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
4.39k
model_responses__best_of_n_atags__eval_evaluation_metadata
stringlengths
225
4.54k
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
189
8.46k
model_responses__best_of_n_atags__internal_answers__eval_evaluation_metadata
stringlengths
70
4.29k
model_responses__best_of_n_atags__metrics
dict
eval_date
stringdate
2025-11-17 00:00:00
2025-11-17 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
2025-11-17 08:20:15
2025-11-17 08:20:15
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 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 + 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 given problem, we need to find a way to combine three distinct numbers (96, 97, 68) using basic arithmetic operations (+, -, *, /) without repeating any digit and ending up with 125. Here’s how we can approach it:\n\n### Step-by-Step Solution\n\n1. **Identify Possible Combinations**: We have three num...
[ false, false, false, false ]
[ "", "", "", "" ]
{ "api_url": "http://127.0.0.1:51075/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/Qwen/Qwen2.5-0.5B-Instruct", "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 [96, 97, 68], create an equation that equals 125. 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/Qwen/Qwen2.5-0.5B-Instruct", "n_responses": 4 }
[ false, false, false, false ]
[ null, null, null, null ]
[{"extraction_type": "final"}, {"extraction_type": "final"}, {"extraction_type": "final"}, {"extraction_type": "final"}]
[{"evaluation_method": "response_processor", "reason": "no_extracted_answer", "extraction_result": "{'extraction_type': 'final'}"}, {"evaluation_method": "response_processor", "reason": "no_extracted_answer", "extraction_result": "{'extraction_type': 'final'}"}, {"evaluation_method": "response_processor", "reason": "no_extracted_answer", "extraction_result": "{'extraction_type': 'final'}"}, {"evaluation_method": "response_processor", "reason": "no_extracted_answer", "extraction_result": "{'extraction_type': 'final'}"}]
null
null
null
null
{ "flips_by": null, "flips_total": null, "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 }
2025-11-17
test
main
Qwen/Qwen2.5-0.5B-Instruct
0
eval_0
1
2025-11-17T08:20:15.192135
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_Q05B_base-eval_0
Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(your answer)</answer>. # Problem Using the numbers in the list [21, 80, 46], create an equation that equals 105. You can use basic arithmetic operations (+, -, *, /) and each number can 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.
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
[ "To solve the problem of creating an equation using the given numbers (21, 80, 46) with one variable \\( x \\), we need to find a way to combine these values into an expression that equals 105. Let's break down the process:\n\n### Step-by-Step Solution\n\n1. **Identify the Variables and Numbers**:\n - We have thr...
[ false, false, false, false ]
[ "", "", "", "" ]
{ "api_url": "http://127.0.0.1:51075/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/Qwen/Qwen2.5-0.5B-Instruct", "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 [21, 80, 46], create an equation that equals 105. 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/Qwen/Qwen2.5-0.5B-Instruct", "n_responses": 4 }
[ false, false, false, false ]
[ null, null, null, "Step 1: 21 * 5 = 105\nStep 2: 105 ÷ 21 = 5" ]
[{"extraction_type": "final"}, {"extraction_type": "final"}, {"extraction_type": "final"}, {"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 1746, "span_end": 1789, "original_span": "Step 1: 21 * 5 = 105\nStep 2: 105 \u00f7 21 = 5"}]
[{"evaluation_method": "response_processor", "reason": "no_extracted_answer", "extraction_result": "{'extraction_type': 'final'}"}, {"evaluation_method": "response_processor", "reason": "no_extracted_answer", "extraction_result": "{'extraction_type': 'final'}"}, {"evaluation_method": "response_processor", "reason": "no_extracted_answer", "extraction_result": "{'extraction_type': 'final'}"}, {"is_correct": false, "error": "Line uses unavailable numbers: Step 1: 21 * 5 = 105", "answer_block": "Step 1: 21 * 5 = 105\nStep 2: 105 \u00f7 21 = 5", "final_answer": 105.0}]
[ [], [], [], [ false ] ]
[ [], [], [], [ "Step 1: 21 * 5 = 105\nStep 2: 105 ÷ 21 = 5" ] ]
[[], [], [], [{"pattern_used": "answer tag", "confidence": 1.0, "position": 1746, "span_text": "Step 1: 21 * 5 = 105\nStep 2: 105 \u00f7 21 = 5", "extraction_type": "internal", "span_start": 1746, "span_end": 1789, "original_span": "Step 1: 21 * 5 = 105\nStep 2: 105 \u00f7 21 = 5"}]]
[[], [], [], [{"is_correct": false, "error": "Line uses unavailable numbers: Step 1: 21 * 5 = 105", "answer_block": "Step 1: 21 * 5 = 105\nStep 2: 105 \u00f7 21 = 5", "final_answer": 105.0}]]
{ "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 }
2025-11-17
test
main
Qwen/Qwen2.5-0.5B-Instruct
0
eval_0
1
2025-11-17T08:20:15.192145
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_Q05B_base-eval_0
Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(your answer)</answer>. # Problem Using the numbers in the list [6, 76, 96], create an equation that equals 500. You can use basic arithmetic operations (+, -, *, /) and each number can 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.
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, we need to find a combination of mathematical operations (addition, subtraction, multiplication, division) using all the numbers from the list [6, 76, 96] exactly once. The goal is to end up with the number 500. Here’s how we can approach it:\n\n### Step-by-Step Solution\n\n1. **Identify Numb...
[ false, false, false, false ]
[ "", "", "", "" ]
{ "api_url": "http://127.0.0.1:51075/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/Qwen/Qwen2.5-0.5B-Instruct", "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 [6, 76, 96], create an equation that equals 500. 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/Qwen/Qwen2.5-0.5B-Instruct", "n_responses": 4 }
[ false, false, false, false ]
[ null, null, null, null ]
[{"extraction_type": "final"}, {"extraction_type": "final"}, {"extraction_type": "final"}, {"extraction_type": "final"}]
[{"evaluation_method": "response_processor", "reason": "no_extracted_answer", "extraction_result": "{'extraction_type': 'final'}"}, {"evaluation_method": "response_processor", "reason": "no_extracted_answer", "extraction_result": "{'extraction_type': 'final'}"}, {"evaluation_method": "response_processor", "reason": "no_extracted_answer", "extraction_result": "{'extraction_type': 'final'}"}, {"evaluation_method": "response_processor", "reason": "no_extracted_answer", "extraction_result": "{'extraction_type': 'final'}"}]
null
null
null
null
{ "flips_by": null, "flips_total": null, "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 }
2025-11-17
test
main
Qwen/Qwen2.5-0.5B-Instruct
0
eval_0
1
2025-11-17T08:20:15.192147
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_Q05B_base-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 [42, 12, 3], create an equation that equals 630. 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.
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 given list [42, 12, 3], we need to form an equation that adds up to 630. We'll start with the largest possible numbers and work our way down to see if we can combine them to get close to 630.\n\nHere’s how we can approach it:\n\n### Step-by-Step Solution\n\n1. **First Number**: The s...
[ false, false, false, false ]
[ "", "", "", "" ]
{ "api_url": "http://127.0.0.1:51075/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/Qwen/Qwen2.5-0.5B-Instruct", "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 [42, 12, 3], create an equation that equals 630. 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/Qwen/Qwen2.5-0.5B-Instruct", "n_responses": 4 }
[ false, false, false, false ]
[ null, null, null, null ]
[{"extraction_type": "final"}, {"extraction_type": "final"}, {"extraction_type": "final"}, {"extraction_type": "final"}]
[{"evaluation_method": "response_processor", "reason": "no_extracted_answer", "extraction_result": "{'extraction_type': 'final'}"}, {"evaluation_method": "response_processor", "reason": "no_extracted_answer", "extraction_result": "{'extraction_type': 'final'}"}, {"evaluation_method": "response_processor", "reason": "no_extracted_answer", "extraction_result": "{'extraction_type': 'final'}"}, {"evaluation_method": "response_processor", "reason": "no_extracted_answer", "extraction_result": "{'extraction_type': 'final'}"}]
null
null
null
null
{ "flips_by": null, "flips_total": null, "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 }
2025-11-17
test
main
Qwen/Qwen2.5-0.5B-Instruct
0
eval_0
1
2025-11-17T08:20:15.192149
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_Q05B_base-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
86 + 69 - 52
countdown_3arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 5005, \\\"number(...TRUNCATED)
test
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 given list [86, 69, 52] and achieve the target number 103, we need (...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://127.0.0.1:51075/v1","backend":"litellm","chat_template_applied":true,"generation_(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-0.5B-Instruct", "n_responses": 4 }
[ false, false, false, false ]
[ null, null, "\\( 86 + 69 - 52 \\)", null ]
"[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\(...TRUNCATED)
"[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED)
[ [], [], [ false ], [] ]
[ [], [], [ "\\( 86 + 69 - 52 \\)" ], [] ]
"[[], [], [{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 857, \"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)
2025-11-17
test
main
Qwen/Qwen2.5-0.5B-Instruct
0
eval_0
1
2025-11-17T08:20:15.192150
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_Q05B_base-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
63*7 - 87
countdown_3arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 5006, \\\"number(...TRUNCATED)
test
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
["To solve the problem using the given numbers (63, 7, 87), we need to find a combination of mathema(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://127.0.0.1:51075/v1","backend":"litellm","chat_template_applied":true,"generation_(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-0.5B-Instruct", "n_responses": 4 }
[ false, false, false, false ]
["No suitable equation has been found that matches exactly 354.","There is no valid solution for the(...TRUNCATED)
"[{\"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 suita(...TRUNCATED)
[ [ false ], [ false ], [], [] ]
[["No suitable equation has been found that matches exactly 354."],["There is no valid solution for (...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 1912, \"span_text\": \"No s(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"No suit(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED)
2025-11-17
test
main
Qwen/Qwen2.5-0.5B-Instruct
0
eval_0
1
2025-11-17T08:20:15.192152
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_Q05B_base-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
19*8 - 50
countdown_3arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 5007, \\\"number(...TRUNCATED)
test
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
["To solve the problem, we need to find a combination of operations (addition, subtraction, multipli(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://127.0.0.1:51075/v1","backend":"litellm","chat_template_applied":true,"generation_(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-0.5B-Instruct", "n_responses": 4 }
[ false, false, false, false ]
[ null, null, null, "\\(8 \\times 50 - 50 = 350\\)" ]
"[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\(...TRUNCATED)
"[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED)
[ [], [], [], [ false ] ]
[ [], [], [], [ "\\(8 \\times 50 - 50 = 350\\)" ] ]
"[[], [], [], [{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 3368, \"span_te(...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)
2025-11-17
test
main
Qwen/Qwen2.5-0.5B-Instruct
0
eval_0
1
2025-11-17T08:20:15.192154
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_Q05B_base-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
40 + 46 + 38
countdown_3arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 5008, \\\"number(...TRUNCATED)
test
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 given list [38, 46, 40] and aiming for 124, we need to find a combi(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://127.0.0.1:51075/v1","backend":"litellm","chat_template_applied":true,"generation_(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-0.5B-Instruct", "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)
2025-11-17
test
main
Qwen/Qwen2.5-0.5B-Instruct
0
eval_0
1
2025-11-17T08:20:15.192156
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_Q05B_base-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
19 + 92 + 21
countdown_3arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 5009, \\\"number(...TRUNCATED)
test
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
["To solve the problem, we need to find a combination of addition, subtraction, multiplication, divi(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://127.0.0.1:51075/v1","backend":"litellm","chat_template_applied":true,"generation_(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-0.5B-Instruct", "n_responses": 4 }
[ false, true, false, false ]
["19 + 21 + 92 + 40 = 132","92 + 21 + 19 = 132","No solution exists for the given set of numbers.",n(...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Expression does not equal stated result\", \"answer_block\": (...TRUNCATED)
[ [ false ], [ true ], [ false ], [] ]
[["19 + 21 + 92 + 40 = 132"],["92 + 21 + 19 = 132"],["No solution exists for the given set of number(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 1076, \"span_text\": \"19 +(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Expression does not equal stated result\", \"answer_block\":(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":1,"pass_at_n":1,"percent_correct":0.25,"skill_co(...TRUNCATED)
2025-11-17
test
main
Qwen/Qwen2.5-0.5B-Instruct
0
eval_0
1
2025-11-17T08:20:15.192157
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_Q05B_base-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
23*(21 - 7)
countdown_3arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 5010, \\\"number(...TRUNCATED)
test
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, we need to find a combination of addition, subtraction, multiplication, and (...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://127.0.0.1:51075/v1","backend":"litellm","chat_template_applied":true,"generation_(...TRUNCATED)
{ "backend": "litellm", "model_name": "hosted_vllm/Qwen/Qwen2.5-0.5B-Instruct", "n_responses": 4 }
[ false, false, false, false ]
[null,null,"No direct solution exists for achieving 322 using the numbers [23, 21, 7]. The given set(...TRUNCATED)
"[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\(...TRUNCATED)
"[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED)
[ [], [], [ false ], [] ]
[[],[],["No direct solution exists for achieving 322 using the numbers [23, 21, 7]. The given set of(...TRUNCATED)
"[[], [], [{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 3352, \"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)
2025-11-17
test
main
Qwen/Qwen2.5-0.5B-Instruct
0
eval_0
1
2025-11-17T08:20:15.192159
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_Q05B_base-eval_0
End of preview. Expand in Data Studio

Experiment Tracker: FinEval_16k_fulleval_Q05B_base

Experiment Description: Simple test experiment for Skill Factory workflows.

Start Time: 2025-11-17T01:18:46.319480

Tracker Dataset: TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_Q05B_base__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_Q05B_base__v1', 'experiment_metadata')

# Load complete training datasets
sft_data = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_Q05B_base__v1', 'training_data__sft')
sft_metadata = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_Q05B_base__v1', 'training_data__sft_metadata')

# Load complete configurations
sft_hyperparams = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_Q05B_base__v1', 'hyperparameters__sft')
rl_hyperparams = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_Q05B_base__v1', 'hyperparameters__rl')

# Load stage-specific logs
sft_logs = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_Q05B_base__v1', 'logs__sft')
rl_logs = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_Q05B_base__v1', 'logs__rl')

# Load evaluation results with annotations
sft_eval_results = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_Q05B_base__v1', 'evals_eval_sft')
rl_eval_results = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_Q05B_base__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_Q05B_base - {stage_name} - {SFT/RL}


Generated by SkillFactory Experiment Management System All artifacts uploaded immediately as stages complete with perfect data provenance

Downloads last month
12