Dataset Viewer
Auto-converted to Parquet Duplicate
question
stringlengths
984
989
answer
stringlengths
17
28
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
192
210
original_split
stringclasses
1 value
metadata
stringlengths
134
152
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
2.69k
model_responses__best_of_n_atags__eval_evaluation_metadata
stringlengths
370
2.89k
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
201
7.5k
model_responses__best_of_n_atags__internal_answers__eval_evaluation_metadata
stringlengths
108
4.18k
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 08:39:10
2025-10-27 08:39:10
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 [37, 27, 3, 84, 5, 80], create an equation that equals 152. You can use basic arithmetic operations (+, -, *, /) and each nu...
84 + 80 - 37 + 3 - 5 + 27
countdown_6arg
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 [37, 27, 3, 84, 5, 80], create an equation that equals 152. You can use basic arithmetic operations...
[]
[]
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 2, \"numbers\": [37, 27, 3, 84, 5, 80], \"target\": 152, \"expression\": \"84 + 80 - 37 + 3 - 5 + 27\"}", "task_source": "countdown"}
test
{"source_dataset": "countdown", "source_index": 2, "numbers": [37, 27, 3, 84, 5, 80], "target": 152, "expression": "84 + 80 - 37 + 3 - 5 + 27"}
[ "<think>\nI have the numbers [37, 27, 3, 84, 5, 80] and need to make 152 using basic arithmetic operations: addition, subtraction, multiplication, and division. Each number can be used only once.\n\nFirst, I should look at what numbers are close to 152. Let me see if any pairs add up to something big. For example, ...
[ 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 ]
[ "Step 1: 84 + 68 = 152", null, null, "(your answer)" ]
[{"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 15625, "span_end": 15648, "original_span": "Step 1: 84 + 68 = 152"}, {"extraction_type": "final"}, {"extraction_type": "final"}, {"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": ...
[{"is_correct": false, "error": "Line uses unavailable numbers: Step 1: 84 + 68 = 152", "answer_block": "Step 1: 84 + 68 = 152", "final_answer": 152.0}, {"evaluation_method": "response_processor", "reason": "no_extracted_answer", "extraction_result": "{'extraction_type': 'final'}"}, {"evaluation_method": "response_proc...
[ [ false ], [], [], [ false ] ]
[ [ "Step 1: 84 + 68 = 152" ], [], [], [ "(your answer)" ] ]
[[{"pattern_used": "answer tag", "confidence": 1.0, "position": 15625, "span_text": "Step 1: 84 + 68 = 152", "extraction_type": "internal", "span_start": 15625, "span_end": 15648, "original_span": "Step 1: 84 + 68 = 152"}], [], [], [{"pattern_used": "answer tag", "confidence": 1.0, "position": 22487, "span_text": "(you...
[[{"is_correct": false, "error": "Line uses unavailable numbers: Step 1: 84 + 68 = 152", "answer_block": "Step 1: 84 + 68 = 152", "final_answer": 152.0}], [], [], [{"is_correct": false, "error": "Could not evaluate expression", "answer_block": "(your answer)", "final_answer": null}]]
{ "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
2025-10-27T08:39:10.536975
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_6arg-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
20*(64 + 48 - 27 - 45) - 81
countdown_6arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 3, \\\"numbers\\(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 3, \"numbers\": [27, 48, 64, 20, 81, 45], \"t(...TRUNCATED)
["<think>\nFirst, I have the numbers: 27, 48, 64, 20, 81, and 45. I need to use each exactly once wi(...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
2025-10-27T08:39:10.536989
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_6arg-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
9*56 - 71 - 59 + 74 + 44
countdown_6arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 5, \\\"numbers\\(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 5, \"numbers\": [74, 44, 56, 9, 59, 71], \"ta(...TRUNCATED)
["<think>\nFirst, I have the numbers: 74, 44, 56, 9, 59, 71. 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 ]
[ "(56 × 9) − (71 − 59)", null, null, null ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 3, \"non_overlapping_spans\": 3, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"(56 \\u0(...TRUNCATED)
[ [ false, false, false ], [], [], [] ]
[["Step 1: 56 × 9 = 504\nStep 2: 71 − 59 = 12\nStep 3: 504 − 12 = 492","(56 × 9) − (71 − 5(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 6071, \"span_text\": \"Step(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Could not evaluate line: Step 1: 56 \\u00d7 9 = 504\", \"ans(...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
2025-10-27T08:39:10.536991
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_6arg-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
27*(75 - 52 - 17 + 37 - 33)
countdown_6arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 16, \\\"numbers\(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 16, \"numbers\": [75, 17, 52, 33, 37, 27], \"(...TRUNCATED)
["<think>\nFirst, I have the numbers: 75, 17, 52, 33, 37, 27. 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, null, "(37 - 27) * 27", null ]
"[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\(...TRUNCATED)
"[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED)
[ [], [], [ false ], [] ]
[ [], [], [ "(37 - 27) * 27" ], [] ]
"[[], [], [{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 10491, \"span_text\(...TRUNCATED)
"[[], [], [{\"is_correct\": false, \"error\": \"Expression uses an unavailable or repeated number\",(...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
2025-10-27T08:39:10.536993
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_6arg-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
27*(52 - 12 - 37 + 4 + 10)
countdown_6arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 19, \\\"numbers\(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 19, \"numbers\": [27, 4, 37, 10, 12, 52], \"t(...TRUNCATED)
["<think>\nFirst, I have the numbers: 27, 4, 37, 10, 12, and 52. I need to use each exactly once wit(...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 ]
["Step 1: 27 - 10 = 17\nStep 2: 17 * 27 = 459","Step 1: 52 - 37 = 15\nStep 2: 15 + 444 = 459",null,n(...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Line uses unavailable numbers: Step 2: 17 * 27 = 459\", \"ans(...TRUNCATED)
[ [ false ], [ false, false ], [], [] ]
[["Step 1: 27 - 10 = 17\nStep 2: 17 * 27 = 459"],["Step 1: 37 * 12 = 444 \nStep 2: 444 + 15 = 459",(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 7536, \"span_text\": \"Step(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Line uses unavailable numbers: Step 2: 17 * 27 = 459\", \"an(...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
2025-10-27T08:39:10.536995
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_6arg-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
34*22 - 67 - 84 + 3 - 55
countdown_6arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 20, \\\"numbers\(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 20, \"numbers\": [3, 55, 22, 34, 84, 67], \"t(...TRUNCATED)
["<think>\nFirst, I have the numbers: 3, 55, 22, 34, 84, and 67. I need to use each exactly once wit(...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\": 12080, \"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
2025-10-27T08:39:10.536997
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_6arg-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
52*(16 + 81 - 79) - 69 - 88
countdown_6arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 22, \\\"numbers\(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 22, \"numbers\": [81, 79, 88, 69, 52, 16], \"(...TRUNCATED)
["<think>\nI have the numbers [81, 79, 88, 69, 52, 16] and I need to make an equation that equals 77(...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
2025-10-27T08:39:10.536999
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_6arg-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
28*(37 - 19 + 26 + 19 - 40)
countdown_6arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 27, \\\"numbers\(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 27, \"numbers\": [19, 19, 37, 26, 40, 28], \"(...TRUNCATED)
["<think>\nI have the numbers [19, 19, 37, 26, 40, 28] and I need to make an equation that equals 64(...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,"(37 * 19) / (465 / (26 + 40)) // simplifying the expression, but for clarity, the equati(...TRUNCATED)
"[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\(...TRUNCATED)
"[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED)
[ [], [], [ false ], [] ]
[[],[],["(37 * 19) / (465 / (26 + 40)) // simplifying the expression, but for clarity, the equation (...TRUNCATED)
"[[], [], [{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 16732, \"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
2025-10-27T08:39:10.537001
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_6arg-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
-2 + (84*22 - 25 + 59)/2
countdown_6arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 29, \\\"numbers\(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 29, \"numbers\": [25, 59, 2, 84, 22, 2], \"ta(...TRUNCATED)
["<think>\nI have the numbers [25, 59, 2, 84, 22, 2] and I need to make an equation that equals 939 (...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,"Step 1: Multiply 59 and 2 to get 118.\nStep 2: Multiply the result (118) by 84 to get 96(...TRUNCATED)
"[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\(...TRUNCATED)
"[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED)
[ [], [], [ false, false, false ], [] ]
[[],[],["Step 1: 1 + 2 = 3\nStep 2: 3 / 3 = 1","(1 + 2) / 3","Step 1: Multiply 59 and 2 to get 118.\(...TRUNCATED)
"[[], [], [{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 6188, \"span_text\"(...TRUNCATED)
"[[], [], [{\"is_correct\": false, \"error\": \"Line uses unavailable numbers: Step 1: 1 + 2 = 3\", (...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
2025-10-27T08:39:10.537003
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_6arg-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
4*(49 - 19 + 82) + 89 - 29
countdown_6arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 30, \\\"numbers\(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 30, \"numbers\": [4, 49, 19, 89, 29, 82], \"t(...TRUNCATED)
["<think>\nFirst, I have the numbers: [4, 49, 19, 89, 29, 82]. I need to use each exactly once with (...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 ]
[ "(89 × 5) + 63", null, null, "Step 1: 19 × 29 = 551\nStep 2: 551 − 43 = 508" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non_overlapping_spans\": 2, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"(89 \\u0(...TRUNCATED)
[ [ false, false ], [], [], [ false, false ] ]
[["(your answer)","(89 × 5) + 63"],[],[],["Step 1: 19 × 29 = 551 \nStep 2: 551 − 43 = 508","Ste(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 5012, \"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":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
2025-10-27T08:39:10.537005
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_6arg-eval_0
End of preview. Expand in Data Studio

Experiment Tracker: FinEval_16k_fulleval_3args_r1-countdown_6arg

Experiment Description: Evaluation experiment for task countdown_6arg from FinEval_16k_fulleval_3args_r1

Start Time: 2025-10-27T04:37:44.694728

Tracker Dataset: TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_6arg__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_6arg__v1', 'experiment_metadata')

# Load complete training datasets
sft_data = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_6arg__v1', 'training_data__sft')
sft_metadata = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_6arg__v1', 'training_data__sft_metadata')

# Load complete configurations
sft_hyperparams = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_6arg__v1', 'hyperparameters__sft')
rl_hyperparams = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_6arg__v1', 'hyperparameters__rl')

# Load stage-specific logs
sft_logs = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_6arg__v1', 'logs__sft')
rl_logs = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_6arg__v1', 'logs__rl')

# Load evaluation results with annotations
sft_eval_results = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_6arg__v1', 'evals_eval_sft')
rl_eval_results = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_6arg__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_6arg - {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