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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
4793 x 9915 | 47522595 | longmult_4dig | 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?\n4793 x 9915\n\nGive your answer in the following format:\n<answer>\n(... | [] | [] | {"metadata": "{\"arg1\": 4793, \"arg2\": 9915, \"solution\": 47522595}", "task_source": "longmult"} | test | {"arg1": 4793, "arg2": 9915, "solution": 47522595} | [
"<think>\nI need to multiply 4793 by 9915. Since these numbers are both large, I should consider how to approach this multiplication.\n\nFirst, let me write down the numbers:\n\n4793\n\nx 9915\n\nI notice that 9915 can be broken down into 10000 - 885 or something, but for simplicity, I'll multiply directly.\n\nHowe... | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {
"api_url": "http://127.0.0.1:41641/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
] | [
"47075845",
"47075845",
"4,800,000",
"(your answer)"
] | [{"extraction_type": "final", "total_spans_found": 3, "non_overlapping_spans": 3, "span_start": 5041, "span_end": 5051, "original_span": "47075845"}, {"extraction_type": "final", "total_spans_found": 3, "non_overlapping_spans": 3, "span_start": 4568, "span_end": 4578, "original_span": "47075845"}, {"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
]
] | [
[
"(your answer)",
"47,075,845",
"47075845"
],
[
"47,075,845",
"(your answer)",
"47075845"
],
[
"(your answer)",
"(your answer)",
"(your answer)",
"(your answer)",
"4,800,000",
"(your answer)",
"4,800,000",
"4,800,000"
],
[
"(your answer)"
]
... | [[{"pattern_used": "answer tag", "confidence": 1.0, "position": 3523, "span_text": "(your answer)", "extraction_type": "internal", "span_start": 3523, "span_end": 3538, "original_span": "(your answer)"}, {"pattern_used": "answer tag", "confidence": 1.0, "position": 3816, "span_text": "47,075,845", "extraction_type": "i... | [[{"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 | 2025-11-03T00:16:55.136267 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1distill_rl-longmult_4dig-eval_rl |
4507 x 8243 | 37151201 | longmult_4dig | 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?\n4507 x 8243\n\nGive your answer in the following format:\n<answer>\n(... | [] | [] | {"metadata": "{\"arg1\": 4507, \"arg2\": 8243, \"solution\": 37151201}", "task_source": "longmult"} | test | {"arg1": 4507, "arg2": 8243, "solution": 37151201} | [
"<think>\nI need to multiply 4507 by 8243. Since these numbers are both fairly large, I shouldn't need a calculator for this. Let me start by looking at the numbers.\n\n4507 and 8243. Both are three-digit and four-digit numbers, respectively. The first number has 4 and 5, while the second has 8 and 2. So basically,... | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {
"api_url": "http://127.0.0.1:41641/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
] | [
"37160511",
"4823590",
"3923342",
"37156701"
] | [{"extraction_type": "final", "total_spans_found": 5, "non_overlapping_spans": 5, "span_start": 4072, "span_end": 4080, "original_span": "37160511"}, {"extraction_type": "final", "total_spans_found": 6, "non_overlapping_spans": 6, "span_start": 9142, "span_end": 9151, "original_span": "4823590"}, {"extraction_type": "f... | [{"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
]
] | [
[
"37160511",
"(your answer)",
"37160511",
"(your answer)",
"37160511"
],
[
"(your answer)",
"4823590",
"4823590",
"(your answer)",
"4823590",
"4823590"
],
[
"(your answer)",
"3923342",
"(your answer)",
"(your answer)",
"3923342",
"(your an... | [[{"pattern_used": "answer tag", "confidence": 1.0, "position": 2276, "span_text": "37160511", "extraction_type": "internal", "span_start": 2276, "span_end": 2284, "original_span": "37160511"}, {"pattern_used": "answer tag", "confidence": 1.0, "position": 2447, "span_text": "(your answer)", "extraction_type": "internal... | [[{"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 | 2025-11-03T00:16:55.136275 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1distill_rl-longmult_4dig-eval_rl |
7645 x 2867 | 21918215 | longmult_4dig | 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?\n7645 x 2867\n\nGive your answer in the following format:\n<answer>\n(... | [] | [] | {"metadata": "{\"arg1\": 7645, \"arg2\": 2867, \"solution\": 21918215}", "task_source": "longmult"} | test | {"arg1": 7645, "arg2": 2867, "solution": 21918215} | [
"<think>\nI need to multiply 7645 by 2867. Since these numbers are both fairly large, I shouldn't need a calculator for this. Let me start by multiplying them step by step.\n\nFirst, I should consider the multiplicands: 7645 and 2867. Both are three-digit and two-digit numbers, respectively.\n\nOne thing to notice:... | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {
"api_url": "http://127.0.0.1:41641/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
] | [
"21873715",
"21861045",
"21787071",
"22340885"
] | [{"extraction_type": "final", "total_spans_found": 11, "non_overlapping_spans": 11, "span_start": 5967, "span_end": 5977, "original_span": "21873715"}, {"extraction_type": "final", "total_spans_found": 4, "non_overlapping_spans": 4, "span_start": 2600, "span_end": 2610, "original_span": "21861045"}, {"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,
false
]
] | [
[
"(your answer)",
"21873715",
"(your answer)",
"21873715",
"(your answer)",
"21873715",
"(your answer)",
"21873715",
"(your answer)",
"21873715",
"21873715"
],
[
"(your answer)",
"(your answer)",
"21861045",
"21861045"
],
[
"21787071",
"(y... | [[{"pattern_used": "answer tag", "confidence": 1.0, "position": 3041, "span_text": "(your answer)", "extraction_type": "internal", "span_start": 3041, "span_end": 3056, "original_span": "(your answer)"}, {"pattern_used": "answer tag", "confidence": 1.0, "position": 3533, "span_text": "21873715", "extraction_type": "int... | [[{"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 | 2025-11-03T00:16:55.136278 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1distill_rl-longmult_4dig-eval_rl |
8344 x 6174 | 51515856 | longmult_4dig | 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?\n8344 x 6174\n\nGive your answer in the following format:\n<answer>\n(... | [] | [] | {"metadata": "{\"arg1\": 8344, \"arg2\": 6174, \"solution\": 51515856}", "task_source": "longmult"} | test | {"arg1": 8344, "arg2": 6174, "solution": 51515856} | [
"<think>\nI need to multiply 8344 by 6174. Since these numbers are both large, I shouldn't manually compute the product. Instead, I can use estimation or long multiplication, but for accuracy, I'll use long multiplication.\n\nLong multiplication involves multiplying each digit of one number by each digit of the oth... | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {
"api_url": "http://127.0.0.1:41641/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
] | [
"50683056",
"50516636",
"51839136",
"51524976"
] | [{"extraction_type": "final", "total_spans_found": 5, "non_overlapping_spans": 5, "span_start": 8906, "span_end": 8914, "original_span": "50683056"}, {"extraction_type": "final", "total_spans_found": 6, "non_overlapping_spans": 6, "span_start": 8003, "span_end": 8011, "original_span": "50516636"}, {"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,
false,
false,
... | [
[
"...",
"(your answer)",
"(your answer)",
"50683056",
"50683056"
],
[
"(your answer)",
"(your answer)",
"(your answer)",
"50516636",
"(your answer)",
"50516636"
],
[
"(your answer)",
"51839136",
"(your answer)",
"(your answer)",
"51839136",
... | [[{"pattern_used": "answer tag", "confidence": 1.0, "position": 5060, "span_text": "...", "extraction_type": "internal", "span_start": 5060, "span_end": 5064, "original_span": "..."}, {"pattern_used": "answer tag", "confidence": 1.0, "position": 5413, "span_text": "(your answer)", "extraction_type": "internal", "span_s... | [[{"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 | 2025-11-03T00:16:55.136279 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1distill_rl-longmult_4dig-eval_rl |
5560 x 2589 | 14394840 | longmult_4dig | longmult | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"metadata\": \"{\\\"arg1\\\": 5560, \\\"arg2\\\": 2589, \\\"solution\\\": 14394840}\", \"task_sou(...TRUNCATED) | test | {"arg1": 5560, "arg2": 2589, "solution": 14394840} | ["<think>\nI need to multiply 5560 by 2589. Since these numbers are both large, I can estimate or us(...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {"api_url":"http://127.0.0.1:41641/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
] | [
"14167240",
"14,399,080",
"14397040",
"14388880"
] | "[{\"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)","(your answer)","14","14167240","14167240"],["(your answer)","14,399,080"],["(your(...TRUNCATED) | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 812, \"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 | 2025-11-03T00:16:55.136281 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1distill_rl-longmult_4dig-eval_rl |
5291 x 7587 | 40142817 | longmult_4dig | longmult | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"metadata\": \"{\\\"arg1\\\": 5291, \\\"arg2\\\": 7587, \\\"solution\\\": 40142817}\", \"task_sou(...TRUNCATED) | test | {"arg1": 5291, "arg2": 7587, "solution": 40142817} | ["<think>\nI need to multiply 5291 by 7587. Since these numbers are both quite large, I should look (...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {"api_url":"http://127.0.0.1:41641/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
] | [
"4533843",
"39461397",
"40137827",
"101835037"
] | "[{\"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)","4533843","4533843"],["(your answer)","(your answer)","39461397","(your answer)","(...TRUNCATED) | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 4519, \"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 | 2025-11-03T00:16:55.136282 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1distill_rl-longmult_4dig-eval_rl |
8481 x 3516 | 29819196 | longmult_4dig | longmult | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"metadata\": \"{\\\"arg1\\\": 8481, \\\"arg2\\\": 3516, \\\"solution\\\": 29819196}\", \"task_sou(...TRUNCATED) | test | {"arg1": 8481, "arg2": 3516, "solution": 29819196} | ["<think>\nI need to multiply 8481 by 3516. Since these numbers are both large, I shouldn't manually(...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {"api_url":"http://127.0.0.1:41641/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
] | [
"29818776",
"28154917",
"3000000",
"29403000"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 8, \"non_overlapping_spans\": 8, \"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) | [["29818776","(your answer)","(your answer)","29818776","(your answer)","29818776","(your answer)","(...TRUNCATED) | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 2053, \"span_text\": \"2981(...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 | 2025-11-03T00:16:55.136284 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1distill_rl-longmult_4dig-eval_rl |
7176 x 7208 | 51724608 | longmult_4dig | longmult | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"metadata\": \"{\\\"arg1\\\": 7176, \\\"arg2\\\": 7208, \\\"solution\\\": 51724608}\", \"task_sou(...TRUNCATED) | test | {"arg1": 7176, "arg2": 7208, "solution": 51724608} | ["<think>\nI need to multiply 7176 by 7208. Since both numbers are relatively large, I shouldn't man(...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {"api_url":"http://127.0.0.1:41641/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
] | [
"51749056",
"51324608",
"51732308",
"51724416"
] | "[{\"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,fa(...TRUNCATED) | [["(your answer)","(your answer)","51749056"],["(your answer)","51261192","(your answer)","51324608"(...TRUNCATED) | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 5619, \"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 | 2025-11-03T00:16:55.136285 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1distill_rl-longmult_4dig-eval_rl |
7493 x 2187 | 16387191 | longmult_4dig | longmult | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"metadata\": \"{\\\"arg1\\\": 7493, \\\"arg2\\\": 2187, \\\"solution\\\": 16387191}\", \"task_sou(...TRUNCATED) | test | {"arg1": 7493, "arg2": 2187, "solution": 16387191} | ["<think>\nI need to multiply 7493 by 2187. Since these numbers are both relatively large, I should (...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {"api_url":"http://127.0.0.1:41641/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
] | [
"16500001",
"16385701",
"16387411",
"(your answer)"
] | "[{\"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>","16500001","(your answer)","16500001","16500001"],["16385701","(your answer)","163(...TRUNCATED) | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 3003, \"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 | 2025-11-03T00:16:55.136287 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1distill_rl-longmult_4dig-eval_rl |
5644 x 8077 | 45586588 | longmult_4dig | longmult | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"metadata\": \"{\\\"arg1\\\": 5644, \\\"arg2\\\": 8077, \\\"solution\\\": 45586588}\", \"task_sou(...TRUNCATED) | test | {"arg1": 5644, "arg2": 8077, "solution": 45586588} | ["<think>\nI need to multiply 5644 by 8077. Let me start by looking at the numbers and seeing if the(...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {"api_url":"http://127.0.0.1:41641/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
] | [
"45585488",
"45595208",
"45835508",
"45643488"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 6, \"non_overlapping_spans\": 6, \"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)","45585488","(your answer)","45585488","(45585488)","45585488"],["45595208","(your (...TRUNCATED) | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 5077, \"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 | 2025-11-03T00:16:55.136288 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1distill_rl-longmult_4dig-eval_rl |
End of preview. Expand in Data Studio
Experiment Tracker: FinEval_16k_fulleval_3args_r1distill_rl-longmult_4dig
Experiment Description: Evaluation experiment for task longmult_4dig from FinEval_16k_fulleval_3args_r1distill_rl
Start Time: 2025-11-02T23:38:55.082833
Tracker Dataset: TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1distill_rl-longmult_4dig__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_4dig__v1', 'experiment_metadata')
# Load complete training datasets
sft_data = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1distill_rl-longmult_4dig__v1', 'training_data__sft')
sft_metadata = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1distill_rl-longmult_4dig__v1', 'training_data__sft_metadata')
# Load complete configurations
sft_hyperparams = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1distill_rl-longmult_4dig__v1', 'hyperparameters__sft')
rl_hyperparams = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1distill_rl-longmult_4dig__v1', 'hyperparameters__rl')
# Load stage-specific logs
sft_logs = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1distill_rl-longmult_4dig__v1', 'logs__sft')
rl_logs = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1distill_rl-longmult_4dig__v1', 'logs__rl')
# Load evaluation results with annotations
sft_eval_results = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1distill_rl-longmult_4dig__v1', 'evals_eval_sft')
rl_eval_results = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1distill_rl-longmult_4dig__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_4dig - {stage_name} - {SFT/RL}
Generated by SkillFactory Experiment Management System All artifacts uploaded immediately as stages complete with perfect data provenance
- Downloads last month
- 7