Dataset Viewer
Auto-converted to Parquet Duplicate
question
stringlengths
973
978
answer
stringlengths
5
14
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
171
185
original_split
stringclasses
1 value
metadata
stringlengths
113
127
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
243
2.5k
model_responses__best_of_n_atags__eval_evaluation_metadata
stringlengths
366
2.45k
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
416
6.39k
model_responses__best_of_n_atags__internal_answers__eval_evaluation_metadata
stringlengths
198
3.35k
model_responses__best_of_n_atags__metrics
dict
eval_date
stringdate
2025-10-26 00:00:00
2025-10-26 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
2025-10-26 21:38:57
2025-10-26 21:38:57
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 Using the numbers in the list [96, 97, 68], create an equation that equals 125. You can use basic arithmetic operations (+, -, *, /) and each number can o...
97 + 96 - 68
countdown_3arg
countdown
[ { "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\nUsing the numbers in the list [96, 97, 68], create an equation that equals 125. You can use basic arithmetic operations (+, -, *,...
[]
[]
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 5000, \"numbers\": [96, 97, 68], \"target\": 125, \"expression\": \"97 + 96 - 68\"}", "task_source": "countdown"}
test
{"source_dataset": "countdown", "source_index": 5000, "numbers": [96, 97, 68], "target": 125, "expression": "97 + 96 - 68"}
[ "<think>\nI have the numbers [96, 97, 68] and I need to make 125 using basic arithmetic operations: addition, subtraction, multiplication, and division. Each number can only be used once.\n\nFirst, I should consider what operations might get me close to 125. Since 125 is a fairly large number, multiplication might ...
[ 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 }
[ true, true, true, true ]
[ "96 + 97 - 68", "Step 1: 96 - 68 = 28 \nStep 2: 97 + 28 = 125", "(96 + 97) - 68", "(96 + 97) - 68" ]
[{"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 5094, "span_end": 5108, "original_span": "96 + 97 - 68"}, {"extraction_type": "final", "total_spans_found": 5, "non_overlapping_spans": 5, "span_start": 5607, "span_end": 5653, "original_span": "Step 1: 96 - 68 = 28 \nStep ...
[{"is_correct": true, "error": null, "answer_block": "96 + 97 - 68", "final_answer": 125.0}, {"is_correct": true, "error": null, "answer_block": "Step 1: 96 - 68 = 28 \nStep 2: 97 + 28 = 125", "final_answer": 125.0}, {"is_correct": true, "error": null, "answer_block": "(96 + 97) - 68", "final_answer": 125.0}, {"is_cor...
[ [ true ], [ true, true, true, false, true ], [ true ], [ true, false, true ] ]
[ [ "96 + 97 - 68" ], [ "97 + (96 - 68) = 125", "(97 + 96) - 68 = 125", "Step 1: 96 - 68 = 28 \nStep 2: 97 + 28 = 125", "(your answer)", "Step 1: 96 - 68 = 28 \nStep 2: 97 + 28 = 125" ], [ "(96 + 97) - 68" ], [ "(96 + 97) - 68 = 125", "Step 1: 1 + 2 = 3", "(96 + 9...
[[{"pattern_used": "answer tag", "confidence": 1.0, "position": 5094, "span_text": "96 + 97 - 68", "extraction_type": "internal", "span_start": 5094, "span_end": 5108, "original_span": "96 + 97 - 68"}], [{"pattern_used": "answer tag", "confidence": 1.0, "position": 2909, "span_text": "97 + (96 - 68) = 125", "extraction...
[[{"is_correct": true, "error": null, "answer_block": "96 + 97 - 68", "final_answer": 125.0}], [{"is_correct": true, "error": null, "answer_block": "97 + (96 - 68) = 125", "final_answer": 125.0}, {"is_correct": true, "error": null, "answer_block": "(97 + 96) - 68 = 125", "final_answer": 125.0}, {"is_correct": true, "er...
{ "flips_by": [ 0, 1, 0, 1 ], "flips_total": 2, "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, ...
2025-10-26
test
main
TAUR-dev/M-R1_distilled_baseline_cd3args_only
0
eval_0
1
2025-10-26T21:38:57.224384
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_3arg-eval_0
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 Using the numbers in the list [21, 80, 46], create an equation that equals 105. You can use basic arithmetic operations (+, -, *, /) and each number can o...
46 + 80 - 21
countdown_3arg
countdown
[ { "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\nUsing the numbers in the list [21, 80, 46], create an equation that equals 105. You can use basic arithmetic operations (+, -, *,...
[]
[]
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 5001, \"numbers\": [21, 80, 46], \"target\": 105, \"expression\": \"46 + 80 - 21\"}", "task_source": "countdown"}
test
{"source_dataset": "countdown", "source_index": 5001, "numbers": [21, 80, 46], "target": 105, "expression": "46 + 80 - 21"}
[ "<think>\nI have the numbers [21, 80, 46] and need to make an equation that equals 105 using basic arithmetic operations: addition, subtraction, multiplication, and division. Each number can only be used once.\n\nFirst, I should consider what operations might get me close to 105. Since 105 is larger than all the in...
[ 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 }
[ true, false, true, true ]
[ "80 - 21 + 46", null, "Step 1: 80 - 21 = 59\nStep 2: 59 + 46 = 105", "(80 - 21) + 46" ]
[{"extraction_type": "final", "total_spans_found": 5, "non_overlapping_spans": 5, "span_start": 5038, "span_end": 5052, "original_span": "80 - 21 + 46"}, {"extraction_type": "final"}, {"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 7798, "span_end": 7842, "original_span": ...
[{"is_correct": true, "error": null, "answer_block": "80 - 21 + 46", "final_answer": 105.0}, {"evaluation_method": "response_processor", "reason": "no_extracted_answer", "extraction_result": "{'extraction_type': 'final'}"}, {"is_correct": true, "error": null, "answer_block": "Step 1: 80 - 21 = 59\nStep 2: 59 + 46 = 105...
[ [ false, false, false, true, true ], [], [ true ], [ false, true, true, true ] ]
[ [ "(your answer)", "Step 1: 1 + 2 = 3\nStep 2: 3 / 3 = 1", "(1 + 2) / 3", "80 - 21 + 46", "80 - 21 + 46" ], [], [ "Step 1: 80 - 21 = 59\nStep 2: 59 + 46 = 105" ], [ "(your answer)", "(80 - 21) + 46", "(80 - 21) + 46", "(80 - 21) + 46" ] ]
[[{"pattern_used": "answer tag", "confidence": 1.0, "position": 2996, "span_text": "(your answer)", "extraction_type": "internal", "span_start": 2996, "span_end": 3009, "original_span": "(your answer)"}, {"pattern_used": "answer tag", "confidence": 1.0, "position": 3072, "span_text": "Step 1: 1 + 2 = 3\nStep 2: 3 / 3 =...
[[{"is_correct": false, "error": "Could not evaluate expression", "answer_block": "(your answer)", "final_answer": null}, {"is_correct": false, "error": "Line uses unavailable numbers: Step 1: 1 + 2 = 3", "answer_block": "Step 1: 1 + 2 = 3\nStep 2: 3 / 3 = 1", "final_answer": 3.0}, {"is_correct": false, "error": "Expre...
{ "flips_by": [ 0, 0, 0, 0 ], "flips_total": 0, "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, ...
2025-10-26
test
main
TAUR-dev/M-R1_distilled_baseline_cd3args_only
0
eval_0
1
2025-10-26T21:38:57.224395
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_3arg-eval_0
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 Using the numbers in the list [6, 76, 96], create an equation that equals 500. You can use basic arithmetic operations (+, -, *, /) and each number can on...
6*96 - 76
countdown_3arg
countdown
[ { "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\nUsing the numbers in the list [6, 76, 96], create an equation that equals 500. You can use basic arithmetic operations (+, -, *, ...
[]
[]
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 5002, \"numbers\": [6, 76, 96], \"target\": 500, \"expression\": \"6*96 - 76\"}", "task_source": "countdown"}
test
{"source_dataset": "countdown", "source_index": 5002, "numbers": [6, 76, 96], "target": 500, "expression": "6*96 - 76"}
[ "<think>\nI have the numbers [6, 76, 96] and need to make 500 using basic arithmetic operations: addition, subtraction, multiplication, and division. Each number can only be used once.\n\nFirst, I should look at the numbers and see what combinations might work. 76 and 96 are both fairly large, and 500 is also large...
[ 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, true ]
[ "(96 × 6) − 76", "Step 1: 76 * 6 = 456 \nStep 2: 456 - 96 = 500", null, "Step 1: 96 * 6 = 576 \nStep 2: 576 - 76 = 500" ]
[{"extraction_type": "final", "total_spans_found": 2, "non_overlapping_spans": 2, "span_start": 5643, "span_end": 5658, "original_span": "(96 \u00d7 6) \u2212 76"}, {"extraction_type": "final", "total_spans_found": 2, "non_overlapping_spans": 2, "span_start": 6970, "span_end": 7017, "original_span": "Step 1: 76 * 6 = 4...
[{"is_correct": false, "error": "Could not evaluate expression", "answer_block": "(96 \u00d7 6) \u2212 76", "final_answer": null}, {"is_correct": false, "error": "Incorrect arithmetic in line: Step 2: 456 - 96 = 500", "answer_block": "Step 1: 76 * 6 = 456 \nStep 2: 456 - 96 = 500", "final_answer": 500.0}, {"evaluation...
[ [ false, false ], [ false, false ], [], [ true ] ]
[ [ "(your answer)", "(96 × 6) − 76" ], [ "Step 1: 76 * 6 = 456\nStep 2: 456 - 96 = 500", "Step 1: 76 * 6 = 456 \nStep 2: 456 - 96 = 500" ], [], [ "Step 1: 96 * 6 = 576 \nStep 2: 576 - 76 = 500" ] ]
[[{"pattern_used": "answer tag", "confidence": 1.0, "position": 2751, "span_text": "(your answer)", "extraction_type": "internal", "span_start": 2751, "span_end": 2764, "original_span": "(your answer)"}, {"pattern_used": "answer tag", "confidence": 1.0, "position": 5643, "span_text": "(96 \u00d7 6) \u2212 76", "extract...
[[{"is_correct": false, "error": "Could not evaluate expression", "answer_block": "(your answer)", "final_answer": null}, {"is_correct": false, "error": "Could not evaluate expression", "answer_block": "(96 \u00d7 6) \u2212 76", "final_answer": null}], [{"is_correct": false, "error": "Incorrect arithmetic in line: Step...
{ "flips_by": [ 0, 0, 0, 0 ], "flips_total": 0, "num_correct": 1, "pass_at_n": 1, "percent_correct": 0.25, "skill_count": { "answer_revision": [ 0, 0, 0, 0 ], "best_of_n": [ 0, 0, 0, 0 ], "reflect_close": [ 0, ...
2025-10-26
test
main
TAUR-dev/M-R1_distilled_baseline_cd3args_only
0
eval_0
1
2025-10-26T21:38:57.224397
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_3arg-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
42*(12 + 3)
countdown_3arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 5003, \\\"number(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 5003, \"numbers\": [42, 12, 3], \"target\": 6(...TRUNCATED)
["<think>\nI have the numbers [42, 12, 3] and need to make an equation that equals 630 using basic a(...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, false, false ]
[ "42 × 12 ÷ 3 + 42", "Step 1: 12 + 3 = 15 \nStep 2: 42 * 15 = 630", null, null ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"42 \\u00(...TRUNCATED)
[ [ false ], [ false, false, false, true ], [], [] ]
[["42 × 12 ÷ 3 + 42"],["(your answer)","42 × (12 + 3)","(1 + 2) / 3","Step 1: 12 + 3 = 15 \nStep(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 12372, \"span_text\": \"42 (...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"42 \\u0(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":1,"pass_at_n":1,"percent_correct":0.25,"skill_co(...TRUNCATED)
2025-10-26
test
main
TAUR-dev/M-R1_distilled_baseline_cd3args_only
0
eval_0
1
2025-10-26T21:38:57.224399
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_3arg-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
86 + 69 - 52
countdown_3arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 5005, \\\"number(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 5005, \"numbers\": [86, 69, 52], \"target\": (...TRUNCATED)
["<think>\nI have the numbers [86, 69, 52] and need to make 103 using basic arithmetic operations: a(...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, true, true, true ]
["Step 1: 86 + 69 = 155\nStep 2: 155 - 52 = 103","Step 1: 86 + 69 = 155 \nStep 2: 155 - 52 = 103","(...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non_overlapping_spans\": 2, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 86 + 69 = 155\\nStep 2: 155 - (...TRUNCATED)
[ [ true, true ], [ true, false, true, true ], [ false, false, true, true ], [ false, true, true ] ]
[["Step 1: 86 + 69 = 155 \nStep 2: 155 - 52 = 103","Step 1: 86 + 69 = 155\nStep 2: 155 - 52 = 103"](...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 1640, \"span_text\": \"Step(...TRUNCATED)
"[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 86 + 69 = 155 \\nStep 2: 155(...TRUNCATED)
{"flips_by":[0,1,0,0],"flips_total":1,"num_correct":4,"pass_at_n":1,"percent_correct":1.0,"skill_cou(...TRUNCATED)
2025-10-26
test
main
TAUR-dev/M-R1_distilled_baseline_cd3args_only
0
eval_0
1
2025-10-26T21:38:57.224401
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_3arg-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
63*7 - 87
countdown_3arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 5006, \\\"number(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 5006, \"numbers\": [63, 7, 87], \"target\": 3(...TRUNCATED)
["<think>\nI have the numbers [63, 7, 87] and need to make an equation that equals 354 using basic a(...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, true, false, false ]
["Step 1: 63 * 7 = 441\nStep 2: 441 - 87 = 354","Step 1: 63 * 7 = 441\nStep 2: 441 - 87 = 354","(63 (...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 63 * 7 = 441\\nStep 2: 441 - 8(...TRUNCATED)
[ [ true ], [ false, true, false, true ], [ false, false ], [ false, false ] ]
[["Step 1: 63 * 7 = 441\nStep 2: 441 - 87 = 354"],["(your answer)","Step 1: 63 * 7 = 441\n\nStep 2: (...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 4083, \"span_text\": \"Step(...TRUNCATED)
"[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 63 * 7 = 441\\nStep 2: 441 - (...TRUNCATED)
{"flips_by":[0,1,0,0],"flips_total":1,"num_correct":2,"pass_at_n":1,"percent_correct":0.5,"skill_cou(...TRUNCATED)
2025-10-26
test
main
TAUR-dev/M-R1_distilled_baseline_cd3args_only
0
eval_0
1
2025-10-26T21:38:57.224403
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_3arg-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
19*8 - 50
countdown_3arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 5007, \\\"number(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 5007, \"numbers\": [8, 50, 19], \"target\": 1(...TRUNCATED)
["<think>\nFirst, I have the numbers [8, 50, 19] and need to make an equation that equals 102 using (...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 ]
["(8 × 19) + 50","(50 * 19) - 8","(50 + 19) * 8 - 50","Step 1: 8 * 19 = 152 \nStep 2: 152 - 50 = 1(...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non_overlapping_spans\": 2, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"(8 \\u00(...TRUNCATED)
[ [ false, false ], [ false, false, false, false ], [ false, false, false ], [ true ] ]
[["(your answer)","(8 × 19) + 50"],["(your answer)","(8 × 19) − 50","(your answer)","(50 * 19) -(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 5224, \"span_text\": \"(you(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"(your a(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":1,"pass_at_n":1,"percent_correct":0.25,"skill_co(...TRUNCATED)
2025-10-26
test
main
TAUR-dev/M-R1_distilled_baseline_cd3args_only
0
eval_0
1
2025-10-26T21:38:57.224404
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_3arg-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
40 + 46 + 38
countdown_3arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 5008, \\\"number(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 5008, \"numbers\": [38, 46, 40], \"target\": (...TRUNCATED)
["<think>\nI have the numbers [38, 46, 40] and need to make 124 using basic arithmetic operations: a(...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, true, true, true ]
["38 + 46 + 40 = 124","(46 + 40) + 38 = 124","Step 1: 40 + 38 = 78 \nStep 2: 78 + 46 = 124","Step 1(...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 3, \"non_overlapping_spans\": 3, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"38 + 46 + 40 = 124\", \"final_answer\"(...TRUNCATED)
[ [ false, true, true ], [ true ], [ true, true ], [ true ] ]
[["(your answer)","38 + 46 + 40 = 124","38 + 46 + 40 = 124"],["(46 + 40) + 38 = 124"],["Step 1: 40 +(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 2632, \"span_text\": \"(you(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"(your a(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":4,"pass_at_n":1,"percent_correct":1.0,"skill_cou(...TRUNCATED)
2025-10-26
test
main
TAUR-dev/M-R1_distilled_baseline_cd3args_only
0
eval_0
1
2025-10-26T21:38:57.224409
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_3arg-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
19 + 92 + 21
countdown_3arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 5009, \\\"number(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 5009, \"numbers\": [92, 21, 19], \"target\": (...TRUNCATED)
["<think>\nI have the numbers [92, 21, 19] and need to make 132 using basic arithmetic operations: a(...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, true, true, true ]
["92 + 21 + 19 = 132","(92 + 21) + 19","Step 1: 92 + 21 = 113 \nStep 2: 113 + 19 = 132","92 + 21 + (...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 4, \"non_overlapping_spans\": 4, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"92 + 21 + 19 = 132\", \"final_answer\"(...TRUNCATED)
[ [ true, true, false, true ], [ false, true ], [ true ], [ false, true ] ]
[["92 + 21 + 19 = 132","(92 + 21) + 19 = 132","(your answer)","92 + 21 + 19 = 132"],["(your answer)"(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 7412, \"span_text\": \"92 +(...TRUNCATED)
"[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"92 + 21 + 19 = 132\", \"final_answer\(...TRUNCATED)
{"flips_by":[1,0,0,0],"flips_total":1,"num_correct":4,"pass_at_n":1,"percent_correct":1.0,"skill_cou(...TRUNCATED)
2025-10-26
test
main
TAUR-dev/M-R1_distilled_baseline_cd3args_only
0
eval_0
1
2025-10-26T21:38:57.224411
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_3arg-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
23*(21 - 7)
countdown_3arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 5010, \\\"number(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 5010, \"numbers\": [23, 21, 7], \"target\": 3(...TRUNCATED)
["<think>\nFirst, I have the numbers [23, 21, 7] and I need to make an equation that equals 322 usin(...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, true, false ]
[ "23 * (21 / 7)", "Step 1: 21 - 7 = 14\nStep 2: 14 × 23 = 322", "(21 - 7) * 23", "(21 × 7) × 23" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Expression does not equal stated result\", \"answer_block\": (...TRUNCATED)
[ [ false ], [ false, false, false ], [ true ], [ false, false, false, false ] ]
[["23 * (21 / 7)"],["Step 1: 21 - 7 = 14\n\nStep 2: 14 × 23 = 322","(21 - 7) × 23 = 322","Step 1: (...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 8835, \"span_text\": \"23 *(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Expression does not equal stated result\", \"answer_block\":(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":1,"pass_at_n":1,"percent_correct":0.25,"skill_co(...TRUNCATED)
2025-10-26
test
main
TAUR-dev/M-R1_distilled_baseline_cd3args_only
0
eval_0
1
2025-10-26T21:38:57.224413
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_3arg-eval_0
End of preview. Expand in Data Studio

Experiment Tracker: FinEval_16k_fulleval_3args_r1-countdown_3arg

Experiment Description: Evaluation experiment for task countdown_3arg from FinEval_16k_fulleval_3args_r1

Start Time: 2025-10-26T21:03:26.985256

Tracker Dataset: TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_3arg__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-countdown_3arg__v1', 'experiment_metadata')

# Load complete training datasets
sft_data = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_3arg__v1', 'training_data__sft')
sft_metadata = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_3arg__v1', 'training_data__sft_metadata')

# Load complete configurations
sft_hyperparams = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_3arg__v1', 'hyperparameters__sft')
rl_hyperparams = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_3arg__v1', 'hyperparameters__rl')

# Load stage-specific logs
sft_logs = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_3arg__v1', 'logs__sft')
rl_logs = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_3arg__v1', 'logs__rl')

# Load evaluation results with annotations
sft_eval_results = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_3arg__v1', 'evals_eval_sft')
rl_eval_results = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_3arg__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-countdown_3arg - {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