question string | answer string | task_config string | task_source string | prompt list | model_responses list | model_responses__eval_is_correct list | all_other_columns string | original_split string | metadata string | model_responses__best_of_n_atags list | model_responses__best_of_n_atags__finish_reason_length_flags list | model_responses__best_of_n_atags__length_partial_responses list | prompt__best_of_n_atags__metadata dict | model_responses__best_of_n_atags__metadata dict | model_responses__best_of_n_atags__eval_is_correct list | model_responses__best_of_n_atags__eval_extracted_answers list | model_responses__best_of_n_atags__eval_extraction_metadata string | model_responses__best_of_n_atags__eval_evaluation_metadata string | model_responses__best_of_n_atags__internal_answers__eval_is_correct list | model_responses__best_of_n_atags__internal_answers__eval_extracted_answers list | model_responses__best_of_n_atags__internal_answers__eval_extraction_metadata string | model_responses__best_of_n_atags__internal_answers__eval_evaluation_metadata string | model_responses__best_of_n_atags__metrics dict | eval_date string | split string | revision_name string | model_path string | checkpoint_step int64 | stage_name string | stage_number int64 | timestamp string | eval_repo_id string |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
61662 x 44241 | 2727988542 | longmult_5dig | longmult | [
{
"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\nWhat is the solution to the multiplication equation below?\n61662 x 44241\n\nGive your answer in the following format:\n<answer>\... | [] | [] | {"metadata": "{\"arg1\": 61662, \"arg2\": 44241, \"solution\": 2727988542}", "task_source": "longmult"} | test | {"arg1": 61662, "arg2": 44241, "solution": 2727988542} | [
"<think>\nI need to multiply 61662 by 44241. Since these numbers are both quite large, I should look for ways to simplify the calculation or estimate the result.\n\nFirst, let's add the two numbers: 61662 + 44241 = 105903. This might be close to the actual product, but it doesn't help directly with the multiplicati... | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {
"api_url": "http://127.0.0.1:35419/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_vllm... | {
"backend": "litellm",
"model_name": "hosted_vllm/TAUR-dev/M-r1_distill_baseline-rl",
"n_responses": 4
} | [
false,
false,
false,
false
] | [
"2748000000",
"2748000000",
"2748000000",
"2728440322"
] | [{"extraction_type": "final", "total_spans_found": 6, "non_overlapping_spans": 6, "span_start": 4676, "span_end": 4686, "original_span": "2748000000"}, {"extraction_type": "final", "total_spans_found": 3, "non_overlapping_spans": 3, "span_start": 3621, "span_end": 3633, "original_span": "2748000000"}, {"extraction_type... | [{"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "legacy_result": false}] | [
[
false,
false,
false,
false,
false,
false
],
[
false,
false,
false
],
[
false,
false,
false,
false,
false,
false,
false,
false,
false
],
[
false,
false,
false,
false,
false,
false
]
] | [
[
"your answer",
"(your answer)",
"(your answer)",
"2748000000",
"(your answer)",
"2748000000"
],
[
"your answer",
"(your answer)",
"2748000000"
],
[
"your answer",
"2748000000",
"(your answer)",
"(your answer)",
"2748000000",
"2748000000",
"(y... | [[{"pattern_used": "answer tag", "confidence": 1.0, "position": 1714, "span_text": "your answer", "extraction_type": "internal", "span_start": 1714, "span_end": 1725, "original_span": "your answer"}, {"pattern_used": "answer tag", "confidence": 1.0, "position": 2639, "span_text": "(your answer)", "extraction_type": "in... | [[{"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "... | {
"flips_by": [
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
],
"best_of_n": [
0,
0,
0,
0
],
"reflect_close": [
0,
0,
... | 2025-11-03 | test | main | TAUR-dev/M-r1_distill_baseline-rl | 0 | eval_rl | 1 | 2025-11-03T00:55:17.390493 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1distill_rl-longmult_5dig-eval_rl |
98270 x 48469 | 4763048630 | longmult_5dig | longmult | [
{
"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\nWhat is the solution to the multiplication equation below?\n98270 x 48469\n\nGive your answer in the following format:\n<answer>\... | [] | [] | {"metadata": "{\"arg1\": 98270, \"arg2\": 48469, \"solution\": 4763048630}", "task_source": "longmult"} | test | {"arg1": 98270, "arg2": 48469, "solution": 4763048630} | [
"<think>\nI need to multiply 98270 by 48469. Since these numbers are both quite large, I should consider some properties or估算methods to make it easier, but for accuracy, I'll do the multiplication directly.\n\nFirst, let me write down the numbers:\n\n98270\nx 48469\n\nI can break it down, but since both numbers hav... | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {
"api_url": "http://127.0.0.1:35419/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_vllm... | {
"backend": "litellm",
"model_name": "hosted_vllm/TAUR-dev/M-r1_distill_baseline-rl",
"n_responses": 4
} | [
false,
false,
false,
false
] | [
"4753087730",
"4,800,000,000",
"4765088630",
"540487630"
] | [{"extraction_type": "final", "total_spans_found": 6, "non_overlapping_spans": 6, "span_start": 5401, "span_end": 5411, "original_span": "4753087730"}, {"extraction_type": "final", "total_spans_found": 4, "non_overlapping_spans": 4, "span_start": 2910, "span_end": 2925, "original_span": "4,800,000,000"}, {"extraction_t... | [{"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "legacy_result": false}] | [
[
false,
false,
false,
false,
false,
false
],
[
false,
false,
false,
false
],
[
false,
false,
false,
false
],
[
false,
false,
false,
false,
false
]
] | [
[
"(your answer)",
"(your answer)",
"4753087730",
"1234567890",
"4753087730",
"4753087730"
],
[
"(your answer)",
"4,800,000,000",
"4,800,000,000",
"4,800,000,000"
],
[
"(your answer)",
"4765088630",
"4765088630",
"4765088630"
],
[
"(your answer... | [[{"pattern_used": "answer tag", "confidence": 1.0, "position": 1614, "span_text": "(your answer)", "extraction_type": "internal", "span_start": 1614, "span_end": 1627, "original_span": "(your answer)"}, {"pattern_used": "answer tag", "confidence": 1.0, "position": 1938, "span_text": "(your answer)", "extraction_type":... | [[{"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "... | {
"flips_by": [
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
],
"best_of_n": [
0,
0,
0,
0
],
"reflect_close": [
0,
0,
... | 2025-11-03 | test | main | TAUR-dev/M-r1_distill_baseline-rl | 0 | eval_rl | 1 | 2025-11-03T00:55:17.390502 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1distill_rl-longmult_5dig-eval_rl |
85574 x 60628 | 5188180472 | longmult_5dig | longmult | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"metadata\": \"{\\\"arg1\\\": 85574, \\\"arg2\\\": 60628, \\\"solution\\\": 5188180472}\", \"task(...TRUNCATED) | test | {"arg1": 85574, "arg2": 60628, "solution": 5188180472} | ["<think>\nI need to multiply 85574 by 60628. Since these numbers are both fairly large, I shouldn't(...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {"api_url":"http://127.0.0.1:35419/v1","backend":"litellm","chat_template_applied":true,"generation_(...TRUNCATED) | {
"backend": "litellm",
"model_name": "hosted_vllm/TAUR-dev/M-r1_distill_baseline-rl",
"n_responses": 4
} | [
false,
false,
false,
false
] | [
"5134440000",
"5187695272",
null,
"5134440000"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 10, \"non_overlapping_spans\": 10, \"span_(...TRUNCATED) | "[{\"evaluation_method\": \"legacy\", \"legacy_result\": false}, {\"evaluation_method\": \"legacy\",(...TRUNCATED) | [[false,false,false,false,false,false,false,false,false,false],[false,false,false,false,false,false](...TRUNCATED) | [["(your answer)","5134440000","(your answer)","(your answer)","5134440000","(your answer)","5134440(...TRUNCATED) | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 2410, \"span_text\": \"(you(...TRUNCATED) | "[[{\"evaluation_method\": \"legacy\", \"legacy_result\": false}, {\"evaluation_method\": \"legacy\"(...TRUNCATED) | {"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED) | 2025-11-03 | test | main | TAUR-dev/M-r1_distill_baseline-rl | 0 | eval_rl | 1 | 2025-11-03T00:55:17.390505 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1distill_rl-longmult_5dig-eval_rl |
87369 x 14157 | 1236882933 | longmult_5dig | longmult | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"metadata\": \"{\\\"arg1\\\": 87369, \\\"arg2\\\": 14157, \\\"solution\\\": 1236882933}\", \"task(...TRUNCATED) | test | {"arg1": 87369, "arg2": 14157, "solution": 1236882933} | ["<think>\nI need to multiply 87369 by 14157. However, before I do that, let me consider if there is(...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {"api_url":"http://127.0.0.1:35419/v1","backend":"litellm","chat_template_applied":true,"generation_(...TRUNCATED) | {
"backend": "litellm",
"model_name": "hosted_vllm/TAUR-dev/M-r1_distill_baseline-rl",
"n_responses": 4
} | [
false,
false,
false,
false
] | [
"87369 * 14157",
"1230701173",
"1222541033",
"1235822933"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 18, \"non_overlapping_spans\": 18, \"span_(...TRUNCATED) | "[{\"evaluation_method\": \"legacy\", \"legacy_result\": false}, {\"evaluation_method\": \"legacy\",(...TRUNCATED) | [[false,false,false,false,false,false,false,false,false,false,false,false,false,false,false,false,fa(...TRUNCATED) | [["(your answer)","(your answer)","(your answer)","和","(your answer)","87369 * 14157","87369 × 14(...TRUNCATED) | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 1871, \"span_text\": \"(you(...TRUNCATED) | "[[{\"evaluation_method\": \"legacy\", \"legacy_result\": false}, {\"evaluation_method\": \"legacy\"(...TRUNCATED) | {"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED) | 2025-11-03 | test | main | TAUR-dev/M-r1_distill_baseline-rl | 0 | eval_rl | 1 | 2025-11-03T00:55:17.390507 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1distill_rl-longmult_5dig-eval_rl |
52577 x 84823 | 4459738871 | longmult_5dig | longmult | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"metadata\": \"{\\\"arg1\\\": 52577, \\\"arg2\\\": 84823, \\\"solution\\\": 4459738871}\", \"task(...TRUNCATED) | test | {"arg1": 52577, "arg2": 84823, "solution": 4459738871} | ["<think>\nI need to multiply these two numbers: 52577 and 84823. Since they are both very large num(...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {"api_url":"http://127.0.0.1:35419/v1","backend":"litellm","chat_template_applied":true,"generation_(...TRUNCATED) | {
"backend": "litellm",
"model_name": "hosted_vllm/TAUR-dev/M-r1_distill_baseline-rl",
"n_responses": 4
} | [
false,
false,
false,
false
] | [
"4499998301",
"4427662735",
"4491601001",
"4280605751"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 7, \"non_overlapping_spans\": 7, \"span_st(...TRUNCATED) | "[{\"evaluation_method\": \"legacy\", \"legacy_result\": false}, {\"evaluation_method\": \"legacy\",(...TRUNCATED) | [[false,false,false,false,false,false,false],[false,false,false,false,false,false,false,false],[fals(...TRUNCATED) | [["(your answer)","4499998301","4499998301","(your answer)","4499998301","(your answer)","4499998301(...TRUNCATED) | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 976, \"span_text\": \"(your(...TRUNCATED) | "[[{\"evaluation_method\": \"legacy\", \"legacy_result\": false}, {\"evaluation_method\": \"legacy\"(...TRUNCATED) | {"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED) | 2025-11-03 | test | main | TAUR-dev/M-r1_distill_baseline-rl | 0 | eval_rl | 1 | 2025-11-03T00:55:17.390508 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1distill_rl-longmult_5dig-eval_rl |
28441 x 57792 | 1643662272 | longmult_5dig | longmult | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"metadata\": \"{\\\"arg1\\\": 28441, \\\"arg2\\\": 57792, \\\"solution\\\": 1643662272}\", \"task(...TRUNCATED) | test | {"arg1": 28441, "arg2": 57792, "solution": 1643662272} | ["<think>\nI need to multiply 28441 by 57792. Since these numbers are both very large, I should look(...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {"api_url":"http://127.0.0.1:35419/v1","backend":"litellm","chat_template_applied":true,"generation_(...TRUNCATED) | {
"backend": "litellm",
"model_name": "hosted_vllm/TAUR-dev/M-r1_distill_baseline-rl",
"n_responses": 4
} | [
false,
false,
false,
false
] | [
"161842112881",
"16555353222",
"1655748432",
"1630136352"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 5, \"non_overlapping_spans\": 5, \"span_st(...TRUNCATED) | "[{\"evaluation_method\": \"legacy\", \"legacy_result\": false}, {\"evaluation_method\": \"legacy\",(...TRUNCATED) | [[false,false,false,false,false],[false,false,false,false],[false],[false,false,false,false,false,fa(...TRUNCATED) | [["(your answer)","161842112881","161842112881","(your answer)","161842112881"],["your answer","1655(...TRUNCATED) | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 2361, \"span_text\": \"(you(...TRUNCATED) | "[[{\"evaluation_method\": \"legacy\", \"legacy_result\": false}, {\"evaluation_method\": \"legacy\"(...TRUNCATED) | {"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED) | 2025-11-03 | test | main | TAUR-dev/M-r1_distill_baseline-rl | 0 | eval_rl | 1 | 2025-11-03T00:55:17.390510 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1distill_rl-longmult_5dig-eval_rl |
81212 x 52484 | 4262330608 | longmult_5dig | longmult | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"metadata\": \"{\\\"arg1\\\": 81212, \\\"arg2\\\": 52484, \\\"solution\\\": 4262330608}\", \"task(...TRUNCATED) | test | {"arg1": 81212, "arg2": 52484, "solution": 4262330608} | ["<think>\nI need to multiply 81212 by 52484 and provide the result.\n\nFirst, I should consider the(...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {"api_url":"http://127.0.0.1:35419/v1","backend":"litellm","chat_template_applied":true,"generation_(...TRUNCATED) | {
"backend": "litellm",
"model_name": "hosted_vllm/TAUR-dev/M-r1_distill_baseline-rl",
"n_responses": 4
} | [
false,
false,
false,
false
] | [
"406384848",
"4273966688",
"426226388",
"4287556088"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 7, \"non_overlapping_spans\": 7, \"span_st(...TRUNCATED) | "[{\"evaluation_method\": \"legacy\", \"legacy_result\": false}, {\"evaluation_method\": \"legacy\",(...TRUNCATED) | [[false,false,false,false,false,false,false],[false,false,false,false,false,false,false,false,false](...TRUNCATED) | [["(your answer)","406384848","(your answer)","406384848","(your answer)","406384848","406384848"],[(...TRUNCATED) | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 985, \"span_text\": \"(your(...TRUNCATED) | "[[{\"evaluation_method\": \"legacy\", \"legacy_result\": false}, {\"evaluation_method\": \"legacy\"(...TRUNCATED) | {"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED) | 2025-11-03 | test | main | TAUR-dev/M-r1_distill_baseline-rl | 0 | eval_rl | 1 | 2025-11-03T00:55:17.390512 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1distill_rl-longmult_5dig-eval_rl |
75436 x 27876 | 2102853936 | longmult_5dig | longmult | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"metadata\": \"{\\\"arg1\\\": 75436, \\\"arg2\\\": 27876, \\\"solution\\\": 2102853936}\", \"task(...TRUNCATED) | test | {"arg1": 75436, "arg2": 27876, "solution": 2102853936} | ["<think>\nI need to multiply 75436 by 27876. Since these numbers are both quite large, I shouldn't (...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {"api_url":"http://127.0.0.1:35419/v1","backend":"litellm","chat_template_applied":true,"generation_(...TRUNCATED) | {
"backend": "litellm",
"model_name": "hosted_vllm/TAUR-dev/M-r1_distill_baseline-rl",
"n_responses": 4
} | [
false,
false,
false,
false
] | [
"2109996896",
"733556336",
"2099999376",
"2100000000"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 3, \"non_overlapping_spans\": 3, \"span_st(...TRUNCATED) | "[{\"evaluation_method\": \"legacy\", \"legacy_result\": false}, {\"evaluation_method\": \"legacy\",(...TRUNCATED) | [[false,false,false],[false,false,false,false,false,false,false],[false,false,false,false,false,fals(...TRUNCATED) | [["(your answer)","2109996896","2109996896"],["...","2103655056","2103655056","(your answer)","21036(...TRUNCATED) | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 888, \"span_text\": \"(your(...TRUNCATED) | "[[{\"evaluation_method\": \"legacy\", \"legacy_result\": false}, {\"evaluation_method\": \"legacy\"(...TRUNCATED) | {"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED) | 2025-11-03 | test | main | TAUR-dev/M-r1_distill_baseline-rl | 0 | eval_rl | 1 | 2025-11-03T00:55:17.390513 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1distill_rl-longmult_5dig-eval_rl |
42929 x 73055 | 3136178095 | longmult_5dig | longmult | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"metadata\": \"{\\\"arg1\\\": 42929, \\\"arg2\\\": 73055, \\\"solution\\\": 3136178095}\", \"task(...TRUNCATED) | test | {"arg1": 42929, "arg2": 73055, "solution": 3136178095} | ["<think>\nI need to multiply these two numbers: 42929 and 73055. Since they are both fairly large, (...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {"api_url":"http://127.0.0.1:35419/v1","backend":"litellm","chat_template_applied":true,"generation_(...TRUNCATED) | {
"backend": "litellm",
"model_name": "hosted_vllm/TAUR-dev/M-r1_distill_baseline-rl",
"n_responses": 4
} | [
false,
false,
false,
false
] | [
"3136887045",
"3169999905",
"3126657945",
"3126827000"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 5, \"non_overlapping_spans\": 5, \"span_st(...TRUNCATED) | "[{\"evaluation_method\": \"legacy\", \"legacy_result\": false}, {\"evaluation_method\": \"legacy\",(...TRUNCATED) | [[false,false,false,false,false],[false,false,false],[false,false,false,false,false,false,false,fals(...TRUNCATED) | [["(your answer)","(your answer)","3136887045","3136887045","3136887045"],["(your answer)","31699999(...TRUNCATED) | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 638, \"span_text\": \"(your(...TRUNCATED) | "[[{\"evaluation_method\": \"legacy\", \"legacy_result\": false}, {\"evaluation_method\": \"legacy\"(...TRUNCATED) | {"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED) | 2025-11-03 | test | main | TAUR-dev/M-r1_distill_baseline-rl | 0 | eval_rl | 1 | 2025-11-03T00:55:17.390515 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1distill_rl-longmult_5dig-eval_rl |
96109 x 64265 | 6176444885 | longmult_5dig | longmult | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"metadata\": \"{\\\"arg1\\\": 96109, \\\"arg2\\\": 64265, \\\"solution\\\": 6176444885}\", \"task(...TRUNCATED) | test | {"arg1": 96109, "arg2": 64265, "solution": 6176444885} | ["<think>\nI need to multiply 96109 by 64265 and provide the result.\n\nFirst, I should consider the(...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {"api_url":"http://127.0.0.1:35419/v1","backend":"litellm","chat_template_applied":true,"generation_(...TRUNCATED) | {
"backend": "litellm",
"model_name": "hosted_vllm/TAUR-dev/M-r1_distill_baseline-rl",
"n_responses": 4
} | [
false,
false,
false,
false
] | [
"6285619595",
"6179621085",
"6182323395",
"6193193535"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 5, \"non_overlapping_spans\": 5, \"span_st(...TRUNCATED) | "[{\"evaluation_method\": \"legacy\", \"legacy_result\": false}, {\"evaluation_method\": \"legacy\",(...TRUNCATED) | [[false,false,false,false,false],[false,false,false,false,false,false,false],[false,false,false,fals(...TRUNCATED) | [["(your answer)","6285619595","(your answer)","6285619595","6285619595"],["(your answer)","(your an(...TRUNCATED) | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 1773, \"span_text\": \"(you(...TRUNCATED) | "[[{\"evaluation_method\": \"legacy\", \"legacy_result\": false}, {\"evaluation_method\": \"legacy\"(...TRUNCATED) | {"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED) | 2025-11-03 | test | main | TAUR-dev/M-r1_distill_baseline-rl | 0 | eval_rl | 1 | 2025-11-03T00:55:17.390516 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1distill_rl-longmult_5dig-eval_rl |
Experiment Tracker: FinEval_16k_fulleval_3args_r1distill_rl-longmult_5dig
Experiment Description: Evaluation experiment for task longmult_5dig from FinEval_16k_fulleval_3args_r1distill_rl
Start Time: 2025-11-03T00:17:04.369291
Tracker Dataset: TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1distill_rl-longmult_5dig__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_r1distill_rl-longmult_5dig__v1', 'experiment_metadata')
# Load complete training datasets
sft_data = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1distill_rl-longmult_5dig__v1', 'training_data__sft')
sft_metadata = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1distill_rl-longmult_5dig__v1', 'training_data__sft_metadata')
# Load complete configurations
sft_hyperparams = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1distill_rl-longmult_5dig__v1', 'hyperparameters__sft')
rl_hyperparams = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1distill_rl-longmult_5dig__v1', 'hyperparameters__rl')
# Load stage-specific logs
sft_logs = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1distill_rl-longmult_5dig__v1', 'logs__sft')
rl_logs = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1distill_rl-longmult_5dig__v1', 'logs__rl')
# Load evaluation results with annotations
sft_eval_results = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1distill_rl-longmult_5dig__v1', 'evals_eval_sft')
rl_eval_results = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1distill_rl-longmult_5dig__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_r1distill_rl-longmult_5dig - {stage_name} - {SFT/RL}
Generated by SkillFactory Experiment Management System All artifacts uploaded immediately as stages complete with perfect data provenance
- Downloads last month
- 3