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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
30 x 62 | 1860 | longmult_2dig | 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?\n30 x 62\n\nGive your answer in the following format:\n<answer>\n(your... | [] | [] | {"metadata": "{\"arg1\": 30, \"arg2\": 62, \"solution\": 1860}", "task_source": "longmult"} | test | {"arg1": 30, "arg2": 62, "solution": 1860} | [
"<think>\nI need to solve the multiplication equation 30 x 62. Let me break it down.\n\nFirst, I can think of 30 as 3 tens. So, I have 3 tens times 62.\n\n3 tens = 30\n\nNow, 30 x 62. This is the same as (30 x 60) + (30 x 2).\n\nLet me calculate that:\n\n30 x 60 = 1800\n\n30 x 2 = 60\n\nSo, 1800 + 60 = 1860\n\nBut ... | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {
"api_url": "http://127.0.0.1:55769/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
} | [
true,
true,
true,
true
] | [
"1860",
"1860",
"1860",
"1860"
] | [{"extraction_type": "final", "total_spans_found": 5, "non_overlapping_spans": 5, "span_start": 2249, "span_end": 2253, "original_span": "1860"}, {"extraction_type": "final", "total_spans_found": 6, "non_overlapping_spans": 6, "span_start": 2952, "span_end": 2956, "original_span": "1860"}, {"extraction_type": "final", ... | [{"evaluation_method": "legacy", "legacy_result": true}, {"evaluation_method": "legacy", "legacy_result": true}, {"evaluation_method": "legacy", "legacy_result": true}, {"evaluation_method": "legacy", "legacy_result": true}] | [
[
false,
true,
true,
false,
true
],
[
false,
true,
true,
false,
true,
true
],
[
false,
true,
true,
false,
true,
true,
false,
true,
false,
true
],
[
false,
true,
false,
true,
true,
true
]
] | [
[
"(your answer)",
"1860",
"1860",
"(your answer)",
"1860"
],
[
"(your answer)",
"1860",
"1860",
"(your answer)",
"1860",
"1860"
],
[
"(your answer)",
"1860",
"1860",
"(your answer)",
"1860",
"1860",
"(your answer)",
"1860",
"85... | [[{"pattern_used": "answer tag", "confidence": 1.0, "position": 930, "span_text": "(your answer)", "extraction_type": "internal", "span_start": 930, "span_end": 943, "original_span": "(your answer)"}, {"pattern_used": "answer tag", "confidence": 1.0, "position": 1027, "span_text": "1860", "extraction_type": "internal",... | [[{"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "legacy_result": true}, {"evaluation_method": "legacy", "legacy_result": true}, {"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "legacy_result": true}], [{"evaluation_method": "legacy", "l... | {
"flips_by": [
1,
1,
3,
1
],
"flips_total": 6,
"num_correct": 4,
"pass_at_n": 1,
"percent_correct": 1,
"skill_count": {
"answer_revision": [
0,
0,
0,
0
],
"best_of_n": [
0,
0,
0,
0
],
"reflect_close": [
0,
0,
... | 2025-11-02 | test | main | TAUR-dev/M-r1_distill_baseline-rl | 0 | eval_rl | 1 | 2025-11-02T22:59:46.794266 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1distill_rl-longmult_2dig-eval_rl |
33 x 67 | 2211 | longmult_2dig | 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?\n33 x 67\n\nGive your answer in the following format:\n<answer>\n(your... | [] | [] | {"metadata": "{\"arg1\": 33, \"arg2\": 67, \"solution\": 2211}", "task_source": "longmult"} | test | {"arg1": 33, "arg2": 67, "solution": 2211} | [
"<think>\nI need to multiply 33 by 67. Let me start with simple multiplication facts if possible.\n\nFor example, 30 times something. 30 times 67 is 2010. But I have a 3 left over, so that would be 2010 + 3 = 2013. Not quite 33.\n\n33 is 3 more than 30, so maybe (30 + 3) * 67 = 30*67 + 3*67 = 2010 + 201 = 2211. Sti... | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {
"api_url": "http://127.0.0.1:55769/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
} | [
true,
true,
true,
true
] | [
"2211",
"2211",
"2211",
"2211"
] | [{"extraction_type": "final", "total_spans_found": 12, "non_overlapping_spans": 12, "span_start": 5521, "span_end": 5525, "original_span": "2211"}, {"extraction_type": "final", "total_spans_found": 5, "non_overlapping_spans": 5, "span_start": 4277, "span_end": 4281, "original_span": "2211"}, {"extraction_type": "final"... | [{"evaluation_method": "legacy", "legacy_result": true}, {"evaluation_method": "legacy", "legacy_result": true}, {"evaluation_method": "legacy", "legacy_result": true}, {"evaluation_method": "legacy", "legacy_result": true}] | [
[
false,
false,
true,
false,
true,
false,
true,
false,
true,
true,
false,
true
],
[
false,
true,
true,
false,
true
],
[
true,
false,
false,
false,
true,
true,
false,
true
],
[
false,
true,
tru... | [
[
"(your answer)",
"(your answer)",
"2211",
"(your answer)",
"2211",
"(your answer)",
"2211",
"(your answer)",
"2211",
"2211",
"(your answer)",
"2211"
],
[
"(your answer)",
"2211",
"2211",
"(your answer)",
"2211"
],
[
"2211",
"(your... | [[{"pattern_used": "answer tag", "confidence": 1.0, "position": 1249, "span_text": "(your answer)", "extraction_type": "internal", "span_start": 1249, "span_end": 1264, "original_span": "(your answer)"}, {"pattern_used": "answer tag", "confidence": 1.0, "position": 2011, "span_text": "(your answer)", "extraction_type":... | [[{"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "legacy_result": true}, {"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "legacy_result": true}, {"evaluation_method": "legacy", "le... | {
"flips_by": [
4,
1,
2,
2
],
"flips_total": 9,
"num_correct": 4,
"pass_at_n": 1,
"percent_correct": 1,
"skill_count": {
"answer_revision": [
0,
0,
0,
0
],
"best_of_n": [
0,
0,
0,
0
],
"reflect_close": [
0,
0,
... | 2025-11-02 | test | main | TAUR-dev/M-r1_distill_baseline-rl | 0 | eval_rl | 1 | 2025-11-02T22:59:46.794275 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1distill_rl-longmult_2dig-eval_rl |
74 x 60 | 4440 | longmult_2dig | 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?\n74 x 60\n\nGive your answer in the following format:\n<answer>\n(your... | [] | [] | {"metadata": "{\"arg1\": 74, \"arg2\": 60, \"solution\": 4440}", "task_source": "longmult"} | test | {"arg1": 74, "arg2": 60, "solution": 4440} | [
"<think>\nI need to solve the multiplication equation 74 x 60.\n\nFirst, I should consider what 74 x 60 means. I can break it down into simpler parts.\n\nOne way to think about it is: 70 x 60 = 4200, and 4 x 60 = 240. But that doesn't seem right.\n\nAnother approach: 74 x 60 = (70 + 4) x 60 = 70 x 60 + 4 x 60.\n\nN... | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {
"api_url": "http://127.0.0.1:55769/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
} | [
true,
true,
true,
true
] | [
"4440",
"4440",
"4440",
"4440"
] | [{"extraction_type": "final", "total_spans_found": 5, "non_overlapping_spans": 5, "span_start": 2153, "span_end": 2157, "original_span": "4440"}, {"extraction_type": "final", "total_spans_found": 5, "non_overlapping_spans": 5, "span_start": 3278, "span_end": 3284, "original_span": "4440"}, {"extraction_type": "final", ... | [{"evaluation_method": "legacy", "legacy_result": true}, {"evaluation_method": "legacy", "legacy_result": true}, {"evaluation_method": "legacy", "legacy_result": true}, {"evaluation_method": "legacy", "legacy_result": true}] | [
[
false,
true,
true,
false,
true
],
[
false,
true,
false,
true,
true
],
[
false,
false,
true,
false,
true,
false,
true
],
[
false,
true,
true,
true
]
] | [
[
"(your answer)",
"4440",
"4440",
"158",
"4440"
],
[
"(your answer)",
"4440",
"(your answer)",
"4440",
"4440"
],
[
"(your answer)",
"your answer",
"4440",
"(your answer)",
"4440",
"(your answer)",
"4440"
],
[
"(your answer)",
"... | [[{"pattern_used": "answer tag", "confidence": 1.0, "position": 790, "span_text": "(your answer)", "extraction_type": "internal", "span_start": 790, "span_end": 803, "original_span": "(your answer)"}, {"pattern_used": "answer tag", "confidence": 1.0, "position": 1011, "span_text": "4440", "extraction_type": "internal",... | [[{"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "legacy_result": true}, {"evaluation_method": "legacy", "legacy_result": true}, {"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "legacy_result": true}], [{"evaluation_method": "legacy", "l... | {
"flips_by": [
1,
1,
2,
0
],
"flips_total": 4,
"num_correct": 4,
"pass_at_n": 1,
"percent_correct": 1,
"skill_count": {
"answer_revision": [
0,
0,
0,
0
],
"best_of_n": [
0,
0,
0,
0
],
"reflect_close": [
0,
0,
... | 2025-11-02 | test | main | TAUR-dev/M-r1_distill_baseline-rl | 0 | eval_rl | 1 | 2025-11-02T22:59:46.794277 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1distill_rl-longmult_2dig-eval_rl |
69 x 45 | 3105 | longmult_2dig | 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?\n69 x 45\n\nGive your answer in the following format:\n<answer>\n(your... | [] | [] | {"metadata": "{\"arg1\": 69, \"arg2\": 45, \"solution\": 3105}", "task_source": "longmult"} | test | {"arg1": 69, "arg2": 45, "solution": 3105} | [
"<think>\nI need to multiply 69 by 45. Let me break it down to make it easier.\n\nFirst, I can think of 69 as 70 - 1, and 45 as 50 - 5. But that might not be the best approach. Instead, I can multiply 70 by 45 directly, which is 3150, but then I have to subtract 69.\n\n70 * 45 = 3150\n\nNow, 69 * 45 = (70 * 45) - 7... | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {
"api_url": "http://127.0.0.1:55769/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,
true,
true,
true
] | [
"3081",
"3105",
"3105",
"3105"
] | [{"extraction_type": "final", "total_spans_found": 10, "non_overlapping_spans": 10, "span_start": 5115, "span_end": 5119, "original_span": "3081"}, {"extraction_type": "final", "total_spans_found": 8, "non_overlapping_spans": 8, "span_start": 4995, "span_end": 4999, "original_span": "3105"}, {"extraction_type": "final"... | [{"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "legacy_result": true}, {"evaluation_method": "legacy", "legacy_result": true}, {"evaluation_method": "legacy", "legacy_result": true}] | [
[
false,
false,
false,
false,
false,
false,
false,
false,
false,
false
],
[
false,
true,
false,
false,
false,
true,
true,
true
],
[
false,
true,
false,
true,
false,
true,
true,
false,
false,
true,... | [
[
"(your answer)",
"3081",
"3081",
"3081",
"(your answer)",
"3081",
"3081",
"(your answer)",
"3081",
"3081"
],
[
"(your answer)",
"3105",
"(your answer)",
"(your answer)",
"(your answer)",
"3105",
"3105",
"3105"
],
[
"(your answer)"... | [[{"pattern_used": "answer tag", "confidence": 1.0, "position": 744, "span_text": "(your answer)", "extraction_type": "internal", "span_start": 744, "span_end": 757, "original_span": "(your answer)"}, {"pattern_used": "answer tag", "confidence": 1.0, "position": 1428, "span_text": "3081", "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,
1,
3,
2
],
"flips_total": 6,
"num_correct": 3,
"pass_at_n": 1,
"percent_correct": 0.75,
"skill_count": {
"answer_revision": [
0,
0,
0,
0
],
"best_of_n": [
0,
0,
0,
0
],
"reflect_close": [
0,
... | 2025-11-02 | test | main | TAUR-dev/M-r1_distill_baseline-rl | 0 | eval_rl | 1 | 2025-11-02T22:59:46.794278 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1distill_rl-longmult_2dig-eval_rl |
73 x 71 | 5183 | longmult_2dig | 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?\n73 x 71\n\nGive your answer in the following format:\n<answer>\n(your... | [] | [] | {"metadata": "{\"arg1\": 73, \"arg2\": 71, \"solution\": 5183}", "task_source": "longmult"} | test | {"arg1": 73, "arg2": 71, "solution": 5183} | [
"<think>\nI need to multiply 73 by 71. Let me write it out:\n\n73 * 71\n\nI can think of this as (70 + 3) * (70 + 1)\n\nUsing the distributive property of multiplication over addition, I get:\n\n(70 * 70) + (70 * 1) + (3 * 70) + (3 * 1)\n\nNow, let me calculate each term:\n\n70 * 70 = 4900\n\n70 * 1 = 70\n\n3 * 70 ... | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {
"api_url": "http://127.0.0.1:55769/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
} | [
true,
true,
true,
true
] | [
"5183",
"5183",
"5183",
"5183"
] | [{"extraction_type": "final", "total_spans_found": 6, "non_overlapping_spans": 6, "span_start": 2461, "span_end": 2465, "original_span": "5183"}, {"extraction_type": "final", "total_spans_found": 9, "non_overlapping_spans": 9, "span_start": 4943, "span_end": 4947, "original_span": "5183"}, {"extraction_type": "final", ... | [{"evaluation_method": "legacy", "legacy_result": true}, {"evaluation_method": "legacy", "legacy_result": true}, {"evaluation_method": "legacy", "legacy_result": true}, {"evaluation_method": "legacy", "legacy_result": true}] | [
[
false,
false,
true,
false,
true,
true
],
[
true,
false,
true,
false,
true,
true,
true,
false,
true
],
[
false,
true,
false,
true,
true,
true,
true
],
[
false,
false,
false,
false,
false,
tru... | [
[
"(your answer)",
"(your answer)",
"5183",
"(your answer)",
"5183",
"5183"
],
[
"5183",
"(your answer)",
"5183",
"(your answer)",
"5183",
"5183",
"5183",
"(your answer)",
"5183"
],
[
"(your answer)",
"5183",
"(your answer)",
"5183"... | [[{"pattern_used": "answer tag", "confidence": 1.0, "position": 522, "span_text": "(your answer)", "extraction_type": "internal", "span_start": 522, "span_end": 535, "original_span": "(your answer)"}, {"pattern_used": "answer tag", "confidence": 1.0, "position": 648, "span_text": "(your answer)", "extraction_type": "in... | [[{"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "legacy_result": true}, {"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "legacy_result": true}, {"evaluation_method": "legacy", "le... | {
"flips_by": [
1,
3,
1,
1
],
"flips_total": 6,
"num_correct": 4,
"pass_at_n": 1,
"percent_correct": 1,
"skill_count": {
"answer_revision": [
0,
0,
0,
0
],
"best_of_n": [
0,
0,
0,
0
],
"reflect_close": [
0,
0,
... | 2025-11-02 | test | main | TAUR-dev/M-r1_distill_baseline-rl | 0 | eval_rl | 1 | 2025-11-02T22:59:46.794280 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1distill_rl-longmult_2dig-eval_rl |
59 x 36 | 2124 | longmult_2dig | 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?\n59 x 36\n\nGive your answer in the following format:\n<answer>\n(your... | [] | [] | {"metadata": "{\"arg1\": 59, \"arg2\": 36, \"solution\": 2124}", "task_source": "longmult"} | test | {"arg1": 59, "arg2": 36, "solution": 2124} | [
"<think>\nI need to multiply 59 by 36. Let me break it down for simplicity.\n\nFirst, I can think of 59 as 60 - 1, and 36 as 40 - 4. But that might not be the best approach. Instead, I can multiply 59 by 30 first, which is easier because 30 times something.\n\n59 multiplied by 30 is 1770. But I have to add 59 more,... | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {
"api_url": "http://127.0.0.1:55769/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
} | [
true,
true,
true,
true
] | [
"2124",
"2124",
"2124",
"2124"
] | [{"extraction_type": "final", "total_spans_found": 7, "non_overlapping_spans": 7, "span_start": 3650, "span_end": 3654, "original_span": "2124"}, {"extraction_type": "final", "total_spans_found": 6, "non_overlapping_spans": 6, "span_start": 5022, "span_end": 5026, "original_span": "2124"}, {"extraction_type": "final", ... | [{"evaluation_method": "legacy", "legacy_result": true}, {"evaluation_method": "legacy", "legacy_result": true}, {"evaluation_method": "legacy", "legacy_result": true}, {"evaluation_method": "legacy", "legacy_result": true}] | [
[
false,
false,
true,
true,
true,
true,
true
],
[
true,
false,
false,
true,
true,
true
],
[
false,
true,
false,
true,
false,
true,
false,
true,
false,
true,
true
],
[
false,
false,
false,
fals... | [
[
"(your answer)",
"(your answer)",
"2124",
"2124",
"2124",
"2124",
"2124"
],
[
"2124",
"(your answer)",
"(your answer)",
"2124",
"2124",
"2124"
],
[
"(your answer)",
"2124",
"(your answer)",
"2124",
"(your answer)",
"2124",
"(y... | [[{"pattern_used": "answer tag", "confidence": 1.0, "position": 1409, "span_text": "(your answer)", "extraction_type": "internal", "span_start": 1409, "span_end": 1424, "original_span": "(your answer)"}, {"pattern_used": "answer tag", "confidence": 1.0, "position": 1619, "span_text": "(your answer)", "extraction_type":... | [[{"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "legacy_result": false}, {"evaluation_method": "legacy", "legacy_result": true}, {"evaluation_method": "legacy", "legacy_result": true}, {"evaluation_method": "legacy", "legacy_result": true}, {"evaluation_method": "legacy", "leg... | {
"flips_by": [
0,
1,
4,
0
],
"flips_total": 5,
"num_correct": 4,
"pass_at_n": 1,
"percent_correct": 1,
"skill_count": {
"answer_revision": [
0,
0,
0,
0
],
"best_of_n": [
0,
0,
0,
0
],
"reflect_close": [
0,
0,
... | 2025-11-02 | test | main | TAUR-dev/M-r1_distill_baseline-rl | 0 | eval_rl | 1 | 2025-11-02T22:59:46.794282 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1distill_rl-longmult_2dig-eval_rl |
23 x 24 | 552 | longmult_2dig | longmult | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"metadata\": \"{\\\"arg1\\\": 23, \\\"arg2\\\": 24, \\\"solution\\\": 552}\", \"task_source\": \"(...TRUNCATED) | test | {"arg1": 23, "arg2": 24, "solution": 552} | ["<think>\nI need to solve the multiplication of 23 and 24. Let me write it out:\n\n23 * 24\n\nI can(...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {"api_url":"http://127.0.0.1:55769/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
} | [
true,
true,
true,
true
] | [
"552",
"552",
"552",
"552"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 4, \"non_overlapping_spans\": 4, \"span_st(...TRUNCATED) | "[{\"evaluation_method\": \"legacy\", \"legacy_result\": true}, {\"evaluation_method\": \"legacy\", (...TRUNCATED) | [[false,false,true,true],[true,false,true,true],[false,true,true,true],[false,true,true,false,true,t(...TRUNCATED) | [["(your answer)","your answer","552","552"],["552","(your answer)","552","552"],["(your answer)","5(...TRUNCATED) | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 456, \"span_text\": \"(your(...TRUNCATED) | "[[{\"evaluation_method\": \"legacy\", \"legacy_result\": false}, {\"evaluation_method\": \"legacy\"(...TRUNCATED) | {"flips_by":[0,1,0,1],"flips_total":2,"num_correct":4,"pass_at_n":1,"percent_correct":1.0,"skill_cou(...TRUNCATED) | 2025-11-02 | test | main | TAUR-dev/M-r1_distill_baseline-rl | 0 | eval_rl | 1 | 2025-11-02T22:59:46.794283 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1distill_rl-longmult_2dig-eval_rl |
47 x 41 | 1927 | longmult_2dig | longmult | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"metadata\": \"{\\\"arg1\\\": 47, \\\"arg2\\\": 41, \\\"solution\\\": 1927}\", \"task_source\": \(...TRUNCATED) | test | {"arg1": 47, "arg2": 41, "solution": 1927} | ["<think>\nI need to multiply 47 by 41. Let me break it down.\n\nFirst, I can look at these numbers (...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {"api_url":"http://127.0.0.1:55769/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
} | [
true,
true,
true,
true
] | [
"1927",
"1927",
"1927",
"1927"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 4, \"non_overlapping_spans\": 4, \"span_st(...TRUNCATED) | "[{\"evaluation_method\": \"legacy\", \"legacy_result\": true}, {\"evaluation_method\": \"legacy\", (...TRUNCATED) | [[true,false,true,true],[false,true,false,true,true,true],[false,true,false,false,true,true],[false,(...TRUNCATED) | [["1927","(your answer)","1927","1927"],["(your answer)","1927","(your answer)","1927","1927","1927"(...TRUNCATED) | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 1596, \"span_text\": \"1927(...TRUNCATED) | "[[{\"evaluation_method\": \"legacy\", \"legacy_result\": true}, {\"evaluation_method\": \"legacy\",(...TRUNCATED) | {"flips_by":[1,1,1,0],"flips_total":3,"num_correct":4,"pass_at_n":1,"percent_correct":1.0,"skill_cou(...TRUNCATED) | 2025-11-02 | test | main | TAUR-dev/M-r1_distill_baseline-rl | 0 | eval_rl | 1 | 2025-11-02T22:59:46.794285 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1distill_rl-longmult_2dig-eval_rl |
89 x 46 | 4094 | longmult_2dig | longmult | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"metadata\": \"{\\\"arg1\\\": 89, \\\"arg2\\\": 46, \\\"solution\\\": 4094}\", \"task_source\": \(...TRUNCATED) | test | {"arg1": 89, "arg2": 46, "solution": 4094} | ["<think>\nI need to multiply 89 by 46. Let me break it down using long multiplication or any other (...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {"api_url":"http://127.0.0.1:55769/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
} | [
true,
true,
true,
true
] | [
"4094",
"4094",
"4094",
"4094"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 7, \"non_overlapping_spans\": 7, \"span_st(...TRUNCATED) | "[{\"evaluation_method\": \"legacy\", \"legacy_result\": true}, {\"evaluation_method\": \"legacy\", (...TRUNCATED) | [[true,true,true,false,false,true,true],[false,false,false,true,false,true,false,true,true,true,true(...TRUNCATED) | [["4094","4094","4094","(your answer)","(your answer)","4094","4094"],["(your answer)","(your answer(...TRUNCATED) | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 1691, \"span_text\": \"4094(...TRUNCATED) | "[[{\"evaluation_method\": \"legacy\", \"legacy_result\": true}, {\"evaluation_method\": \"legacy\",(...TRUNCATED) | {"flips_by":[1,2,2,1],"flips_total":6,"num_correct":4,"pass_at_n":1,"percent_correct":1.0,"skill_cou(...TRUNCATED) | 2025-11-02 | test | main | TAUR-dev/M-r1_distill_baseline-rl | 0 | eval_rl | 1 | 2025-11-02T22:59:46.794287 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1distill_rl-longmult_2dig-eval_rl |
30 x 35 | 1050 | longmult_2dig | longmult | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"metadata\": \"{\\\"arg1\\\": 30, \\\"arg2\\\": 35, \\\"solution\\\": 1050}\", \"task_source\": \(...TRUNCATED) | test | {"arg1": 30, "arg2": 35, "solution": 1050} | ["<think>\nI need to solve the multiplication equation 30 x 35. Let me break it down.\n\nFirst, I ca(...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {"api_url":"http://127.0.0.1:55769/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
} | [
true,
true,
true,
true
] | [
"1050",
"1050",
"1050",
"1050"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 6, \"non_overlapping_spans\": 6, \"span_st(...TRUNCATED) | "[{\"evaluation_method\": \"legacy\", \"legacy_result\": true}, {\"evaluation_method\": \"legacy\", (...TRUNCATED) | [[true,false,true,true,false,true],[false,false,true,false,false,true,false,true,true],[false,true,t(...TRUNCATED) | [["1050","(your answer)","1050","1050","(your answer)","1050"],["(your answer)","(your answer)","105(...TRUNCATED) | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 1322, \"span_text\": \"1050(...TRUNCATED) | "[[{\"evaluation_method\": \"legacy\", \"legacy_result\": true}, {\"evaluation_method\": \"legacy\",(...TRUNCATED) | {"flips_by":[2,2,2,2],"flips_total":8,"num_correct":4,"pass_at_n":1,"percent_correct":1.0,"skill_cou(...TRUNCATED) | 2025-11-02 | test | main | TAUR-dev/M-r1_distill_baseline-rl | 0 | eval_rl | 1 | 2025-11-02T22:59:46.794288 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1distill_rl-longmult_2dig-eval_rl |
End of preview. Expand in Data Studio
Experiment Tracker: FinEval_16k_fulleval_3args_r1distill_rl-longmult_2dig
Experiment Description: Evaluation experiment for task longmult_2dig from FinEval_16k_fulleval_3args_r1distill_rl
Start Time: 2025-11-02T22:22:07.963517
Tracker Dataset: TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1distill_rl-longmult_2dig__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_2dig__v1', 'experiment_metadata')
# Load complete training datasets
sft_data = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1distill_rl-longmult_2dig__v1', 'training_data__sft')
sft_metadata = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1distill_rl-longmult_2dig__v1', 'training_data__sft_metadata')
# Load complete configurations
sft_hyperparams = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1distill_rl-longmult_2dig__v1', 'hyperparameters__sft')
rl_hyperparams = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1distill_rl-longmult_2dig__v1', 'hyperparameters__rl')
# Load stage-specific logs
sft_logs = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1distill_rl-longmult_2dig__v1', 'logs__sft')
rl_logs = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1distill_rl-longmult_2dig__v1', 'logs__rl')
# Load evaluation results with annotations
sft_eval_results = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1distill_rl-longmult_2dig__v1', 'evals_eval_sft')
rl_eval_results = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1distill_rl-longmult_2dig__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_2dig - {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