Dataset Viewer
Auto-converted to Parquet Duplicate
question
stringlengths
7
989
answer
stringlengths
0
28
task_config
stringclasses
14 values
task_source
stringclasses
6 values
prompt
listlengths
1
1
model_responses
listlengths
0
0
model_responses__eval_is_correct
listlengths
0
0
all_other_columns
stringlengths
90
1.36k
original_split
stringclasses
1 value
acronym
stringclasses
341 values
answer_index
int64
0
4
answer_key
stringclasses
5 values
choices
dict
difficulty
stringclasses
1 value
domain
stringclasses
1 value
evaluation_type
stringclasses
1 value
expected_answer_format
stringclasses
1 value
formed_acronym
stringclasses
341 values
id
stringlengths
7
34
length
int64
4
8
letters
stringclasses
600 values
metadata
stringlengths
41
152
original_answer
stringlengths
48
1.07k
source
stringclasses
601 values
task_type
stringclasses
1 value
variant
stringclasses
1 value
word_count
int64
4
8
words
listlengths
4
8
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
3.65k
model_responses__best_of_n_atags__eval_evaluation_metadata
stringlengths
224
3.84k
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
192
182k
model_responses__best_of_n_atags__internal_answers__eval_evaluation_metadata
stringlengths
70
150k
model_responses__best_of_n_atags__metrics
dict
eval_date
stringdate
2025-11-21 00:00:00
2025-11-21 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
2025-11-21 12:15:56
2025-11-21 12:15:56
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
null
null
null
null
null
null
null
null
null
null
null
null
{"source_dataset": "countdown", "source_index": 5000, "numbers": [96, 97, 68], "target": 125, "expression": "97 + 96 - 68"}
null
null
null
null
null
null
[ "To solve the problem using the numbers 96, 97, 68 to get 125 with each number used once:\n\nFirst, let's consider possible combinations and arithmetic operations. Let’s try different permutations and operations:\n\n**Step-by-Step Approach:**\n\n1. **Start with 97**: This is the largest number which might help us a...
[ false, false, false, false ]
[ "", "", "", "" ]
{ "api_url": "http://10.32.36.198:9080/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_vl...
{ "backend": "litellm", "model_name": "hosted_vllm/SkillFactory/M-OT_otdata_10k_SFT-sft", "n_responses": 4 }
[ false, true, true, true ]
[ "Step 1: Subtract 68 from 97: 97 - 68 = 29\nStep 2: Add 96 to the result: 29 + 96 = 125", "Step 1: 97 - 68 = 29 \nStep 2: 96 + 29 = 125 \nOR \n96 + 97 - 68", "Step 1: 97 - 68 = 29 \nStep 2: 96 + 29 = 125", "(97 - 68) + 96 = 125" ]
[{"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 1809, "span_end": 1896, "original_span": "Step 1: Subtract 68 from 97: 97 - 68 = 29\nStep 2: Add 96 to the result: 29 + 96 = 125"}, {"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start...
[{"is_correct": false, "error": "Could not evaluate line: Step 1: Subtract 68 from 97: 97 - 68 = 29", "answer_block": "Step 1: Subtract 68 from 97: 97 - 68 = 29\nStep 2: Add 96 to the result: 29 + 96 = 125", "final_answer": null}, {"is_correct": true, "error": null, "answer_block": "Step 1: 97 - 68 = 29 \nStep 2: 96 +...
[ [ false ], [ true ], [ true ], [ true, true ] ]
[ [ "Step 1: Subtract 68 from 97: 97 - 68 = 29\nStep 2: Add 96 to the result: 29 + 96 = 125" ], [ "Step 1: 97 - 68 = 29 \nStep 2: 96 + 29 = 125 \nOR \n96 + 97 - 68" ], [ "Step 1: 97 - 68 = 29 \nStep 2: 96 + 29 = 125" ], [ "Step 1: 97 - 68 = 29\nStep 2: 29 + 96 = 125", "(97 - 68) + ...
[[{"pattern_used": "answer tag", "confidence": 1.0, "position": 1809, "span_text": "Step 1: Subtract 68 from 97: 97 - 68 = 29\nStep 2: Add 96 to the result: 29 + 96 = 125", "extraction_type": "internal", "span_start": 1809, "span_end": 1896, "original_span": "Step 1: Subtract 68 from 97: 97 - 68 = 29\nStep 2: Add 96 to...
[[{"is_correct": false, "error": "Could not evaluate line: Step 1: Subtract 68 from 97: 97 - 68 = 29", "answer_block": "Step 1: Subtract 68 from 97: 97 - 68 = 29\nStep 2: Add 96 to the result: 29 + 96 = 125", "final_answer": null}], [{"is_correct": true, "error": null, "answer_block": "Step 1: 97 - 68 = 29 \nStep 2: 9...
{ "flips_by": [ 0, 0, 0, 0 ], "flips_total": 0, "num_correct": 3, "pass_at_n": 1, "percent_correct": 0.75, "total_responses": 4 }
2025-11-21
test
main
SkillFactory/M-OT_otdata_10k_SFT-sft
0
eval_sft
1
2025-11-21T12:15:56.678309
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_OT10k_ot-SFT-eval_sft
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
null
null
null
null
null
null
null
null
null
null
null
null
{"source_dataset": "countdown", "source_index": 5001, "numbers": [21, 80, 46], "target": 105, "expression": "46 + 80 - 21"}
null
null
null
null
null
null
[ "<think>\nOkay, so I need to solve this problem where I have to use the numbers from the list [21, 80, 46] exactly once with basic arithmetic operations like addition, subtraction, multiplication, division, etc., to get the result 105. Let me start by understanding what numbers I have here. The numbers are 21, 80, ...
[ false, false, false, false ]
[ "", "", "", "" ]
{ "api_url": "http://10.32.36.198:9080/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_vl...
{ "backend": "litellm", "model_name": "hosted_vllm/SkillFactory/M-OT_otdata_10k_SFT-sft", "n_responses": 4 }
[ false, true, true, true ]
[ "Step 1: Add 80 and 46 to get 126.\nStep 2: Subtract 21 from 126 to get 105.", "Step 1: 80 + 46 = 126 \nStep 2: 126 - 21 = 105", "Step 1: 80 + 46 = 126\nStep 2: 126 - 21 = 105", "Step 1: 80 + 46 = 126\nStep 2: 126 - 21 = 105" ]
[{"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 2306, "span_end": 2382, "original_span": "Step 1: Add 80 and 46 to get 126.\nStep 2: Subtract 21 from 126 to get 105."}, {"extraction_type": "final", "total_spans_found": 3, "non_overlapping_spans": 3, "span_start": 9313, "s...
[{"is_correct": false, "error": "Error evaluating final answer", "answer_block": "Step 1: Add 80 and 46 to get 126.\nStep 2: Subtract 21 from 126 to get 105.", "final_answer": null}, {"is_correct": true, "error": null, "answer_block": "Step 1: 80 + 46 = 126 \nStep 2: 126 - 21 = 105", "final_answer": 105.0}, {"is_corre...
[ [ false ], [ true, true, true ], [ true ], [ true ] ]
[ [ "Step 1: Add 80 and 46 to get 126.\nStep 2: Subtract 21 from 126 to get 105." ], [ "Step 1: 80 + 46 = 126\nStep 2: 126 - 21 = 105", "80 + 46 - 21", "Step 1: 80 + 46 = 126 \nStep 2: 126 - 21 = 105" ], [ "Step 1: 80 + 46 = 126\nStep 2: 126 - 21 = 105" ], [ "Step 1: 80 + 46 = 126...
[[{"pattern_used": "answer tag", "confidence": 1.0, "position": 2306, "span_text": "Step 1: Add 80 and 46 to get 126.\nStep 2: Subtract 21 from 126 to get 105.", "extraction_type": "internal", "span_start": 2306, "span_end": 2382, "original_span": "Step 1: Add 80 and 46 to get 126.\nStep 2: Subtract 21 from 126 to get ...
[[{"is_correct": false, "error": "Error evaluating final answer", "answer_block": "Step 1: Add 80 and 46 to get 126.\nStep 2: Subtract 21 from 126 to get 105.", "final_answer": null}], [{"is_correct": true, "error": null, "answer_block": "Step 1: 80 + 46 = 126\nStep 2: 126 - 21 = 105", "final_answer": 105.0}, {"is_corr...
{ "flips_by": [ 0, 0, 0, 0 ], "flips_total": 0, "num_correct": 3, "pass_at_n": 1, "percent_correct": 0.75, "total_responses": 4 }
2025-11-21
test
main
SkillFactory/M-OT_otdata_10k_SFT-sft
0
eval_sft
1
2025-11-21T12:15:56.678317
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_OT10k_ot-SFT-eval_sft
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
null
null
null
null
null
null
null
null
null
null
null
null
{"source_dataset": "countdown", "source_index": 5002, "numbers": [6, 76, 96], "target": 500, "expression": "6*96 - 76"}
null
null
null
null
null
null
[ "To solve the problem using the numbers [6, 76, 96] and creating an equation that equals 500 with each number used exactly once, let's analyze possible combinations through various arithmetic operations.\n\nFirst, consider how large numbers like 76 and 96 can contribute towards 500 when combined with 6. Let's start...
[ false, false, false, false ]
[ "", "", "", "" ]
{ "api_url": "http://10.32.36.198:9080/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_vl...
{ "backend": "litellm", "model_name": "hosted_vllm/SkillFactory/M-OT_otdata_10k_SFT-sft", "n_responses": 4 }
[ false, false, true, false ]
[ "Step 1: Calculate 96 multiplied by 6: \\( 96 \\times 6 = 576 \\)\nStep 2: Subtract 76 from the result: \\( 576 - 76 = 500 \\)", null, "96*6 -76 =500", "Step 1: Multiply 6 and 96.\nStep 2: Subtract 76 from the result of Step 1." ]
[{"extraction_type": "final", "total_spans_found": 2, "non_overlapping_spans": 2, "span_start": 1971, "span_end": 2092, "original_span": "Step 1: Calculate 96 multiplied by 6: \\( 96 \\times 6 = 576 \\)\nStep 2: Subtract 76 from the result: \\( 576 - 76 = 500 \\)"}, {"extraction_type": "final"}, {"extraction_type": "fi...
[{"is_correct": false, "error": "Could not evaluate line: Step 1: Calculate 96 multiplied by 6: \\( 96 \\times 6 = 576 \\)", "answer_block": "Step 1: Calculate 96 multiplied by 6: \\( 96 \\times 6 = 576 \\)\nStep 2: Subtract 76 from the result: \\( 576 - 76 = 500 \\)", "final_answer": null}, {"evaluation_method": "resp...
[ [ false, false ], [], [ false, true, true, true, true ], [ false ] ]
[ [ "\\( (96 \\times 6) - 76 = 500 \\)", "Step 1: Calculate 96 multiplied by 6: \\( 96 \\times 6 = 576 \\)\nStep 2: Subtract 76 from the result: \\( 576 - 76 = 500 \\)" ], [], [ "76*6 +96 -36 -16 =500", "96*6 -76 =500", "Step 1: 96 * 6 = 576 \nStep 2: 576 - 76 = 500 \nResult: 500", "96...
[[{"pattern_used": "answer tag", "confidence": 1.0, "position": 1779, "span_text": "\\( (96 \\times 6) - 76 = 500 \\)", "extraction_type": "internal", "span_start": 1779, "span_end": 1811, "original_span": "\\( (96 \\times 6) - 76 = 500 \\)"}, {"pattern_used": "answer tag", "confidence": 1.0, "position": 1971, "span_te...
[[{"is_correct": false, "error": "Could not evaluate expression", "answer_block": "\\( (96 \\times 6) - 76 = 500 \\)", "final_answer": null}, {"is_correct": false, "error": "Could not evaluate line: Step 1: Calculate 96 multiplied by 6: \\( 96 \\times 6 = 576 \\)", "answer_block": "Step 1: Calculate 96 multiplied by 6:...
{ "flips_by": [ 0, 0, 0, 0 ], "flips_total": 0, "num_correct": 1, "pass_at_n": 1, "percent_correct": 0.25, "total_responses": 4 }
2025-11-21
test
main
SkillFactory/M-OT_otdata_10k_SFT-sft
0
eval_sft
1
2025-11-21T12:15:56.678319
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_OT10k_ot-SFT-eval_sft
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 [42, 12, 3], create an equation that equals 630. You can use basic arithmetic operations (+, -, *, /) and each number can on...
42*(12 + 3)
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 [42, 12, 3], create an equation that equals 630. You can use basic arithmetic operations (+, -, *, ...
[]
[]
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 5003, \"numbers\": [42, 12, 3], \"target\": 630, \"expression\": \"42*(12 + 3)\"}", "task_source": "countdown"}
test
null
null
null
null
null
null
null
null
null
null
null
null
{"source_dataset": "countdown", "source_index": 5003, "numbers": [42, 12, 3], "target": 630, "expression": "42*(12 + 3)"}
null
null
null
null
null
null
[ "To solve the problem using the numbers [42, 12, 3] to create an equation that equals 630, let's analyze possible combinations step by step:\n\nFirst, consider the largest number available, which is 42. We need to determine how this number can contribute significantly towards 630 when combined with other numbers vi...
[ false, false, false, false ]
[ "", "", "", "" ]
{ "api_url": "http://10.32.36.198:9080/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_vl...
{ "backend": "litellm", "model_name": "hosted_vllm/SkillFactory/M-OT_otdata_10k_SFT-sft", "n_responses": 4 }
[ true, false, false, true ]
[ "Step 1: 12 + 3 = 15\nStep 2: 42 * 15 = 630", "Step 1: 12 + 3 = 15\nStep 2: 42 × 15 = 630", "Step 1: 12 + 3 = 15\nStep 2: 42 × 15 = 630", "42 * (12 + 3)" ]
[{"extraction_type": "final", "total_spans_found": 5, "non_overlapping_spans": 5, "span_start": 2833, "span_end": 2876, "original_span": "Step 1: 12 + 3 = 15\nStep 2: 42 * 15 = 630"}, {"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 2253, "span_end": 2296, "original_span": ...
[{"is_correct": true, "error": null, "answer_block": "Step 1: 12 + 3 = 15\nStep 2: 42 * 15 = 630", "final_answer": 630.0}, {"is_correct": false, "error": "Could not evaluate line: Step 2: 42 \u00d7 15 = 630", "answer_block": "Step 1: 12 + 3 = 15\nStep 2: 42 \u00d7 15 = 630", "final_answer": null}, {"is_correct": false,...
[ [ true, true, true, true, true ], [ false ], [ false ], [ false, true ] ]
[ [ "42 * (12 + 3) = 630", "Step 1: 12 + 3 = 15\nStep 2: 42 * 15 = 630", "42*(12+3)", "Step 1: 12 + 3 = 15\nStep 2: 42 * 15 = 630", "Step 1: 12 + 3 = 15\nStep 2: 42 * 15 = 630" ], [ "Step 1: 12 + 3 = 15\nStep 2: 42 × 15 = 630" ], [ "Step 1: 12 + 3 = 15\nStep 2: 42 × 15 = 630" ], ...
[[{"pattern_used": "answer tag", "confidence": 1.0, "position": 1848, "span_text": "42 * (12 + 3) = 630", "extraction_type": "internal", "span_start": 1848, "span_end": 1869, "original_span": "42 * (12 + 3) = 630"}, {"pattern_used": "answer tag", "confidence": 1.0, "position": 1946, "span_text": "Step 1: 12 + 3 = 15\nS...
[[{"is_correct": true, "error": null, "answer_block": "42 * (12 + 3) = 630", "final_answer": 630.0}, {"is_correct": true, "error": null, "answer_block": "Step 1: 12 + 3 = 15\nStep 2: 42 * 15 = 630", "final_answer": 630.0}, {"is_correct": true, "error": null, "answer_block": "42*(12+3)", "final_answer": 630.0}, {"is_cor...
{ "flips_by": [ 0, 0, 0, 0 ], "flips_total": 0, "num_correct": 2, "pass_at_n": 1, "percent_correct": 0.5, "total_responses": 4 }
2025-11-21
test
main
SkillFactory/M-OT_otdata_10k_SFT-sft
0
eval_sft
1
2025-11-21T12:15:56.678320
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_OT10k_ot-SFT-eval_sft
"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
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 5005, \"numbers\": [86, 69, 52], \"target\": (...TRUNCATED)
null
null
null
null
null
null
["To solve the problem using the numbers in the list [86, 69, 52] to create an equation that equals (...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.36.198:9080/v1","backend":"litellm","chat_template_applied":true,"generatio(...TRUNCATED)
{"backend":"litellm","model_name":"hosted_vllm/SkillFactory/M-OT_otdata_10k_SFT-sft","n_responses":4(...TRUNCATED)
[ true, false, false, true ]
["86 + 69 - 52","(your answer)","Step 1: Calculate 69 - 52 = 17 \nStep 2: Add the result to 86: 86 (...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non_overlapping_spans\": 2, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"86 + 69 - 52\", \"final_answer\": 103.(...TRUNCATED)
[[true,true],[false,false,false,false,false,false,false,false,false,false,false,false,false,false,fa(...TRUNCATED)
[["Step 1: 86 + 69 = 155\nStep 2: 155 - 52 = 103","86 + 69 - 52"],["(1 + 2)/3","(your answer)","(you(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 1605, \"span_text\": \"Step(...TRUNCATED)
"[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 86 + 69 = 155\\nStep 2: 155 -(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":2,"pass_at_n":1,"percent_correct":0.5,"total_res(...TRUNCATED)
2025-11-21
test
main
SkillFactory/M-OT_otdata_10k_SFT-sft
0
eval_sft
1
2025-11-21T12:15:56.678322
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_OT10k_ot-SFT-eval_sft
"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
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 5006, \"numbers\": [63, 7, 87], \"target\": 3(...TRUNCATED)
null
null
null
null
null
null
["<think>\nOkay, so I need to take the numbers 63, 7, and 87 from the list and combine them using ad(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.36.198:9080/v1","backend":"litellm","chat_template_applied":true,"generatio(...TRUNCATED)
{"backend":"litellm","model_name":"hosted_vllm/SkillFactory/M-OT_otdata_10k_SFT-sft","n_responses":4(...TRUNCATED)
[ false, true, true, false ]
[ "(63 - 7) ÷ (7 × 2) × 87 = 354", "63*7 - 87", "63 * 7 - 87 = 354", 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\": \"(63 - 7)(...TRUNCATED)
[ [ false ], [ true, true ], [ true ], [] ]
[["(63 - 7) ÷ (7 × 2) × 87 = 354"],["Step 1: 63 * 7 = 441\nStep 2: 441 - 87 = 354","63*7 - 87"],[(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 4591, \"span_text\": \"(63 (...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"(63 - 7(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":2,"pass_at_n":1,"percent_correct":0.5,"total_res(...TRUNCATED)
2025-11-21
test
main
SkillFactory/M-OT_otdata_10k_SFT-sft
0
eval_sft
1
2025-11-21T12:15:56.678324
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_OT10k_ot-SFT-eval_sft
"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
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 5007, \"numbers\": [8, 50, 19], \"target\": 1(...TRUNCATED)
null
null
null
null
null
null
["<think>\nOkay, so I need to solve this problem where I have to use the numbers from the list [8, 5(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.36.198:9080/v1","backend":"litellm","chat_template_applied":true,"generatio(...TRUNCATED)
{"backend":"litellm","model_name":"hosted_vllm/SkillFactory/M-OT_otdata_10k_SFT-sft","n_responses":4(...TRUNCATED)
[ false, true, true, false ]
["Step 1: 19 * 8 = 152 \nStep 2: 152 - 50 = 102 \n**Answer:** 19*8 - 50 = 102","8 * 19 - 50 = 102"(...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Could not evaluate line: **Answer:** 19*8 - 50 = 102\", \"ans(...TRUNCATED)
[ [ false ], [ true, true ], [ true, true, true, true ], [ false ] ]
[["Step 1: 19 * 8 = 152 \nStep 2: 152 - 50 = 102 \n**Answer:** 19*8 - 50 = 102"],["8 * 19 - 50 = 1(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 3447, \"span_text\": \"Step(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Could not evaluate line: **Answer:** 19*8 - 50 = 102\", \"an(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":2,"pass_at_n":1,"percent_correct":0.5,"total_res(...TRUNCATED)
2025-11-21
test
main
SkillFactory/M-OT_otdata_10k_SFT-sft
0
eval_sft
1
2025-11-21T12:15:56.678325
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_OT10k_ot-SFT-eval_sft
"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
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 5008, \"numbers\": [38, 46, 40], \"target\": (...TRUNCATED)
null
null
null
null
null
null
["To solve the problem using the numbers [38, 46, 40] to create an equation equaling 124 with each n(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.36.198:9080/v1","backend":"litellm","chat_template_applied":true,"generatio(...TRUNCATED)
{"backend":"litellm","model_name":"hosted_vllm/SkillFactory/M-OT_otdata_10k_SFT-sft","n_responses":4(...TRUNCATED)
[ true, true, true, false ]
["38 + 46 + 40 = 124","38 + 46 + 40 = 124","Step 1: 38 + 46 = 84\nStep 2: 84 + 40 = 124","Step 1: Ad(...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"38 + 46 + 40 = 124\", \"final_answer\"(...TRUNCATED)
[ [ true ], [ true ], [ true ], [ false ] ]
[["38 + 46 + 40 = 124"],["38 + 46 + 40 = 124"],["Step 1: 38 + 46 = 84\nStep 2: 84 + 40 = 124"],["Ste(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 1846, \"span_text\": \"38 +(...TRUNCATED)
"[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"38 + 46 + 40 = 124\", \"final_answer\(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":3,"pass_at_n":1,"percent_correct":0.75,"total_re(...TRUNCATED)
2025-11-21
test
main
SkillFactory/M-OT_otdata_10k_SFT-sft
0
eval_sft
1
2025-11-21T12:15:56.678329
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_OT10k_ot-SFT-eval_sft
"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
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 5009, \"numbers\": [92, 21, 19], \"target\": (...TRUNCATED)
null
null
null
null
null
null
["<think>\nOkay, so I need to use the numbers 92, 21, and 19 from the list to make an equation that (...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.36.198:9080/v1","backend":"litellm","chat_template_applied":true,"generatio(...TRUNCATED)
{"backend":"litellm","model_name":"hosted_vllm/SkillFactory/M-OT_otdata_10k_SFT-sft","n_responses":4(...TRUNCATED)
[ true, true, true, true ]
["Step 1: 92 + 21 = 113 \nStep 2: 113 + 19 = 132","92 + 21 + 19 = 132","92 + 21 + 19 = 132","92 + 2(...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 4, \"non_overlapping_spans\": 4, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 92 + 21 = 113 \\nStep 2: 113 (...TRUNCATED)
[ [ false, false, true, true ], [ true ], [ true ], [ true ] ]
[["Step 1: 1 + 2 = 3\nStep 2: 3 / 3 = 1","(1 + 2) / 3","Step 1: 92 + 21 = 113\nStep 2: 113 + 19 = 13(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 4232, \"span_text\": \"Step(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Line uses unavailable numbers: Step 1: 1 + 2 = 3\", \"answer(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":4,"pass_at_n":1,"percent_correct":1.0,"total_res(...TRUNCATED)
2025-11-21
test
main
SkillFactory/M-OT_otdata_10k_SFT-sft
0
eval_sft
1
2025-11-21T12:15:56.678331
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_OT10k_ot-SFT-eval_sft
"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
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 5010, \"numbers\": [23, 21, 7], \"target\": 3(...TRUNCATED)
null
null
null
null
null
null
["To solve the problem using the numbers [23, 21, 7] to create an equation that equals 322 with each(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.36.198:9080/v1","backend":"litellm","chat_template_applied":true,"generatio(...TRUNCATED)
{"backend":"litellm","model_name":"hosted_vllm/SkillFactory/M-OT_otdata_10k_SFT-sft","n_responses":4(...TRUNCATED)
[ true, false, false, false ]
["Step 1: 21 - 7 = 14\nStep 2: 23 * 14 = 322",null,"Step 1: Calculate (21 - 7) = 14 \nStep 2: Multi(...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 21 - 7 = 14\\nStep 2: 23 * 14 (...TRUNCATED)
[ [ true ], [], [ false ], [ false ] ]
[["Step 1: 21 - 7 = 14\nStep 2: 23 * 14 = 322"],[],["Step 1: Calculate (21 - 7) = 14 \nStep 2: Mult(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 2944, \"span_text\": \"Step(...TRUNCATED)
"[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 21 - 7 = 14\\nStep 2: 23 * 14(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":1,"pass_at_n":1,"percent_correct":0.25,"total_re(...TRUNCATED)
2025-11-21
test
main
SkillFactory/M-OT_otdata_10k_SFT-sft
0
eval_sft
1
2025-11-21T12:15:56.678333
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_OT10k_ot-SFT-eval_sft
End of preview. Expand in Data Studio

Experiment Tracker: FinEval_16k_fulleval_OT10k_ot-SFT

Experiment Description: Simple test experiment for Skill Factory workflows.

Start Time: 2025-11-20T22:54:04.828512

Tracker Dataset: TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_OT10k_ot-SFT__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_OT10k_ot-SFT__v1', 'experiment_metadata')

# Load complete training datasets
sft_data = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_OT10k_ot-SFT__v1', 'training_data__sft')
sft_metadata = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_OT10k_ot-SFT__v1', 'training_data__sft_metadata')

# Load complete configurations
sft_hyperparams = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_OT10k_ot-SFT__v1', 'hyperparameters__sft')
rl_hyperparams = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_OT10k_ot-SFT__v1', 'hyperparameters__rl')

# Load stage-specific logs
sft_logs = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_OT10k_ot-SFT__v1', 'logs__sft')
rl_logs = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_OT10k_ot-SFT__v1', 'logs__rl')

# Load evaluation results with annotations
sft_eval_results = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_OT10k_ot-SFT__v1', 'evals_eval_sft')
rl_eval_results = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_OT10k_ot-SFT__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_OT10k_ot-SFT - {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