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
659
model_responses__best_of_n_atags__eval_evaluation_metadata
stringlengths
352
590
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
208
1.12k
model_responses__best_of_n_atags__internal_answers__eval_evaluation_metadata
stringlengths
103
683
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 06:48:50
2025-10-27 06:48:50
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 number can only be used once. Your solution should include a series of steps "Step X:" where each step is a mathematical operation and the final step ultimately leads to the target number or it should be a single equation that results in the target. Give your answer in the following format: <answer> (your answer) </answer> Where "(your answer)" is the list of steps to reach the target number or it should be a single equation that results in the target. For example: If the list of numbers was [1, 2, 3] and the target was 1, you could write: <answer> Step 1: 1 + 2 = 3 Step 2: 3 / 3 = 1 </answer> or <answer> (1 + 2) / 3 </answer> Let's think step by step.
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"}
[ "To create an equation using the numbers 68, 97, 78, 16, and 66 that equals 137, we can follow these steps:\n\n1. First, add 97 and 78:\n Step 1: 97 + 78 = 175\n\n2. Then, subtract 66 from the result:\n Step 2: 175 - 66 = 109\n\nHowever, this does not equal 137. Let's try another approach:\n\n1. Add 68 and 97:\...
[ false, false, false, false ]
[ "", "", "", "" ]
{ "api_url": "http://10.32.37.25:9080/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_vllm/TAUR-dev/M-bolt_gpt4o_baseline-rl", "prompt": [ { "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 (+, -, *, /) and each number can only be used once. Your solution should include a series of steps \"Step X:\" where each step is a mathematical operation and the final step ultimately leads to the target number or it should be a single equation that results in the target.\n\nGive your answer in the following format:\n<answer>\n(your answer)\n</answer>\n\nWhere \"(your answer)\" is the list of steps to reach the target number or it should be a single equation that results in the target. \n\nFor example:\nIf the list of numbers was [1, 2, 3] and the target was 1, you could write:\n<answer>\nStep 1: 1 + 2 = 3\nStep 2: 3 / 3 = 1\n</answer>\n\nor \n\n<answer>\n(1 + 2) / 3\n</answer>\n\nLet's think step by step.", "role": "user" } ] }
{ "backend": "litellm", "model_name": "hosted_vllm/TAUR-dev/M-bolt_gpt4o_baseline-rl", "n_responses": 4 }
[ false, false, false, false ]
[ "(97 - 16) * 78 - 68", null, "(97 - 68) - 16", null ]
[{"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 13163, "span_end": 13184, "original_span": "(97 - 16) * 78 - 68"}, {"extraction_type": "final"}, {"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 10212, "span_end": 10228, "original_span": "(97 - 68) - 16"}, {"extraction_type": "final"}]
[{"is_correct": false, "error": "Expression does not equal stated result", "answer_block": "(97 - 16) * 78 - 68", "final_answer": 137.0}, {"evaluation_method": "response_processor", "reason": "no_extracted_answer", "extraction_result": "{'extraction_type': 'final'}"}, {"is_correct": false, "error": "Expression does not equal stated result", "answer_block": "(97 - 68) - 16", "final_answer": 137.0}, {"evaluation_method": "response_processor", "reason": "no_extracted_answer", "extraction_result": "{'extraction_type': 'final'}"}]
[ [ false ], [], [ false ], [] ]
[ [ "(97 - 16) * 78 - 68" ], [], [ "(97 - 68) - 16" ], [] ]
[[{"pattern_used": "answer tag", "confidence": 1.0, "position": 13163, "span_text": "(97 - 16) * 78 - 68", "extraction_type": "internal", "span_start": 13163, "span_end": 13184, "original_span": "(97 - 16) * 78 - 68"}], [], [{"pattern_used": "answer tag", "confidence": 1.0, "position": 10212, "span_text": "(97 - 68) - 16", "extraction_type": "internal", "span_start": 10212, "span_end": 10228, "original_span": "(97 - 68) - 16"}], []]
[[{"is_correct": false, "error": "Expression does not equal stated result", "answer_block": "(97 - 16) * 78 - 68", "final_answer": 137.0}], [], [{"is_correct": false, "error": "Expression does not equal stated result", "answer_block": "(97 - 68) - 16", "final_answer": 137.0}], []]
{ "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, 0, 0 ], "reflect_open": [ 0, 0, 0, 0 ], "reflection_sbon": [ 0, 0, 0, 0 ], "sample_close": [ 0, 0, 0, 0 ], "sample_open": [ 0, 0, 0, 0 ], "vote_close": [ 0, 0, 0, 0 ], "vote_open": [ 0, 0, 0, 0 ], "voting": [ 0, 0, 0, 0 ] }, "total_responses": 4 }
2025-10-27
test
main
TAUR-dev/M-bolt_gpt4o_baseline-rl
0
eval_rl
1
2025-10-27T06:48:50.006148
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_bolt-countdown_5arg-eval_rl
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 number can only be used once. Your solution should include a series of steps "Step X:" where each step is a mathematical operation and the final step ultimately leads to the target number or it should be a single equation that results in the target. Give your answer in the following format: <answer> (your answer) </answer> Where "(your answer)" is the list of steps to reach the target number or it should be a single equation that results in the target. For example: If the list of numbers was [1, 2, 3] and the target was 1, you could write: <answer> Step 1: 1 + 2 = 3 Step 2: 3 / 3 = 1 </answer> or <answer> (1 + 2) / 3 </answer> Let's think step by step.
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"}
[ "To create an equation using the numbers 34, 81, 40, 25, and 24 that equals 106, we can follow these steps:\n\n1. First, add 81 and 40:\n Step 1: 81 + 40 = 121\n\n2. Then, subtract 34 from the result:\n Step 2: 121 - 34 = 87\n\n3. Finally, add 25 to the result:\n Step 3: 87 + 25 = 112\n\nIt seems we did not r...
[ false, false, false, false ]
[ "", "", "", "" ]
{ "api_url": "http://10.32.37.25:9080/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_vllm/TAUR-dev/M-bolt_gpt4o_baseline-rl", "prompt": [ { "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 (+, -, *, /) and each number can only be used once. Your solution should include a series of steps \"Step X:\" where each step is a mathematical operation and the final step ultimately leads to the target number or it should be a single equation that results in the target.\n\nGive your answer in the following format:\n<answer>\n(your answer)\n</answer>\n\nWhere \"(your answer)\" is the list of steps to reach the target number or it should be a single equation that results in the target. \n\nFor example:\nIf the list of numbers was [1, 2, 3] and the target was 1, you could write:\n<answer>\nStep 1: 1 + 2 = 3\nStep 2: 3 / 3 = 1\n</answer>\n\nor \n\n<answer>\n(1 + 2) / 3\n</answer>\n\nLet's think step by step.", "role": "user" } ] }
{ "backend": "litellm", "model_name": "hosted_vllm/TAUR-dev/M-bolt_gpt4o_baseline-rl", "n_responses": 4 }
[ true, true, true, true ]
[ "(81 + 25) = 106", "(81 + 25)", "(81 + 25)", "(81 + 25)" ]
[{"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 10450, "span_end": 10467, "original_span": "(81 + 25) = 106"}, {"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 5621, "span_end": 5632, "original_span": "(81 + 25)"}, {"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 421, "span_end": 432, "original_span": "(81 + 25)"}, {"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 421, "span_end": 432, "original_span": "(81 + 25)"}]
[{"is_correct": true, "error": null, "answer_block": "(81 + 25) = 106", "final_answer": 106.0}, {"is_correct": true, "error": null, "answer_block": "(81 + 25)", "final_answer": 106.0}, {"is_correct": true, "error": null, "answer_block": "(81 + 25)", "final_answer": 106.0}, {"is_correct": true, "error": null, "answer_block": "(81 + 25)", "final_answer": 106.0}]
[ [ true ], [ true ], [ true ], [ true ] ]
[ [ "(81 + 25) = 106" ], [ "(81 + 25)" ], [ "(81 + 25)" ], [ "(81 + 25)" ] ]
[[{"pattern_used": "answer tag", "confidence": 1.0, "position": 10450, "span_text": "(81 + 25) = 106", "extraction_type": "internal", "span_start": 10450, "span_end": 10467, "original_span": "(81 + 25) = 106"}], [{"pattern_used": "answer tag", "confidence": 1.0, "position": 5621, "span_text": "(81 + 25)", "extraction_type": "internal", "span_start": 5621, "span_end": 5632, "original_span": "(81 + 25)"}], [{"pattern_used": "answer tag", "confidence": 1.0, "position": 421, "span_text": "(81 + 25)", "extraction_type": "internal", "span_start": 421, "span_end": 432, "original_span": "(81 + 25)"}], [{"pattern_used": "answer tag", "confidence": 1.0, "position": 421, "span_text": "(81 + 25)", "extraction_type": "internal", "span_start": 421, "span_end": 432, "original_span": "(81 + 25)"}]]
[[{"is_correct": true, "error": null, "answer_block": "(81 + 25) = 106", "final_answer": 106.0}], [{"is_correct": true, "error": null, "answer_block": "(81 + 25)", "final_answer": 106.0}], [{"is_correct": true, "error": null, "answer_block": "(81 + 25)", "final_answer": 106.0}], [{"is_correct": true, "error": null, "answer_block": "(81 + 25)", "final_answer": 106.0}]]
{ "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, 0, 0 ], "reflect_open": [ 0, 0, 0, 0 ], "reflection_sbon": [ 0, 0, 0, 0 ], "sample_close": [ 0, 0, 0, 0 ], "sample_open": [ 0, 0, 0, 0 ], "vote_close": [ 0, 0, 0, 0 ], "vote_open": [ 0, 0, 0, 0 ], "voting": [ 0, 0, 0, 0 ] }, "total_responses": 4 }
2025-10-27
test
main
TAUR-dev/M-bolt_gpt4o_baseline-rl
0
eval_rl
1
2025-10-27T06:48:50.006159
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_bolt-countdown_5arg-eval_rl
"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)
["To create an equation using the numbers 100, 93, 82, 18, and 63 that equals 903, we can follow the(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.37.25:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/TAUR-dev/M-bolt_gpt4o_baseline-rl", "n_responses": 4 }
[ false, false, false, false ]
[ null, null, "(100 - 82) - 63", null ]
"[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\(...TRUNCATED)
"[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED)
[ [], [], [ false ], [] ]
[ [], [], [ "(100 - 82) - 63" ], [] ]
"[[], [], [{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 21843, \"span_text\(...TRUNCATED)
"[[], [], [{\"is_correct\": false, \"error\": \"Expression does not equal stated result\", \"answer_(...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-bolt_gpt4o_baseline-rl
0
eval_rl
1
2025-10-27T06:48:50.006160
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_bolt-countdown_5arg-eval_rl
"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)
["To create an equation using the numbers 49, 4, 7, 68, and 77 that equals 716, we can follow these (...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.37.25:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/TAUR-dev/M-bolt_gpt4o_baseline-rl", "n_responses": 4 }
[ 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-bolt_gpt4o_baseline-rl
0
eval_rl
1
2025-10-27T06:48:50.006162
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_bolt-countdown_5arg-eval_rl
"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)
["To create an equation using the numbers 96, 6, 42, 93, and 52 that equals 103, we can follow these(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.37.25:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/TAUR-dev/M-bolt_gpt4o_baseline-rl", "n_responses": 4 }
[ false, false, false, true ]
[ null, null, null, "(42 / 6) + 96" ]
"[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\(...TRUNCATED)
"[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED)
[ [], [], [], [ true ] ]
[ [], [], [], [ "(42 / 6) + 96" ] ]
"[[], [], [], [{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 3322, \"span_te(...TRUNCATED)
"[[], [], [], [{\"is_correct\": true, \"error\": null, \"answer_block\": \"(42 / 6) + 96\", \"final_(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":1,"pass_at_n":1,"percent_correct":0.25,"skill_co(...TRUNCATED)
2025-10-27
test
main
TAUR-dev/M-bolt_gpt4o_baseline-rl
0
eval_rl
1
2025-10-27T06:48:50.006163
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_bolt-countdown_5arg-eval_rl
"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)
["To create an equation using the numbers 91, 36, 19, 21, and 66 that equals 932, we can follow thes(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.37.25:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/TAUR-dev/M-bolt_gpt4o_baseline-rl", "n_responses": 4 }
[ 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-bolt_gpt4o_baseline-rl
0
eval_rl
1
2025-10-27T06:48:50.006165
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_bolt-countdown_5arg-eval_rl
"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)
["To create an equation using the numbers 57, 72, 1, 25, and 12 that equals 165, we can follow these(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.37.25:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/TAUR-dev/M-bolt_gpt4o_baseline-rl", "n_responses": 4 }
[ false, true, false, false ]
[ null, "(12 - 1) * (72 - 57)", null, null ]
"[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non(...TRUNCATED)
"[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED)
[ [], [ true ], [], [] ]
[ [], [ "(12 - 1) * (72 - 57)" ], [], [] ]
"[[], [{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 9045, \"span_text\": \"(...TRUNCATED)
"[[], [{\"is_correct\": true, \"error\": null, \"answer_block\": \"(12 - 1) * (72 - 57)\", \"final_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)
2025-10-27
test
main
TAUR-dev/M-bolt_gpt4o_baseline-rl
0
eval_rl
1
2025-10-27T06:48:50.006167
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_bolt-countdown_5arg-eval_rl
"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)
["To create an equation using the numbers 69, 18, 54, 73, and 4 that equals 899, we can follow these(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.37.25:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/TAUR-dev/M-bolt_gpt4o_baseline-rl", "n_responses": 4 }
[ true, true, true, true ]
[ "(18 * 54) - 73", "(18 * 54) - 73", "(54 * 18) - 4 - 69", "(54 * 18) - 73" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"(18 * 54) - 73\", \"final_answer\": 89(...TRUNCATED)
[ [ true ], [ true ], [ true ], [ true ] ]
[ [ "(18 * 54) - 73" ], [ "(18 * 54) - 73" ], [ "(54 * 18) - 4 - 69" ], [ "(54 * 18) - 73" ] ]
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 15819, \"span_text\": \"(18(...TRUNCATED)
"[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"(18 * 54) - 73\", \"final_answer\": 8(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":4,"pass_at_n":1,"percent_correct":1.0,"skill_cou(...TRUNCATED)
2025-10-27
test
main
TAUR-dev/M-bolt_gpt4o_baseline-rl
0
eval_rl
1
2025-10-27T06:48:50.006168
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_bolt-countdown_5arg-eval_rl
"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)
["To create an equation using the numbers 87, 19, 71, 79, and 62 that equals 301, we can follow thes(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.37.25:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/TAUR-dev/M-bolt_gpt4o_baseline-rl", "n_responses": 4 }
[ 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-bolt_gpt4o_baseline-rl
0
eval_rl
1
2025-10-27T06:48:50.006170
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_bolt-countdown_5arg-eval_rl
"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)
["To create an equation using the numbers 97, 7, 7, 34, and 38 that equals 656, we can follow these (...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.37.25:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/TAUR-dev/M-bolt_gpt4o_baseline-rl", "n_responses": 4 }
[ 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-bolt_gpt4o_baseline-rl
0
eval_rl
1
2025-10-27T06:48:50.006171
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_bolt-countdown_5arg-eval_rl
End of preview. Expand in Data Studio

Experiment Tracker: FinEval_16k_fulleval_3args_bolt-countdown_5arg

Experiment Description: Evaluation experiment for task countdown_5arg from FinEval_16k_fulleval_3args_bolt

Start Time: 2025-10-27T01:44:53.350725

Tracker Dataset: TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_bolt-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_bolt-countdown_5arg__v1', 'experiment_metadata')

# Load complete training datasets
sft_data = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_bolt-countdown_5arg__v1', 'training_data__sft')
sft_metadata = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_bolt-countdown_5arg__v1', 'training_data__sft_metadata')

# Load complete configurations
sft_hyperparams = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_bolt-countdown_5arg__v1', 'hyperparameters__sft')
rl_hyperparams = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_bolt-countdown_5arg__v1', 'hyperparameters__rl')

# Load stage-specific logs
sft_logs = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_bolt-countdown_5arg__v1', 'logs__sft')
rl_logs = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_bolt-countdown_5arg__v1', 'logs__rl')

# Load evaluation results with annotations
sft_eval_results = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_bolt-countdown_5arg__v1', 'evals_eval_sft')
rl_eval_results = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_bolt-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_bolt-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
4