Dataset Viewer
Auto-converted to Parquet Duplicate
question
stringlengths
980
985
answer
stringlengths
13
23
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
186
201
original_split
stringclasses
1 value
metadata
stringlengths
128
143
model_responses__best_of_n_atags
listlengths
4
4
model_responses__best_of_n_atags__finish_reason_length_flags
listlengths
4
4
model_responses__best_of_n_atags__length_partial_responses
listlengths
4
4
prompt__best_of_n_atags__metadata
dict
model_responses__best_of_n_atags__metadata
dict
model_responses__best_of_n_atags__eval_is_correct
listlengths
4
4
model_responses__best_of_n_atags__eval_extracted_answers
listlengths
4
4
model_responses__best_of_n_atags__eval_extraction_metadata
stringlengths
120
2.76k
model_responses__best_of_n_atags__eval_evaluation_metadata
stringlengths
354
2.98k
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
212
5.82k
model_responses__best_of_n_atags__internal_answers__eval_evaluation_metadata
stringlengths
115
3.05k
model_responses__best_of_n_atags__metrics
dict
eval_date
stringdate
2025-10-27 00:00:00
2025-10-27 00:00:00
split
stringclasses
1 value
revision_name
stringclasses
1 value
model_path
stringclasses
1 value
checkpoint_step
int64
0
0
stage_name
stringclasses
1 value
stage_number
int64
1
1
timestamp
stringdate
2025-10-27 04:37:37
2025-10-27 04:37:37
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 [68, 97, 78, 16, 66], create an equation that equals 137. You can use basic arithmetic operations (+, -, *, /) and each numb...
97 - 16 - 78 + 66 + 68
countdown_5arg
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 [68, 97, 78, 16, 66], create an equation that equals 137. You can use basic arithmetic operations (...
[]
[]
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 250, \"numbers\": [68, 97, 78, 16, 66], \"target\": 137, \"expression\": \"97 - 16 - 78 + 66 + 68\"}", "task_source": "countdown"}
test
{"source_dataset": "countdown", "source_index": 250, "numbers": [68, 97, 78, 16, 66], "target": 137, "expression": "97 - 16 - 78 + 66 + 68"}
[ "<think>\nI have the numbers [68, 97, 78, 16, 66] and I need to make an equation that equals 137 using basic arithmetic operations: addition, subtraction, multiplication, and division. Each number can be used only once.\n\nFirst, I should consider what operations might get me close to 137. Since 137 is larger than ...
[ false, false, false, false ]
[ "", "", "", "" ]
{ "api_url": "http://10.32.37.28:9080/v1", "backend": "litellm", "chat_template_applied": true, "generation_params": { "chat_template_applied": true, "max_tokens": 16384, "n": 1, "repetition_penalty": 1.1, "temperature": 0.7, "top_k": 20, "top_p": 0.8 }, "model_name": "hosted_vll...
{ "backend": "litellm", "model_name": "hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only", "n_responses": 4 }
[ false, false, false, false ]
[ null, "(68 + 68) + (16 / 16)", "Step 1: 97 + 66 = 163 \nStep 2: 163 - 66 = 97", null ]
[{"extraction_type": "final"}, {"extraction_type": "final", "total_spans_found": 3, "non_overlapping_spans": 3, "span_start": 10970, "span_end": 10993, "original_span": "(68 + 68) + (16 / 16)"}, {"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 6776, "span_end": 6823, "origi...
[{"evaluation_method": "response_processor", "reason": "no_extracted_answer", "extraction_result": "{'extraction_type': 'final'}"}, {"is_correct": false, "error": "Expression uses an unavailable or repeated number", "answer_block": "(68 + 68) + (16 / 16)", "final_answer": 137.0}, {"is_correct": false, "error": "Line us...
[ [], [ false, false, false ], [ false ], [] ]
[ [], [ "(68 + 68) + (16 / 16)", "(your answer)", "(68 + 68) + (16 / 16)" ], [ "Step 1: 97 + 66 = 163 \nStep 2: 163 - 66 = 97" ], [] ]
[[], [{"pattern_used": "answer tag", "confidence": 1.0, "position": 7507, "span_text": "(68 + 68) + (16 / 16)", "extraction_type": "internal", "span_start": 7507, "span_end": 7528, "original_span": "(68 + 68) + (16 / 16)"}, {"pattern_used": "answer tag", "confidence": 1.0, "position": 7760, "span_text": "(your answer)"...
[[], [{"is_correct": false, "error": "Expression uses an unavailable or repeated number", "answer_block": "(68 + 68) + (16 / 16)", "final_answer": 137.0}, {"is_correct": false, "error": "Could not evaluate expression", "answer_block": "(your answer)", "final_answer": null}, {"is_correct": false, "error": "Expression us...
{ "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, ...
2025-10-27
test
main
TAUR-dev/M-R1_distilled_baseline_cd3args_only
0
eval_0
1
2025-10-27T04:37:37.611068
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_5arg-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 [34, 81, 40, 25, 24], create an equation that equals 106. You can use basic arithmetic operations (+, -, *, /) and each numb...
34 + 81 - 24 - 25 + 40
countdown_5arg
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 [34, 81, 40, 25, 24], create an equation that equals 106. You can use basic arithmetic operations (...
[]
[]
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 251, \"numbers\": [34, 81, 40, 25, 24], \"target\": 106, \"expression\": \"34 + 81 - 24 - 25 + 40\"}", "task_source": "countdown"}
test
{"source_dataset": "countdown", "source_index": 251, "numbers": [34, 81, 40, 25, 24], "target": 106, "expression": "34 + 81 - 24 - 25 + 40"}
[ "<think>\nI have the numbers [34, 81, 40, 25, 24] and need to make an equation that equals 106 using basic arithmetic operations: addition, subtraction, multiplication, and division. Each number can only be used once.\n\nFirst, I should look at the target number, 106, and see how it might relate to the given number...
[ 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 ]
[ "81 + 25 = 106", "81 + 25 = 106", "81 + 25 = 106", "81 + 25 = 106" ]
[{"extraction_type": "final", "total_spans_found": 2, "non_overlapping_spans": 2, "span_start": 7406, "span_end": 7421, "original_span": "81 + 25 = 106"}, {"extraction_type": "final", "total_spans_found": 2, "non_overlapping_spans": 2, "span_start": 6839, "span_end": 6854, "original_span": "81 + 25 = 106"}, {"extractio...
[{"is_correct": true, "error": null, "answer_block": "81 + 25 = 106", "final_answer": 106.0}, {"is_correct": true, "error": null, "answer_block": "81 + 25 = 106", "final_answer": 106.0}, {"is_correct": true, "error": null, "answer_block": "81 + 25 = 106", "final_answer": 106.0}, {"is_correct": true, "error": null, "ans...
[ [ true, true ], [ true, true ], [ true, true ], [ false, false, true ] ]
[ [ "81 + 25 = 106", "81 + 25 = 106" ], [ "81 + 25 = 106", "81 + 25 = 106" ], [ "81 + 25 = 106", "81 + 25 = 106" ], [ "(your answer)", "(your answer)", "81 + 25 = 106" ] ]
[[{"pattern_used": "answer tag", "confidence": 1.0, "position": 4901, "span_text": "81 + 25 = 106", "extraction_type": "internal", "span_start": 4901, "span_end": 4916, "original_span": "81 + 25 = 106"}, {"pattern_used": "answer tag", "confidence": 1.0, "position": 7406, "span_text": "81 + 25 = 106", "extraction_type":...
[[{"is_correct": true, "error": null, "answer_block": "81 + 25 = 106", "final_answer": 106.0}, {"is_correct": true, "error": null, "answer_block": "81 + 25 = 106", "final_answer": 106.0}], [{"is_correct": true, "error": null, "answer_block": "81 + 25 = 106", "final_answer": 106.0}, {"is_correct": true, "error": null, "...
{ "flips_by": [ 0, 0, 0, 0 ], "flips_total": 0, "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, ...
2025-10-27
test
main
TAUR-dev/M-R1_distilled_baseline_cd3args_only
0
eval_0
1
2025-10-27T04:37:37.611079
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_5arg-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
18*(63 - 100 + 82) + 93
countdown_5arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 252, \\\"numbers(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 252, \"numbers\": [100, 93, 82, 18, 63], \"ta(...TRUNCATED)
["<think>\nI have the numbers [100, 93, 82, 18, 63] and I need to make an equation that equals 903 u(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.37.28:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED)
{"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only","n_res(...TRUNCATED)
[ false, false, false, false ]
[ null, "(100 * 82) - 7297", null, null ]
"[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\", \"total_spans_found\": 4, \"non(...TRUNCATED)
"[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED)
[ [], [ false, false, false, false ], [], [] ]
[ [], [ "(your answer)", "(100 * 82) - 7297", "(your answer)", "(100 * 82) - 7297" ], [], [] ]
"[[], [{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 10060, \"span_text\": \(...TRUNCATED)
"[[], [{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"(yo(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED)
2025-10-27
test
main
TAUR-dev/M-R1_distilled_baseline_cd3args_only
0
eval_0
1
2025-10-27T04:37:37.611080
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_5arg-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
4*7*(77 - 49) - 68
countdown_5arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 253, \\\"numbers(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 253, \"numbers\": [49, 4, 7, 68, 77], \"targe(...TRUNCATED)
["<think>\nFirst, I have the numbers: 49, 4, 7, 68, and 77. I need to use each exactly once with bas(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.37.28:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED)
{"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only","n_res(...TRUNCATED)
[ false, false, false, false ]
[ null, null, null, null ]
"[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\(...TRUNCATED)
"[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED)
null
null
null
null
{"flips_by":null,"flips_total":null,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_count(...TRUNCATED)
2025-10-27
test
main
TAUR-dev/M-R1_distilled_baseline_cd3args_only
0
eval_0
1
2025-10-27T04:37:37.611082
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_5arg-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
96 + 52 + 6 - 93 + 42
countdown_5arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 255, \\\"numbers(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 255, \"numbers\": [96, 6, 42, 93, 52], \"targ(...TRUNCATED)
["<think>\nI have the numbers [96, 6, 42, 93, 52] and I need to make an equation that equals 103 usi(...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: 93 + 52 = 145 \nStep 2: 145 - 42 = 103", "(93 + 52) - 42", null, null ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 93 + 52 = 145 \\nStep 2: 145 (...TRUNCATED)
[ [ true ], [ true ], [], [] ]
[ [ "Step 1: 93 + 52 = 145 \nStep 2: 145 - 42 = 103" ], [ "(93 + 52) - 42" ], [], [] ]
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 7906, \"span_text\": \"Step(...TRUNCATED)
"[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 93 + 52 = 145 \\nStep 2: 145(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":2,"pass_at_n":1,"percent_correct":0.5,"skill_cou(...TRUNCATED)
2025-10-27
test
main
TAUR-dev/M-R1_distilled_baseline_cd3args_only
0
eval_0
1
2025-10-27T04:37:37.611083
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_5arg-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
21*36 + 19 + 91 + 66
countdown_5arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 257, \\\"numbers(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 257, \"numbers\": [91, 36, 19, 21, 66], \"tar(...TRUNCATED)
["<think>\nFirst, I have the numbers: 91, 36, 19, 21, and 66. I need to use each exactly once with b(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.37.28:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED)
{"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only","n_res(...TRUNCATED)
[ false, false, false, false ]
[ null, "(91 × 66) − 5014", "Step 1: 91 + 21 = 112\nStep 2: 112 * 8 = 932", null ]
"[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non(...TRUNCATED)
"[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED)
[ [], [ false ], [ false ], [] ]
[ [], [ "(91 × 66) − 5014" ], [ "Step 1: 91 + 21 = 112\nStep 2: 112 * 8 = 932" ], [] ]
"[[], [{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 11939, \"span_text\": \(...TRUNCATED)
"[[], [{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"(91(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED)
2025-10-27
test
main
TAUR-dev/M-R1_distilled_baseline_cd3args_only
0
eval_0
1
2025-10-27T04:37:37.611085
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_5arg-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
57 - 1 + 72 + 12 + 25
countdown_5arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 258, \\\"numbers(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 258, \"numbers\": [57, 72, 1, 25, 12], \"targ(...TRUNCATED)
["<think>\nI have the numbers [57, 72, 1, 25, 12] and need to make an equation that equals 165 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, false ]
[ "(72 + 12) × 2 - 3", null, 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\": \"(72 + 12(...TRUNCATED)
[ [ false ], [], [], [] ]
[ [ "(72 + 12) × 2 - 3" ], [], [], [] ]
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 5706, \"span_text\": \"(72 (...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"(72 + 1(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED)
2025-10-27
test
main
TAUR-dev/M-R1_distilled_baseline_cd3args_only
0
eval_0
1
2025-10-27T04:37:37.611086
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_5arg-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
73*(18 - 4) - 54 - 69
countdown_5arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 259, \\\"numbers(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 259, \"numbers\": [69, 18, 54, 73, 4], \"targ(...TRUNCATED)
["<think>\nFirst, I have the numbers: 69, 18, 54, 73, and 4. I need to use each exactly once with ba(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.37.28:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED)
{"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only","n_res(...TRUNCATED)
[ false, false, false, false ]
[ "(54 × 18) − 73", "(54 × 18) − 73", null, null ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non_overlapping_spans\": 2, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"(54 \\u0(...TRUNCATED)
[ [ false, false ], [ false ], [], [] ]
[ [ "(54 × 18) − 73", "(54 × 18) − 73" ], [ "(54 × 18) − 73" ], [], [] ]
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 8196, \"span_text\": \"(54 (...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"(54 \\u(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED)
2025-10-27
test
main
TAUR-dev/M-R1_distilled_baseline_cd3args_only
0
eval_0
1
2025-10-27T04:37:37.611088
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_5arg-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
19*(79 - 71) + 62 + 87
countdown_5arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 260, \\\"numbers(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 260, \"numbers\": [87, 19, 71, 79, 62], \"tar(...TRUNCATED)
["<think>\nI have the numbers [87, 19, 71, 79, 62] and I need to make an equation that equals 301 us(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.37.28:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED)
{"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only","n_res(...TRUNCATED)
[ false, false, false, false ]
[ "No solution exists.", null, 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\": \"No solut(...TRUNCATED)
[ [ false ], [], [], [] ]
[ [ "No solution exists." ], [], [], [] ]
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 24796, \"span_text\": \"No (...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"No solu(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED)
2025-10-27
test
main
TAUR-dev/M-R1_distilled_baseline_cd3args_only
0
eval_0
1
2025-10-27T04:37:37.611089
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_5arg-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
7*(97 + 7) - 38 - 34
countdown_5arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 262, \\\"numbers(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 262, \"numbers\": [97, 7, 7, 34, 38], \"targe(...TRUNCATED)
["<think>\nFirst, I have the numbers: 97, 7, 7, 34, 38. I need to use each exactly once with 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, false, false, false ]
[ null, null, "(your answer)", null ]
"[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\(...TRUNCATED)
"[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED)
[ [], [], [ false ], [] ]
[ [], [], [ "(your answer)" ], [] ]
"[[], [], [{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 24974, \"span_text\(...TRUNCATED)
"[[], [], [{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED)
2025-10-27
test
main
TAUR-dev/M-R1_distilled_baseline_cd3args_only
0
eval_0
1
2025-10-27T04:37:37.611091
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_5arg-eval_0
End of preview. Expand in Data Studio

Experiment Tracker: FinEval_16k_fulleval_3args_r1-countdown_5arg

Experiment Description: Evaluation experiment for task countdown_5arg from FinEval_16k_fulleval_3args_r1

Start Time: 2025-10-27T00:40:45.205927

Tracker Dataset: TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_5arg__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_5arg__v1', 'experiment_metadata')

# Load complete training datasets
sft_data = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_5arg__v1', 'training_data__sft')
sft_metadata = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_5arg__v1', 'training_data__sft_metadata')

# Load complete configurations
sft_hyperparams = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_5arg__v1', 'hyperparameters__sft')
rl_hyperparams = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_5arg__v1', 'hyperparameters__rl')

# Load stage-specific logs
sft_logs = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_5arg__v1', 'logs__sft')
rl_logs = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_5arg__v1', 'logs__rl')

# Load evaluation results with annotations
sft_eval_results = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_5arg__v1', 'evals_eval_sft')
rl_eval_results = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_5arg__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_5arg - {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