...TRUNCATED) | "[[{\"is_correct\": false, \"error\": \"Constraint violations: violates_character_position_constrain(...TRUNCATED) | {"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED) | 2025-10-27 | test | main | TAUR-dev/M-R1_distilled_baseline_cd3args_only | 0 | eval_0 | 1 | 2025-10-27T12:13:18.576229 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-acronym_4o-eval_0 | |
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED) | acronym_4o | acronym | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"acronym\": \"some\", \"words\": [\"sufficient\", \"overwhelming\", \"mentally\", \"elizabeth\"],(...TRUNCATED) | test | some | some | 4 | [
"sufficient",
"overwhelming",
"mentally",
"elizabeth"
] | ["<think>\nFirst, I need to construct an acronym based on the given list of words. The conditions ar(...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {"api_url":"http://10.32.37.28:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED) | {"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only","n_res(...TRUNCATED) | [
false,
false,
false,
true
] | [
"somoe",
null,
"No valid acronym exists",
"some"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 3, \"non_overlapping_spans\": 3, \"span_st(...TRUNCATED) | "[{\"is_correct\": false, \"error\": \"Constraint violations: not_valid_english_word, invalid_length(...TRUNCATED) | [
[
false,
false,
false
],
[],
[
false,
false
],
[
false,
false,
true,
true
]
] | [["idea","iota","somoe"],[],["No valid acronym exists","No valid acronym exists"],["idea","(your ans(...TRUNCATED) | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 10346, \"span_text\": \"ide(...TRUNCATED) | "[[{\"is_correct\": false, \"error\": \"Constraint violations: violates_character_position_constrain(...TRUNCATED) | {"flips_by":[0,0,0,0],"flips_total":0,"num_correct":1,"pass_at_n":1,"percent_correct":0.25,"skill_co(...TRUNCATED) | 2025-10-27 | test | main | TAUR-dev/M-R1_distilled_baseline_cd3args_only | 0 | eval_0 | 1 | 2025-10-27T12:13:18.576231 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-acronym_4o-eval_0 | |
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED) | acronym_4o | acronym | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"acronym\": \"back\", \"words\": [\"believed\", \"allison\", \"clips\", \"kane\"], \"word_count\"(...TRUNCATED) | test | back | back | 4 | [
"believed",
"allison",
"clips",
"kane"
] | ["<think>\nI need to create an acronym from the given list of words that meets certain criteria. Let(...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {"api_url":"http://10.32.37.28:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED) | {"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only","n_res(...TRUNCATED) | [
false,
false,
false,
false
] | [
"becpk",
"idea",
"bacck",
"bacik"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 3, \"non_overlapping_spans\": 3, \"span_st(...TRUNCATED) | "[{\"is_correct\": false, \"error\": \"Constraint violations: not_valid_english_word, invalid_length(...TRUNCATED) | [
[
false,
false,
false
],
[
false,
false
],
[
false,
false,
false,
false
],
[
false,
false,
false
]
] | [["(your answer)","become","becpk"],["idea","idea"],["bakck","idea","bakck","bacck"],["idea","bacik"(...TRUNCATED) | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 4912, \"span_text\": \"(you(...TRUNCATED) | "[[{\"is_correct\": false, \"error\": \"Constraint violations: not_valid_english_word, invalid_lengt(...TRUNCATED) | {"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED) | 2025-10-27 | test | main | TAUR-dev/M-R1_distilled_baseline_cd3args_only | 0 | eval_0 | 1 | 2025-10-27T12:13:18.576232 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-acronym_4o-eval_0 | |
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED) | acronym_4o | acronym | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"acronym\": \"life\", \"words\": [\"layer\", \"immigrant\", \"fisher\", \"exhibits\"], \"word_cou(...TRUNCATED) | test | life | life | 4 | [
"layer",
"immigrant",
"fisher",
"exhibits"
] | ["<think>\nI need to construct an acronym based on the given list of words. Let me look at the requi(...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {"api_url":"http://10.32.37.28:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED) | {"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only","n_res(...TRUNCATED) | [
false,
false,
false,
false
] | [
"idea",
"liefe",
"lipmfe",
"(your answer)"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED) | "[{\"is_correct\": false, \"error\": \"Constraint violations: violates_character_position_constraint(...TRUNCATED) | [
[
false
],
[
false,
false
],
[
false,
false,
false
],
[
false,
false
]
] | [
[
"idea"
],
[
"idea",
"liefe"
],
[
"(your answer)",
"lipmfe",
"lipmfe"
],
[
"ideamashup",
"(your answer)"
]
] | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 7806, \"span_text\": \"idea(...TRUNCATED) | "[[{\"is_correct\": false, \"error\": \"Constraint violations: violates_character_position_constrain(...TRUNCATED) | {"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED) | 2025-10-27 | test | main | TAUR-dev/M-R1_distilled_baseline_cd3args_only | 0 | eval_0 | 1 | 2025-10-27T12:13:18.576234 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-acronym_4o-eval_0 | |
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED) | acronym_4o | acronym | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"acronym\": \"best\", \"words\": [\"bonus\", \"eight\", \"shanghai\", \"them\"], \"word_count\": (...TRUNCATED) | test | best | best | 4 | [
"bonus",
"eight",
"shanghai",
"them"
] | ["<think>\nFirst, I need to construct an acronym based on the given list of words. The conditions ar(...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {"api_url":"http://10.32.37.28:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED) | {"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only","n_res(...TRUNCATED) | [
false,
true,
true,
true
] | [
null,
"best",
"best",
"best"
] | "[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non(...TRUNCATED) | "[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED) | [
[],
[
true
],
[
false,
true
],
[
false,
true
]
] | [
[],
[
"best"
],
[
"(your answer)",
"best"
],
[
"idea",
"best"
]
] | "[[], [{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 17577, \"span_text\": \(...TRUNCATED) | "[[], [{\"is_correct\": true, \"error\": null, \"answer_block\": \"best\", \"final_answer\": \"best\(...TRUNCATED) | {"flips_by":[0,0,0,0],"flips_total":0,"num_correct":3,"pass_at_n":1,"percent_correct":0.75,"skill_co(...TRUNCATED) | 2025-10-27 | test | main | TAUR-dev/M-R1_distilled_baseline_cd3args_only | 0 | eval_0 | 1 | 2025-10-27T12:13:18.576235 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-acronym_4o-eval_0 | |
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED) | acronym_4o | acronym | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"acronym\": \"long\", \"words\": [\"listen\", \"offensive\", \"nets\", \"galaxy\"], \"word_count\(...TRUNCATED) | test | long | long | 4 | [
"listen",
"offensive",
"nets",
"galaxy"
] | ["<think>\nFirst, I need to understand the requirements for constructing an acronym based on the giv(...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {"api_url":"http://10.32.37.28:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED) | {"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only","n_res(...TRUNCATED) | [
false,
false,
false,
false
] | [
"line",
null,
"LN",
"logan"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non_overlapping_spans\": 2, \"span_st(...TRUNCATED) | "[{\"is_correct\": false, \"error\": \"Constraint violations: violates_character_position_constraint(...TRUNCATED) | [
[
false,
false
],
[],
[
false,
false,
false,
false
],
[
false,
false,
false
]
] | [["idea","line"],[],["(your answer)","(your answer)","(your answer)","LN"],["(your answer)","logan",(...TRUNCATED) | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 6526, \"span_text\": \"idea(...TRUNCATED) | "[[{\"is_correct\": false, \"error\": \"Constraint violations: violates_character_position_constrain(...TRUNCATED) | {"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED) | 2025-10-27 | test | main | TAUR-dev/M-R1_distilled_baseline_cd3args_only | 0 | eval_0 | 1 | 2025-10-27T12:13:18.576237 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-acronym_4o-eval_0 | |
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED) | acronym_4o | acronym | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"acronym\": \"part\", \"words\": [\"proposed\", \"agreements\", \"randomly\", \"tube\"], \"word_c(...TRUNCATED) | test | part | part | 4 | [
"proposed",
"agreements",
"randomly",
"tube"
] | ["<think>\nI need to create an acronym based on the given list of words, but there are some specific(...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {"api_url":"http://10.32.37.28:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED) | {"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only","n_res(...TRUNCATED) | [
false,
false,
false,
false
] | [
"padt",
"idea",
"(your answer)",
"padt"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED) | "[{\"is_correct\": false, \"error\": \"Constraint violations: not_valid_english_word, violates_chara(...TRUNCATED) | [
[
false
],
[
false,
false
],
[
false
],
[
false,
false,
false,
false
]
] | [
[
"padt"
],
[
"idea",
"idea"
],
[
"(your answer)"
],
[
"...",
"padt",
"(your answer)",
"padt"
]
] | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 13948, \"span_text\": \"pad(...TRUNCATED) | "[[{\"is_correct\": false, \"error\": \"Constraint violations: not_valid_english_word, violates_char(...TRUNCATED) | {"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED) | 2025-10-27 | test | main | TAUR-dev/M-R1_distilled_baseline_cd3args_only | 0 | eval_0 | 1 | 2025-10-27T12:13:18.576239 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-acronym_4o-eval_0 | |
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED) | acronym_4o | acronym | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"acronym\": \"find\", \"words\": [\"folks\", \"investigated\", \"next\", \"destinations\"], \"wor(...TRUNCATED) | test | find | find | 4 | [
"folks",
"investigated",
"next",
"destinations"
] | ["<think>\nI need to create an acronym based on the given list of words, but there are some specific(...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {"api_url":"http://10.32.37.28:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED) | {"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only","n_res(...TRUNCATED) | [
true,
false,
false,
false
] | [
"find",
"indeed",
"indnd",
"ides"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 3, \"non_overlapping_spans\": 3, \"span_st(...TRUNCATED) | "[{\"is_correct\": true, \"error\": null, \"answer_block\": \"find\", \"final_answer\": \"find\", \"(...TRUNCATED) | [
[
false,
true,
true
],
[
false,
false,
false
],
[
false,
false
],
[
false
]
] | [
[
"(your answer)",
"find",
"find"
],
[
"indeed",
"...",
"indeed"
],
[
"indnd",
"indnd"
],
[
"ides"
]
] | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 5086, \"span_text\": \"(you(...TRUNCATED) | "[[{\"is_correct\": false, \"error\": \"Constraint violations: not_valid_english_word, invalid_lengt(...TRUNCATED) | {"flips_by":[0,0,0,0],"flips_total":0,"num_correct":1,"pass_at_n":1,"percent_correct":0.25,"skill_co(...TRUNCATED) | 2025-10-27 | test | main | TAUR-dev/M-R1_distilled_baseline_cd3args_only | 0 | eval_0 | 1 | 2025-10-27T12:13:18.576240 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-acronym_4o-eval_0 | |
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED) | acronym_4o | acronym | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"acronym\": \"does\", \"words\": [\"donated\", \"organisations\", \"efforts\", \"scientists\"], \(...TRUNCATED) | test | does | does | 4 | [
"donated",
"organisations",
"efforts",
"scientists"
] | ["<think>\nI need to create an acronym based on the given list of words, but there are some constrai(...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {"api_url":"http://10.32.37.28:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED) | {"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only","n_res(...TRUNCATED) | [
true,
false,
false,
false
] | [
"does",
"dose",
null,
"dose"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 3, \"non_overlapping_spans\": 3, \"span_st(...TRUNCATED) | "[{\"is_correct\": true, \"error\": null, \"answer_block\": \"does\", \"final_answer\": \"does\", \"(...TRUNCATED) | [
[
false,
true,
true
],
[
false,
false,
false
],
[],
[
false,
false
]
] | [
[
"(your answer)",
"does",
"does"
],
[
"(your answer)",
"dose",
"dose"
],
[],
[
"(your answer)",
"dose"
]
] | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 11209, \"span_text\": \"(yo(...TRUNCATED) | "[[{\"is_correct\": false, \"error\": \"Constraint violations: not_valid_english_word, invalid_lengt(...TRUNCATED) | {"flips_by":[0,0,0,0],"flips_total":0,"num_correct":1,"pass_at_n":1,"percent_correct":0.25,"skill_co(...TRUNCATED) | 2025-10-27 | test | main | TAUR-dev/M-R1_distilled_baseline_cd3args_only | 0 | eval_0 | 1 | 2025-10-27T12:13:18.576242 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-acronym_4o-eval_0 |
End of preview. Expand in Data Studio
Experiment Tracker: FinEval_16k_fulleval_3args_r1-acronym_4o
Experiment Description: Evaluation experiment for task acronym_4o from FinEval_16k_fulleval_3args_r1
Start Time: 2025-10-27T11:48:31.570449
Tracker Dataset: TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-acronym_4o__v1
Stages Completed
Total stages: 1
Models Created
Dataset Configurations
This tracker dataset contains the following configurations with immediate upload as stages complete:
Training Data (Complete Datasets)
Hyperparameters (Complete Configurations)
Logs (Stage-Specific)
Evaluation Results (Complete with Annotations)
Metadata
- experiment_metadata: Timeline and stage information
Usage
Load specific configurations with:
from datasets import load_dataset
# Load experiment metadata
metadata = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-acronym_4o__v1', 'experiment_metadata')
# Load complete training datasets
sft_data = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-acronym_4o__v1', 'training_data__sft')
sft_metadata = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-acronym_4o__v1', 'training_data__sft_metadata')
# Load complete configurations
sft_hyperparams = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-acronym_4o__v1', 'hyperparameters__sft')
rl_hyperparams = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-acronym_4o__v1', 'hyperparameters__rl')
# Load stage-specific logs
sft_logs = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-acronym_4o__v1', 'logs__sft')
rl_logs = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-acronym_4o__v1', 'logs__rl')
# Load evaluation results with annotations
sft_eval_results = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-acronym_4o__v1', 'evals_eval_sft')
rl_eval_results = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-acronym_4o__v1', 'evals_eval_rl')
Models
Registry
All models from this experiment are automatically registered in the SkillFactory Model Registry with:
- Complete training configuration (hyperparameters, datasets, methods)
- Experiment lineage (links back to this tracker dataset)
- Stage-specific metadata (SFT vs RL training details)
- Structured input data references (training datasets and configurations)
Registry entries follow the naming pattern: Model - FinEval_16k_fulleval_3args_r1-acronym_4o - {stage_name} - {SFT/RL}
Generated by SkillFactory Experiment Management System All artifacts uploaded immediately as stages complete with perfect data provenance
- Downloads last month
- 4