Dataset Viewer
Search is not available for this dataset
question
string | answer
string | task_config
string | task_source
string | prompt
list | model_responses
list | model_responses__eval_is_correct
list | all_other_columns
string | original_split
string | answer_index
int64 | answer_key
string | choices
dict | difficulty
string | domain
string | evaluation_type
string | expected_answer_format
string | id
string | metadata
string | original_answer
string | prompt__few_shot
list | source
string | task_type
string | variant
string | model_responses__greedy
list | model_responses__greedy__finish_reason_length_flags
list | model_responses__greedy__length_partial_responses
list | prompt__greedy__metadata
dict | model_responses__greedy__metadata
dict | model_responses__greedy__eval_is_correct
list | model_responses__greedy__eval_extracted_answers
list | model_responses__greedy__eval_extraction_metadata
dict | model_responses__greedy__eval_evaluation_metadata
list | model_responses__greedy__internal_answers__eval_is_correct
list | model_responses__greedy__internal_answers__eval_extracted_answers
list | model_responses__greedy__internal_answers__eval_extraction_metadata
dict | model_responses__greedy__internal_answers__eval_evaluation_metadata
list | model_responses__greedy__metrics
dict | eval_date
string | split
string | revision_name
string | model_path
string | checkpoint_step
int64 | stage_name
string | stage_number
int64 | timestamp
string | eval_repo_id
string |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
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 [73, 48], create an equation that equals 121. 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.
|
48 + 73
|
countdown_2arg
|
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 [73, 48], create an equation that equals 121. 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"
}
] |
[] |
[] |
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 6756, \"numbers\": [73, 48], \"target\": 121, \"expression\": \"48 + 73\"}"}
|
test
| null | null | null | null | null | null | null | null |
{"source_dataset": "countdown", "source_index": 6756, "numbers": [73, 48], "target": 121, "expression": "48 + 73"}
| null | null | null | null | null |
[
""
] |
[
false
] |
[
""
] |
{
"api_url": "http://127.0.0.1:50231/v1",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"temperature": 0,
"top_p": 1
},
"model_name": "hosted_vllm/TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-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 [73, 48], create an equation that equals 121. 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-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl",
"n_responses": 1
}
|
[
false
] |
[
null
] |
{
"all_spans_summary": null,
"empty_response": true,
"extraction_method": "llm_judge",
"final_span_info": null,
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"total_spans": 0,
"total_spans_found": null
}
|
[
{
"answer_block": null,
"comparison_type": null,
"correct_answer": null,
"error": null,
"evaluation_method": null,
"extracted_answer": null,
"final_answer": null,
"is_correct": null,
"is_equivalent": null,
"method": "llm_judge",
"reason": "no_answer"
}
] |
[
[]
] |
[
[]
] |
{
"empty_response": true,
"extraction_method": "llm_judge",
"internal_spans_detailed": [],
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"span_positions": [],
"total_internal_spans": 0,
"total_spans": 0
}
|
[
[]
] |
{
"flips_by": [
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": null,
"percent_correct": null,
"skill_count": {
"answer_revision": [
0
],
"best_of_n": [
0
],
"reflect_close": [
0
],
"reflect_open": [
0
],
"reflection_sbon": [
0
],
"sample_close": [
0
],
"sample_open": [
0
],
"voting": [
0
]
},
"total_responses": 1
}
|
2025-08-20
|
test
|
main
|
TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl
| 0 |
eval_rl
| 1 |
2025-08-20T16:03:14.939053
|
TAUR-dev/D-EVAL__standard_eval_v3__SBON_skills_in_rl_v2__1e6_all_tasks_eval-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 [14, 54], create an equation that equals 756. 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.
|
14*54
|
countdown_2arg
|
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 [14, 54], create an equation that equals 756. 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"
}
] |
[] |
[] |
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 6685, \"numbers\": [14, 54], \"target\": 756, \"expression\": \"14*54\"}"}
|
test
| null | null | null | null | null | null | null | null |
{"source_dataset": "countdown", "source_index": 6685, "numbers": [14, 54], "target": 756, "expression": "14*54"}
| null | null | null | null | null |
[
""
] |
[
false
] |
[
""
] |
{
"api_url": "http://127.0.0.1:50231/v1",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"temperature": 0,
"top_p": 1
},
"model_name": "hosted_vllm/TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-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 [14, 54], create an equation that equals 756. 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-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl",
"n_responses": 1
}
|
[
false
] |
[
null
] |
{
"all_spans_summary": null,
"empty_response": true,
"extraction_method": "llm_judge",
"final_span_info": null,
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"total_spans": 0,
"total_spans_found": null
}
|
[
{
"answer_block": null,
"comparison_type": null,
"correct_answer": null,
"error": null,
"evaluation_method": null,
"extracted_answer": null,
"final_answer": null,
"is_correct": null,
"is_equivalent": null,
"method": "llm_judge",
"reason": "no_answer"
}
] |
[
[]
] |
[
[]
] |
{
"empty_response": true,
"extraction_method": "llm_judge",
"internal_spans_detailed": [],
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"span_positions": [],
"total_internal_spans": 0,
"total_spans": 0
}
|
[
[]
] |
{
"flips_by": [
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": null,
"percent_correct": null,
"skill_count": {
"answer_revision": [
0
],
"best_of_n": [
0
],
"reflect_close": [
0
],
"reflect_open": [
0
],
"reflection_sbon": [
0
],
"sample_close": [
0
],
"sample_open": [
0
],
"voting": [
0
]
},
"total_responses": 1
}
|
2025-08-20
|
test
|
main
|
TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl
| 0 |
eval_rl
| 1 |
2025-08-20T16:03:14.939063
|
TAUR-dev/D-EVAL__standard_eval_v3__SBON_skills_in_rl_v2__1e6_all_tasks_eval-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 [40, 70], create an equation that equals 110. 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.
|
40 + 70
|
countdown_2arg
|
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 [40, 70], create an equation that equals 110. 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"
}
] |
[] |
[] |
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 5824, \"numbers\": [40, 70], \"target\": 110, \"expression\": \"40 + 70\"}"}
|
test
| null | null | null | null | null | null | null | null |
{"source_dataset": "countdown", "source_index": 5824, "numbers": [40, 70], "target": 110, "expression": "40 + 70"}
| null | null | null | null | null |
[
""
] |
[
false
] |
[
""
] |
{
"api_url": "http://127.0.0.1:50231/v1",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"temperature": 0,
"top_p": 1
},
"model_name": "hosted_vllm/TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-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 [40, 70], create an equation that equals 110. 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-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl",
"n_responses": 1
}
|
[
false
] |
[
null
] |
{
"all_spans_summary": null,
"empty_response": true,
"extraction_method": "llm_judge",
"final_span_info": null,
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"total_spans": 0,
"total_spans_found": null
}
|
[
{
"answer_block": null,
"comparison_type": null,
"correct_answer": null,
"error": null,
"evaluation_method": null,
"extracted_answer": null,
"final_answer": null,
"is_correct": null,
"is_equivalent": null,
"method": "llm_judge",
"reason": "no_answer"
}
] |
[
[]
] |
[
[]
] |
{
"empty_response": true,
"extraction_method": "llm_judge",
"internal_spans_detailed": [],
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"span_positions": [],
"total_internal_spans": 0,
"total_spans": 0
}
|
[
[]
] |
{
"flips_by": [
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": null,
"percent_correct": null,
"skill_count": {
"answer_revision": [
0
],
"best_of_n": [
0
],
"reflect_close": [
0
],
"reflect_open": [
0
],
"reflection_sbon": [
0
],
"sample_close": [
0
],
"sample_open": [
0
],
"voting": [
0
]
},
"total_responses": 1
}
|
2025-08-20
|
test
|
main
|
TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl
| 0 |
eval_rl
| 1 |
2025-08-20T16:03:14.939066
|
TAUR-dev/D-EVAL__standard_eval_v3__SBON_skills_in_rl_v2__1e6_all_tasks_eval-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 [30, 31], create an equation that equals 930. 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.
|
31*30
|
countdown_2arg
|
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 [30, 31], create an equation that equals 930. 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"
}
] |
[] |
[] |
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 5930, \"numbers\": [30, 31], \"target\": 930, \"expression\": \"31*30\"}"}
|
test
| null | null | null | null | null | null | null | null |
{"source_dataset": "countdown", "source_index": 5930, "numbers": [30, 31], "target": 930, "expression": "31*30"}
| null | null | null | null | null |
[
""
] |
[
false
] |
[
""
] |
{
"api_url": "http://127.0.0.1:50231/v1",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"temperature": 0,
"top_p": 1
},
"model_name": "hosted_vllm/TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-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 [30, 31], create an equation that equals 930. 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-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl",
"n_responses": 1
}
|
[
false
] |
[
null
] |
{
"all_spans_summary": null,
"empty_response": true,
"extraction_method": "llm_judge",
"final_span_info": null,
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"total_spans": 0,
"total_spans_found": null
}
|
[
{
"answer_block": null,
"comparison_type": null,
"correct_answer": null,
"error": null,
"evaluation_method": null,
"extracted_answer": null,
"final_answer": null,
"is_correct": null,
"is_equivalent": null,
"method": "llm_judge",
"reason": "no_answer"
}
] |
[
[]
] |
[
[]
] |
{
"empty_response": true,
"extraction_method": "llm_judge",
"internal_spans_detailed": [],
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"span_positions": [],
"total_internal_spans": 0,
"total_spans": 0
}
|
[
[]
] |
{
"flips_by": [
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": null,
"percent_correct": null,
"skill_count": {
"answer_revision": [
0
],
"best_of_n": [
0
],
"reflect_close": [
0
],
"reflect_open": [
0
],
"reflection_sbon": [
0
],
"sample_close": [
0
],
"sample_open": [
0
],
"voting": [
0
]
},
"total_responses": 1
}
|
2025-08-20
|
test
|
main
|
TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl
| 0 |
eval_rl
| 1 |
2025-08-20T16:03:14.939068
|
TAUR-dev/D-EVAL__standard_eval_v3__SBON_skills_in_rl_v2__1e6_all_tasks_eval-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 [25, 78], create an equation that equals 103. 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.
|
25 + 78
|
countdown_2arg
|
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 [25, 78], create an equation that equals 103. 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"
}
] |
[] |
[] |
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 5864, \"numbers\": [25, 78], \"target\": 103, \"expression\": \"25 + 78\"}"}
|
test
| null | null | null | null | null | null | null | null |
{"source_dataset": "countdown", "source_index": 5864, "numbers": [25, 78], "target": 103, "expression": "25 + 78"}
| null | null | null | null | null |
[
""
] |
[
false
] |
[
""
] |
{
"api_url": "http://127.0.0.1:50231/v1",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"temperature": 0,
"top_p": 1
},
"model_name": "hosted_vllm/TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-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 [25, 78], create an equation that equals 103. 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-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl",
"n_responses": 1
}
|
[
false
] |
[
null
] |
{
"all_spans_summary": null,
"empty_response": true,
"extraction_method": "llm_judge",
"final_span_info": null,
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"total_spans": 0,
"total_spans_found": null
}
|
[
{
"answer_block": null,
"comparison_type": null,
"correct_answer": null,
"error": null,
"evaluation_method": null,
"extracted_answer": null,
"final_answer": null,
"is_correct": null,
"is_equivalent": null,
"method": "llm_judge",
"reason": "no_answer"
}
] |
[
[]
] |
[
[]
] |
{
"empty_response": true,
"extraction_method": "llm_judge",
"internal_spans_detailed": [],
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"span_positions": [],
"total_internal_spans": 0,
"total_spans": 0
}
|
[
[]
] |
{
"flips_by": [
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": null,
"percent_correct": null,
"skill_count": {
"answer_revision": [
0
],
"best_of_n": [
0
],
"reflect_close": [
0
],
"reflect_open": [
0
],
"reflection_sbon": [
0
],
"sample_close": [
0
],
"sample_open": [
0
],
"voting": [
0
]
},
"total_responses": 1
}
|
2025-08-20
|
test
|
main
|
TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl
| 0 |
eval_rl
| 1 |
2025-08-20T16:03:14.939070
|
TAUR-dev/D-EVAL__standard_eval_v3__SBON_skills_in_rl_v2__1e6_all_tasks_eval-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 [85, 76], create an equation that equals 161. 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.
|
76 + 85
|
countdown_2arg
|
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 [85, 76], create an equation that equals 161. 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"
}
] |
[] |
[] |
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 6120, \"numbers\": [85, 76], \"target\": 161, \"expression\": \"76 + 85\"}"}
|
test
| null | null | null | null | null | null | null | null |
{"source_dataset": "countdown", "source_index": 6120, "numbers": [85, 76], "target": 161, "expression": "76 + 85"}
| null | null | null | null | null |
[
""
] |
[
false
] |
[
""
] |
{
"api_url": "http://127.0.0.1:50231/v1",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"temperature": 0,
"top_p": 1
},
"model_name": "hosted_vllm/TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-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 [85, 76], create an equation that equals 161. 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-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl",
"n_responses": 1
}
|
[
false
] |
[
null
] |
{
"all_spans_summary": null,
"empty_response": true,
"extraction_method": "llm_judge",
"final_span_info": null,
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"total_spans": 0,
"total_spans_found": null
}
|
[
{
"answer_block": null,
"comparison_type": null,
"correct_answer": null,
"error": null,
"evaluation_method": null,
"extracted_answer": null,
"final_answer": null,
"is_correct": null,
"is_equivalent": null,
"method": "llm_judge",
"reason": "no_answer"
}
] |
[
[]
] |
[
[]
] |
{
"empty_response": true,
"extraction_method": "llm_judge",
"internal_spans_detailed": [],
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"span_positions": [],
"total_internal_spans": 0,
"total_spans": 0
}
|
[
[]
] |
{
"flips_by": [
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": null,
"percent_correct": null,
"skill_count": {
"answer_revision": [
0
],
"best_of_n": [
0
],
"reflect_close": [
0
],
"reflect_open": [
0
],
"reflection_sbon": [
0
],
"sample_close": [
0
],
"sample_open": [
0
],
"voting": [
0
]
},
"total_responses": 1
}
|
2025-08-20
|
test
|
main
|
TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl
| 0 |
eval_rl
| 1 |
2025-08-20T16:03:14.939072
|
TAUR-dev/D-EVAL__standard_eval_v3__SBON_skills_in_rl_v2__1e6_all_tasks_eval-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 [45, 75], create an equation that equals 120. 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.
|
45 + 75
|
countdown_2arg
|
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 [45, 75], create an equation that equals 120. 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"
}
] |
[] |
[] |
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 5533, \"numbers\": [45, 75], \"target\": 120, \"expression\": \"45 + 75\"}"}
|
test
| null | null | null | null | null | null | null | null |
{"source_dataset": "countdown", "source_index": 5533, "numbers": [45, 75], "target": 120, "expression": "45 + 75"}
| null | null | null | null | null |
[
""
] |
[
false
] |
[
""
] |
{
"api_url": "http://127.0.0.1:50231/v1",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"temperature": 0,
"top_p": 1
},
"model_name": "hosted_vllm/TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-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 [45, 75], create an equation that equals 120. 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-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl",
"n_responses": 1
}
|
[
false
] |
[
null
] |
{
"all_spans_summary": null,
"empty_response": true,
"extraction_method": "llm_judge",
"final_span_info": null,
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"total_spans": 0,
"total_spans_found": null
}
|
[
{
"answer_block": null,
"comparison_type": null,
"correct_answer": null,
"error": null,
"evaluation_method": null,
"extracted_answer": null,
"final_answer": null,
"is_correct": null,
"is_equivalent": null,
"method": "llm_judge",
"reason": "no_answer"
}
] |
[
[]
] |
[
[]
] |
{
"empty_response": true,
"extraction_method": "llm_judge",
"internal_spans_detailed": [],
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"span_positions": [],
"total_internal_spans": 0,
"total_spans": 0
}
|
[
[]
] |
{
"flips_by": [
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": null,
"percent_correct": null,
"skill_count": {
"answer_revision": [
0
],
"best_of_n": [
0
],
"reflect_close": [
0
],
"reflect_open": [
0
],
"reflection_sbon": [
0
],
"sample_close": [
0
],
"sample_open": [
0
],
"voting": [
0
]
},
"total_responses": 1
}
|
2025-08-20
|
test
|
main
|
TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl
| 0 |
eval_rl
| 1 |
2025-08-20T16:03:14.939074
|
TAUR-dev/D-EVAL__standard_eval_v3__SBON_skills_in_rl_v2__1e6_all_tasks_eval-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 [62, 14], create an equation that equals 868. 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.
|
14*62
|
countdown_2arg
|
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 [62, 14], create an equation that equals 868. 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"
}
] |
[] |
[] |
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 5746, \"numbers\": [62, 14], \"target\": 868, \"expression\": \"14*62\"}"}
|
test
| null | null | null | null | null | null | null | null |
{"source_dataset": "countdown", "source_index": 5746, "numbers": [62, 14], "target": 868, "expression": "14*62"}
| null | null | null | null | null |
[
""
] |
[
false
] |
[
""
] |
{
"api_url": "http://127.0.0.1:50231/v1",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"temperature": 0,
"top_p": 1
},
"model_name": "hosted_vllm/TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-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 [62, 14], create an equation that equals 868. 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-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl",
"n_responses": 1
}
|
[
false
] |
[
null
] |
{
"all_spans_summary": null,
"empty_response": true,
"extraction_method": "llm_judge",
"final_span_info": null,
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"total_spans": 0,
"total_spans_found": null
}
|
[
{
"answer_block": null,
"comparison_type": null,
"correct_answer": null,
"error": null,
"evaluation_method": null,
"extracted_answer": null,
"final_answer": null,
"is_correct": null,
"is_equivalent": null,
"method": "llm_judge",
"reason": "no_answer"
}
] |
[
[]
] |
[
[]
] |
{
"empty_response": true,
"extraction_method": "llm_judge",
"internal_spans_detailed": [],
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"span_positions": [],
"total_internal_spans": 0,
"total_spans": 0
}
|
[
[]
] |
{
"flips_by": [
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": null,
"percent_correct": null,
"skill_count": {
"answer_revision": [
0
],
"best_of_n": [
0
],
"reflect_close": [
0
],
"reflect_open": [
0
],
"reflection_sbon": [
0
],
"sample_close": [
0
],
"sample_open": [
0
],
"voting": [
0
]
},
"total_responses": 1
}
|
2025-08-20
|
test
|
main
|
TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl
| 0 |
eval_rl
| 1 |
2025-08-20T16:03:14.939076
|
TAUR-dev/D-EVAL__standard_eval_v3__SBON_skills_in_rl_v2__1e6_all_tasks_eval-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 [87, 6], create an equation that equals 522. 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*87
|
countdown_2arg
|
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 [87, 6], create an equation that equals 522. 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"
}
] |
[] |
[] |
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 5021, \"numbers\": [87, 6], \"target\": 522, \"expression\": \"6*87\"}"}
|
test
| null | null | null | null | null | null | null | null |
{"source_dataset": "countdown", "source_index": 5021, "numbers": [87, 6], "target": 522, "expression": "6*87"}
| null | null | null | null | null |
[
""
] |
[
false
] |
[
""
] |
{
"api_url": "http://127.0.0.1:50231/v1",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"temperature": 0,
"top_p": 1
},
"model_name": "hosted_vllm/TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-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 [87, 6], create an equation that equals 522. 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-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl",
"n_responses": 1
}
|
[
false
] |
[
null
] |
{
"all_spans_summary": null,
"empty_response": true,
"extraction_method": "llm_judge",
"final_span_info": null,
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"total_spans": 0,
"total_spans_found": null
}
|
[
{
"answer_block": null,
"comparison_type": null,
"correct_answer": null,
"error": null,
"evaluation_method": null,
"extracted_answer": null,
"final_answer": null,
"is_correct": null,
"is_equivalent": null,
"method": "llm_judge",
"reason": "no_answer"
}
] |
[
[]
] |
[
[]
] |
{
"empty_response": true,
"extraction_method": "llm_judge",
"internal_spans_detailed": [],
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"span_positions": [],
"total_internal_spans": 0,
"total_spans": 0
}
|
[
[]
] |
{
"flips_by": [
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": null,
"percent_correct": null,
"skill_count": {
"answer_revision": [
0
],
"best_of_n": [
0
],
"reflect_close": [
0
],
"reflect_open": [
0
],
"reflection_sbon": [
0
],
"sample_close": [
0
],
"sample_open": [
0
],
"voting": [
0
]
},
"total_responses": 1
}
|
2025-08-20
|
test
|
main
|
TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl
| 0 |
eval_rl
| 1 |
2025-08-20T16:03:14.939078
|
TAUR-dev/D-EVAL__standard_eval_v3__SBON_skills_in_rl_v2__1e6_all_tasks_eval-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 [90, 66], create an equation that equals 156. 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.
|
90 + 66
|
countdown_2arg
|
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 [90, 66], create an equation that equals 156. 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"
}
] |
[] |
[] |
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 6819, \"numbers\": [90, 66], \"target\": 156, \"expression\": \"90 + 66\"}"}
|
test
| null | null | null | null | null | null | null | null |
{"source_dataset": "countdown", "source_index": 6819, "numbers": [90, 66], "target": 156, "expression": "90 + 66"}
| null | null | null | null | null |
[
""
] |
[
false
] |
[
""
] |
{
"api_url": "http://127.0.0.1:50231/v1",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"temperature": 0,
"top_p": 1
},
"model_name": "hosted_vllm/TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-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 [90, 66], create an equation that equals 156. 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-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl",
"n_responses": 1
}
|
[
false
] |
[
null
] |
{
"all_spans_summary": null,
"empty_response": true,
"extraction_method": "llm_judge",
"final_span_info": null,
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"total_spans": 0,
"total_spans_found": null
}
|
[
{
"answer_block": null,
"comparison_type": null,
"correct_answer": null,
"error": null,
"evaluation_method": null,
"extracted_answer": null,
"final_answer": null,
"is_correct": null,
"is_equivalent": null,
"method": "llm_judge",
"reason": "no_answer"
}
] |
[
[]
] |
[
[]
] |
{
"empty_response": true,
"extraction_method": "llm_judge",
"internal_spans_detailed": [],
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"span_positions": [],
"total_internal_spans": 0,
"total_spans": 0
}
|
[
[]
] |
{
"flips_by": [
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": null,
"percent_correct": null,
"skill_count": {
"answer_revision": [
0
],
"best_of_n": [
0
],
"reflect_close": [
0
],
"reflect_open": [
0
],
"reflection_sbon": [
0
],
"sample_close": [
0
],
"sample_open": [
0
],
"voting": [
0
]
},
"total_responses": 1
}
|
2025-08-20
|
test
|
main
|
TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl
| 0 |
eval_rl
| 1 |
2025-08-20T16:03:14.939079
|
TAUR-dev/D-EVAL__standard_eval_v3__SBON_skills_in_rl_v2__1e6_all_tasks_eval-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 [17, 92], create an equation that equals 109. 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.
|
17 + 92
|
countdown_2arg
|
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 [17, 92], create an equation that equals 109. 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"
}
] |
[] |
[] |
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 5462, \"numbers\": [17, 92], \"target\": 109, \"expression\": \"17 + 92\"}"}
|
test
| null | null | null | null | null | null | null | null |
{"source_dataset": "countdown", "source_index": 5462, "numbers": [17, 92], "target": 109, "expression": "17 + 92"}
| null | null | null | null | null |
[
""
] |
[
false
] |
[
""
] |
{
"api_url": "http://127.0.0.1:50231/v1",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"temperature": 0,
"top_p": 1
},
"model_name": "hosted_vllm/TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-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 [17, 92], create an equation that equals 109. 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-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl",
"n_responses": 1
}
|
[
false
] |
[
null
] |
{
"all_spans_summary": null,
"empty_response": true,
"extraction_method": "llm_judge",
"final_span_info": null,
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"total_spans": 0,
"total_spans_found": null
}
|
[
{
"answer_block": null,
"comparison_type": null,
"correct_answer": null,
"error": null,
"evaluation_method": null,
"extracted_answer": null,
"final_answer": null,
"is_correct": null,
"is_equivalent": null,
"method": "llm_judge",
"reason": "no_answer"
}
] |
[
[]
] |
[
[]
] |
{
"empty_response": true,
"extraction_method": "llm_judge",
"internal_spans_detailed": [],
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"span_positions": [],
"total_internal_spans": 0,
"total_spans": 0
}
|
[
[]
] |
{
"flips_by": [
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": null,
"percent_correct": null,
"skill_count": {
"answer_revision": [
0
],
"best_of_n": [
0
],
"reflect_close": [
0
],
"reflect_open": [
0
],
"reflection_sbon": [
0
],
"sample_close": [
0
],
"sample_open": [
0
],
"voting": [
0
]
},
"total_responses": 1
}
|
2025-08-20
|
test
|
main
|
TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl
| 0 |
eval_rl
| 1 |
2025-08-20T16:03:14.939081
|
TAUR-dev/D-EVAL__standard_eval_v3__SBON_skills_in_rl_v2__1e6_all_tasks_eval-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 [32, 20], create an equation that equals 640. 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.
|
32*20
|
countdown_2arg
|
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 [32, 20], create an equation that equals 640. 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"
}
] |
[] |
[] |
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 6675, \"numbers\": [32, 20], \"target\": 640, \"expression\": \"32*20\"}"}
|
test
| null | null | null | null | null | null | null | null |
{"source_dataset": "countdown", "source_index": 6675, "numbers": [32, 20], "target": 640, "expression": "32*20"}
| null | null | null | null | null |
[
""
] |
[
false
] |
[
""
] |
{
"api_url": "http://127.0.0.1:50231/v1",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"temperature": 0,
"top_p": 1
},
"model_name": "hosted_vllm/TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-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 [32, 20], create an equation that equals 640. 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-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl",
"n_responses": 1
}
|
[
false
] |
[
null
] |
{
"all_spans_summary": null,
"empty_response": true,
"extraction_method": "llm_judge",
"final_span_info": null,
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"total_spans": 0,
"total_spans_found": null
}
|
[
{
"answer_block": null,
"comparison_type": null,
"correct_answer": null,
"error": null,
"evaluation_method": null,
"extracted_answer": null,
"final_answer": null,
"is_correct": null,
"is_equivalent": null,
"method": "llm_judge",
"reason": "no_answer"
}
] |
[
[]
] |
[
[]
] |
{
"empty_response": true,
"extraction_method": "llm_judge",
"internal_spans_detailed": [],
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"span_positions": [],
"total_internal_spans": 0,
"total_spans": 0
}
|
[
[]
] |
{
"flips_by": [
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": null,
"percent_correct": null,
"skill_count": {
"answer_revision": [
0
],
"best_of_n": [
0
],
"reflect_close": [
0
],
"reflect_open": [
0
],
"reflection_sbon": [
0
],
"sample_close": [
0
],
"sample_open": [
0
],
"voting": [
0
]
},
"total_responses": 1
}
|
2025-08-20
|
test
|
main
|
TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl
| 0 |
eval_rl
| 1 |
2025-08-20T16:03:14.939083
|
TAUR-dev/D-EVAL__standard_eval_v3__SBON_skills_in_rl_v2__1e6_all_tasks_eval-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 [74, 51], 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.
|
74 + 51
|
countdown_2arg
|
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 [74, 51], 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"
}
] |
[] |
[] |
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 5279, \"numbers\": [74, 51], \"target\": 125, \"expression\": \"74 + 51\"}"}
|
test
| null | null | null | null | null | null | null | null |
{"source_dataset": "countdown", "source_index": 5279, "numbers": [74, 51], "target": 125, "expression": "74 + 51"}
| null | null | null | null | null |
[
""
] |
[
false
] |
[
""
] |
{
"api_url": "http://127.0.0.1:50231/v1",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"temperature": 0,
"top_p": 1
},
"model_name": "hosted_vllm/TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-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 [74, 51], 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/TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl",
"n_responses": 1
}
|
[
false
] |
[
null
] |
{
"all_spans_summary": null,
"empty_response": true,
"extraction_method": "llm_judge",
"final_span_info": null,
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"total_spans": 0,
"total_spans_found": null
}
|
[
{
"answer_block": null,
"comparison_type": null,
"correct_answer": null,
"error": null,
"evaluation_method": null,
"extracted_answer": null,
"final_answer": null,
"is_correct": null,
"is_equivalent": null,
"method": "llm_judge",
"reason": "no_answer"
}
] |
[
[]
] |
[
[]
] |
{
"empty_response": true,
"extraction_method": "llm_judge",
"internal_spans_detailed": [],
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"span_positions": [],
"total_internal_spans": 0,
"total_spans": 0
}
|
[
[]
] |
{
"flips_by": [
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": null,
"percent_correct": null,
"skill_count": {
"answer_revision": [
0
],
"best_of_n": [
0
],
"reflect_close": [
0
],
"reflect_open": [
0
],
"reflection_sbon": [
0
],
"sample_close": [
0
],
"sample_open": [
0
],
"voting": [
0
]
},
"total_responses": 1
}
|
2025-08-20
|
test
|
main
|
TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl
| 0 |
eval_rl
| 1 |
2025-08-20T16:03:14.939087
|
TAUR-dev/D-EVAL__standard_eval_v3__SBON_skills_in_rl_v2__1e6_all_tasks_eval-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 [80, 7], create an equation that equals 560. 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.
|
7*80
|
countdown_2arg
|
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 [80, 7], create an equation that equals 560. 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"
}
] |
[] |
[] |
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 5775, \"numbers\": [80, 7], \"target\": 560, \"expression\": \"7*80\"}"}
|
test
| null | null | null | null | null | null | null | null |
{"source_dataset": "countdown", "source_index": 5775, "numbers": [80, 7], "target": 560, "expression": "7*80"}
| null | null | null | null | null |
[
""
] |
[
false
] |
[
""
] |
{
"api_url": "http://127.0.0.1:50231/v1",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"temperature": 0,
"top_p": 1
},
"model_name": "hosted_vllm/TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-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 [80, 7], create an equation that equals 560. 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-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl",
"n_responses": 1
}
|
[
false
] |
[
null
] |
{
"all_spans_summary": null,
"empty_response": true,
"extraction_method": "llm_judge",
"final_span_info": null,
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"total_spans": 0,
"total_spans_found": null
}
|
[
{
"answer_block": null,
"comparison_type": null,
"correct_answer": null,
"error": null,
"evaluation_method": null,
"extracted_answer": null,
"final_answer": null,
"is_correct": null,
"is_equivalent": null,
"method": "llm_judge",
"reason": "no_answer"
}
] |
[
[]
] |
[
[]
] |
{
"empty_response": true,
"extraction_method": "llm_judge",
"internal_spans_detailed": [],
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"span_positions": [],
"total_internal_spans": 0,
"total_spans": 0
}
|
[
[]
] |
{
"flips_by": [
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": null,
"percent_correct": null,
"skill_count": {
"answer_revision": [
0
],
"best_of_n": [
0
],
"reflect_close": [
0
],
"reflect_open": [
0
],
"reflection_sbon": [
0
],
"sample_close": [
0
],
"sample_open": [
0
],
"voting": [
0
]
},
"total_responses": 1
}
|
2025-08-20
|
test
|
main
|
TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl
| 0 |
eval_rl
| 1 |
2025-08-20T16:03:14.939089
|
TAUR-dev/D-EVAL__standard_eval_v3__SBON_skills_in_rl_v2__1e6_all_tasks_eval-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 [73, 80], create an equation that equals 153. 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.
|
73 + 80
|
countdown_2arg
|
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 [73, 80], create an equation that equals 153. 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"
}
] |
[] |
[] |
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 6089, \"numbers\": [73, 80], \"target\": 153, \"expression\": \"73 + 80\"}"}
|
test
| null | null | null | null | null | null | null | null |
{"source_dataset": "countdown", "source_index": 6089, "numbers": [73, 80], "target": 153, "expression": "73 + 80"}
| null | null | null | null | null |
[
""
] |
[
false
] |
[
""
] |
{
"api_url": "http://127.0.0.1:50231/v1",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"temperature": 0,
"top_p": 1
},
"model_name": "hosted_vllm/TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-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 [73, 80], create an equation that equals 153. 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-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl",
"n_responses": 1
}
|
[
false
] |
[
null
] |
{
"all_spans_summary": null,
"empty_response": true,
"extraction_method": "llm_judge",
"final_span_info": null,
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"total_spans": 0,
"total_spans_found": null
}
|
[
{
"answer_block": null,
"comparison_type": null,
"correct_answer": null,
"error": null,
"evaluation_method": null,
"extracted_answer": null,
"final_answer": null,
"is_correct": null,
"is_equivalent": null,
"method": "llm_judge",
"reason": "no_answer"
}
] |
[
[]
] |
[
[]
] |
{
"empty_response": true,
"extraction_method": "llm_judge",
"internal_spans_detailed": [],
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"span_positions": [],
"total_internal_spans": 0,
"total_spans": 0
}
|
[
[]
] |
{
"flips_by": [
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": null,
"percent_correct": null,
"skill_count": {
"answer_revision": [
0
],
"best_of_n": [
0
],
"reflect_close": [
0
],
"reflect_open": [
0
],
"reflection_sbon": [
0
],
"sample_close": [
0
],
"sample_open": [
0
],
"voting": [
0
]
},
"total_responses": 1
}
|
2025-08-20
|
test
|
main
|
TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl
| 0 |
eval_rl
| 1 |
2025-08-20T16:03:14.939091
|
TAUR-dev/D-EVAL__standard_eval_v3__SBON_skills_in_rl_v2__1e6_all_tasks_eval-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 [27, 84], create an equation that equals 111. 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.
|
84 + 27
|
countdown_2arg
|
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 [27, 84], create an equation that equals 111. 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"
}
] |
[] |
[] |
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 5705, \"numbers\": [27, 84], \"target\": 111, \"expression\": \"84 + 27\"}"}
|
test
| null | null | null | null | null | null | null | null |
{"source_dataset": "countdown", "source_index": 5705, "numbers": [27, 84], "target": 111, "expression": "84 + 27"}
| null | null | null | null | null |
[
""
] |
[
false
] |
[
""
] |
{
"api_url": "http://127.0.0.1:50231/v1",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"temperature": 0,
"top_p": 1
},
"model_name": "hosted_vllm/TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-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 [27, 84], create an equation that equals 111. 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-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl",
"n_responses": 1
}
|
[
false
] |
[
null
] |
{
"all_spans_summary": null,
"empty_response": true,
"extraction_method": "llm_judge",
"final_span_info": null,
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"total_spans": 0,
"total_spans_found": null
}
|
[
{
"answer_block": null,
"comparison_type": null,
"correct_answer": null,
"error": null,
"evaluation_method": null,
"extracted_answer": null,
"final_answer": null,
"is_correct": null,
"is_equivalent": null,
"method": "llm_judge",
"reason": "no_answer"
}
] |
[
[]
] |
[
[]
] |
{
"empty_response": true,
"extraction_method": "llm_judge",
"internal_spans_detailed": [],
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"span_positions": [],
"total_internal_spans": 0,
"total_spans": 0
}
|
[
[]
] |
{
"flips_by": [
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": null,
"percent_correct": null,
"skill_count": {
"answer_revision": [
0
],
"best_of_n": [
0
],
"reflect_close": [
0
],
"reflect_open": [
0
],
"reflection_sbon": [
0
],
"sample_close": [
0
],
"sample_open": [
0
],
"voting": [
0
]
},
"total_responses": 1
}
|
2025-08-20
|
test
|
main
|
TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl
| 0 |
eval_rl
| 1 |
2025-08-20T16:03:14.939093
|
TAUR-dev/D-EVAL__standard_eval_v3__SBON_skills_in_rl_v2__1e6_all_tasks_eval-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 [66, 55], create an equation that equals 121. 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.
|
55 + 66
|
countdown_2arg
|
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 [66, 55], create an equation that equals 121. 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"
}
] |
[] |
[] |
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 6474, \"numbers\": [66, 55], \"target\": 121, \"expression\": \"55 + 66\"}"}
|
test
| null | null | null | null | null | null | null | null |
{"source_dataset": "countdown", "source_index": 6474, "numbers": [66, 55], "target": 121, "expression": "55 + 66"}
| null | null | null | null | null |
[
""
] |
[
false
] |
[
""
] |
{
"api_url": "http://127.0.0.1:50231/v1",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"temperature": 0,
"top_p": 1
},
"model_name": "hosted_vllm/TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-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 [66, 55], create an equation that equals 121. 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-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl",
"n_responses": 1
}
|
[
false
] |
[
null
] |
{
"all_spans_summary": null,
"empty_response": true,
"extraction_method": "llm_judge",
"final_span_info": null,
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"total_spans": 0,
"total_spans_found": null
}
|
[
{
"answer_block": null,
"comparison_type": null,
"correct_answer": null,
"error": null,
"evaluation_method": null,
"extracted_answer": null,
"final_answer": null,
"is_correct": null,
"is_equivalent": null,
"method": "llm_judge",
"reason": "no_answer"
}
] |
[
[]
] |
[
[]
] |
{
"empty_response": true,
"extraction_method": "llm_judge",
"internal_spans_detailed": [],
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"span_positions": [],
"total_internal_spans": 0,
"total_spans": 0
}
|
[
[]
] |
{
"flips_by": [
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": null,
"percent_correct": null,
"skill_count": {
"answer_revision": [
0
],
"best_of_n": [
0
],
"reflect_close": [
0
],
"reflect_open": [
0
],
"reflection_sbon": [
0
],
"sample_close": [
0
],
"sample_open": [
0
],
"voting": [
0
]
},
"total_responses": 1
}
|
2025-08-20
|
test
|
main
|
TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl
| 0 |
eval_rl
| 1 |
2025-08-20T16:03:14.939095
|
TAUR-dev/D-EVAL__standard_eval_v3__SBON_skills_in_rl_v2__1e6_all_tasks_eval-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 [66, 47], create an equation that equals 113. 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.
|
47 + 66
|
countdown_2arg
|
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 [66, 47], create an equation that equals 113. 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"
}
] |
[] |
[] |
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 5465, \"numbers\": [66, 47], \"target\": 113, \"expression\": \"47 + 66\"}"}
|
test
| null | null | null | null | null | null | null | null |
{"source_dataset": "countdown", "source_index": 5465, "numbers": [66, 47], "target": 113, "expression": "47 + 66"}
| null | null | null | null | null |
[
""
] |
[
false
] |
[
""
] |
{
"api_url": "http://127.0.0.1:50231/v1",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"temperature": 0,
"top_p": 1
},
"model_name": "hosted_vllm/TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-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 [66, 47], create an equation that equals 113. 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-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl",
"n_responses": 1
}
|
[
false
] |
[
null
] |
{
"all_spans_summary": null,
"empty_response": true,
"extraction_method": "llm_judge",
"final_span_info": null,
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"total_spans": 0,
"total_spans_found": null
}
|
[
{
"answer_block": null,
"comparison_type": null,
"correct_answer": null,
"error": null,
"evaluation_method": null,
"extracted_answer": null,
"final_answer": null,
"is_correct": null,
"is_equivalent": null,
"method": "llm_judge",
"reason": "no_answer"
}
] |
[
[]
] |
[
[]
] |
{
"empty_response": true,
"extraction_method": "llm_judge",
"internal_spans_detailed": [],
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"span_positions": [],
"total_internal_spans": 0,
"total_spans": 0
}
|
[
[]
] |
{
"flips_by": [
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": null,
"percent_correct": null,
"skill_count": {
"answer_revision": [
0
],
"best_of_n": [
0
],
"reflect_close": [
0
],
"reflect_open": [
0
],
"reflection_sbon": [
0
],
"sample_close": [
0
],
"sample_open": [
0
],
"voting": [
0
]
},
"total_responses": 1
}
|
2025-08-20
|
test
|
main
|
TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl
| 0 |
eval_rl
| 1 |
2025-08-20T16:03:14.939096
|
TAUR-dev/D-EVAL__standard_eval_v3__SBON_skills_in_rl_v2__1e6_all_tasks_eval-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 [75, 91], create an equation that equals 166. 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.
|
91 + 75
|
countdown_2arg
|
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 [75, 91], create an equation that equals 166. 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"
}
] |
[] |
[] |
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 6286, \"numbers\": [75, 91], \"target\": 166, \"expression\": \"91 + 75\"}"}
|
test
| null | null | null | null | null | null | null | null |
{"source_dataset": "countdown", "source_index": 6286, "numbers": [75, 91], "target": 166, "expression": "91 + 75"}
| null | null | null | null | null |
[
""
] |
[
false
] |
[
""
] |
{
"api_url": "http://127.0.0.1:50231/v1",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"temperature": 0,
"top_p": 1
},
"model_name": "hosted_vllm/TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-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 [75, 91], create an equation that equals 166. 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-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl",
"n_responses": 1
}
|
[
false
] |
[
null
] |
{
"all_spans_summary": null,
"empty_response": true,
"extraction_method": "llm_judge",
"final_span_info": null,
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"total_spans": 0,
"total_spans_found": null
}
|
[
{
"answer_block": null,
"comparison_type": null,
"correct_answer": null,
"error": null,
"evaluation_method": null,
"extracted_answer": null,
"final_answer": null,
"is_correct": null,
"is_equivalent": null,
"method": "llm_judge",
"reason": "no_answer"
}
] |
[
[]
] |
[
[]
] |
{
"empty_response": true,
"extraction_method": "llm_judge",
"internal_spans_detailed": [],
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"span_positions": [],
"total_internal_spans": 0,
"total_spans": 0
}
|
[
[]
] |
{
"flips_by": [
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": null,
"percent_correct": null,
"skill_count": {
"answer_revision": [
0
],
"best_of_n": [
0
],
"reflect_close": [
0
],
"reflect_open": [
0
],
"reflection_sbon": [
0
],
"sample_close": [
0
],
"sample_open": [
0
],
"voting": [
0
]
},
"total_responses": 1
}
|
2025-08-20
|
test
|
main
|
TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl
| 0 |
eval_rl
| 1 |
2025-08-20T16:03:14.939098
|
TAUR-dev/D-EVAL__standard_eval_v3__SBON_skills_in_rl_v2__1e6_all_tasks_eval-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 [81, 40], create an equation that equals 121. 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.
|
81 + 40
|
countdown_2arg
|
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 [81, 40], create an equation that equals 121. 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"
}
] |
[] |
[] |
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 6311, \"numbers\": [81, 40], \"target\": 121, \"expression\": \"81 + 40\"}"}
|
test
| null | null | null | null | null | null | null | null |
{"source_dataset": "countdown", "source_index": 6311, "numbers": [81, 40], "target": 121, "expression": "81 + 40"}
| null | null | null | null | null |
[
""
] |
[
false
] |
[
""
] |
{
"api_url": "http://127.0.0.1:50231/v1",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"temperature": 0,
"top_p": 1
},
"model_name": "hosted_vllm/TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-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 [81, 40], create an equation that equals 121. 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-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl",
"n_responses": 1
}
|
[
false
] |
[
null
] |
{
"all_spans_summary": null,
"empty_response": true,
"extraction_method": "llm_judge",
"final_span_info": null,
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"total_spans": 0,
"total_spans_found": null
}
|
[
{
"answer_block": null,
"comparison_type": null,
"correct_answer": null,
"error": null,
"evaluation_method": null,
"extracted_answer": null,
"final_answer": null,
"is_correct": null,
"is_equivalent": null,
"method": "llm_judge",
"reason": "no_answer"
}
] |
[
[]
] |
[
[]
] |
{
"empty_response": true,
"extraction_method": "llm_judge",
"internal_spans_detailed": [],
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"span_positions": [],
"total_internal_spans": 0,
"total_spans": 0
}
|
[
[]
] |
{
"flips_by": [
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": null,
"percent_correct": null,
"skill_count": {
"answer_revision": [
0
],
"best_of_n": [
0
],
"reflect_close": [
0
],
"reflect_open": [
0
],
"reflection_sbon": [
0
],
"sample_close": [
0
],
"sample_open": [
0
],
"voting": [
0
]
},
"total_responses": 1
}
|
2025-08-20
|
test
|
main
|
TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl
| 0 |
eval_rl
| 1 |
2025-08-20T16:03:14.939100
|
TAUR-dev/D-EVAL__standard_eval_v3__SBON_skills_in_rl_v2__1e6_all_tasks_eval-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 [37, 87], create an equation that equals 124. 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.
|
37 + 87
|
countdown_2arg
|
countdown
|
[
{
"content": "Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(your answer)</answer>.\n\n# Problem\nUsing the numbers in the list [37, 87], create an equation that equals 124. 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"
}
] |
[] |
[] |
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 6106, \"numbers\": [37, 87], \"target\": 124, \"expression\": \"37 + 87\"}"}
|
test
| null | null | null | null | null | null | null | null |
{"source_dataset": "countdown", "source_index": 6106, "numbers": [37, 87], "target": 124, "expression": "37 + 87"}
| null | null | null | null | null |
[
""
] |
[
false
] |
[
""
] |
{
"api_url": "http://127.0.0.1:50231/v1",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"temperature": 0,
"top_p": 1
},
"model_name": "hosted_vllm/TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-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 [37, 87], create an equation that equals 124. 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-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl",
"n_responses": 1
}
|
[
false
] |
[
null
] |
{
"all_spans_summary": null,
"empty_response": true,
"extraction_method": "llm_judge",
"final_span_info": null,
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"total_spans": 0,
"total_spans_found": null
}
|
[
{
"answer_block": null,
"comparison_type": null,
"correct_answer": null,
"error": null,
"evaluation_method": null,
"extracted_answer": null,
"final_answer": null,
"is_correct": null,
"is_equivalent": null,
"method": "llm_judge",
"reason": "no_answer"
}
] |
[
[]
] |
[
[]
] |
{
"empty_response": true,
"extraction_method": "llm_judge",
"internal_spans_detailed": [],
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"span_positions": [],
"total_internal_spans": 0,
"total_spans": 0
}
|
[
[]
] |
{
"flips_by": [
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": null,
"percent_correct": null,
"skill_count": {
"answer_revision": [
0
],
"best_of_n": [
0
],
"reflect_close": [
0
],
"reflect_open": [
0
],
"reflection_sbon": [
0
],
"sample_close": [
0
],
"sample_open": [
0
],
"voting": [
0
]
},
"total_responses": 1
}
|
2025-08-20
|
test
|
main
|
TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl
| 0 |
eval_rl
| 1 |
2025-08-20T16:03:14.939102
|
TAUR-dev/D-EVAL__standard_eval_v3__SBON_skills_in_rl_v2__1e6_all_tasks_eval-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 [63, 52], create an equation that equals 115. 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.
|
63 + 52
|
countdown_2arg
|
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 [63, 52], create an equation that equals 115. 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"
}
] |
[] |
[] |
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 6182, \"numbers\": [63, 52], \"target\": 115, \"expression\": \"63 + 52\"}"}
|
test
| null | null | null | null | null | null | null | null |
{"source_dataset": "countdown", "source_index": 6182, "numbers": [63, 52], "target": 115, "expression": "63 + 52"}
| null | null | null | null | null |
[
""
] |
[
false
] |
[
""
] |
{
"api_url": "http://127.0.0.1:50231/v1",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"temperature": 0,
"top_p": 1
},
"model_name": "hosted_vllm/TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-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 [63, 52], create an equation that equals 115. 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-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl",
"n_responses": 1
}
|
[
false
] |
[
null
] |
{
"all_spans_summary": null,
"empty_response": true,
"extraction_method": "llm_judge",
"final_span_info": null,
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"total_spans": 0,
"total_spans_found": null
}
|
[
{
"answer_block": null,
"comparison_type": null,
"correct_answer": null,
"error": null,
"evaluation_method": null,
"extracted_answer": null,
"final_answer": null,
"is_correct": null,
"is_equivalent": null,
"method": "llm_judge",
"reason": "no_answer"
}
] |
[
[]
] |
[
[]
] |
{
"empty_response": true,
"extraction_method": "llm_judge",
"internal_spans_detailed": [],
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"span_positions": [],
"total_internal_spans": 0,
"total_spans": 0
}
|
[
[]
] |
{
"flips_by": [
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": null,
"percent_correct": null,
"skill_count": {
"answer_revision": [
0
],
"best_of_n": [
0
],
"reflect_close": [
0
],
"reflect_open": [
0
],
"reflection_sbon": [
0
],
"sample_close": [
0
],
"sample_open": [
0
],
"voting": [
0
]
},
"total_responses": 1
}
|
2025-08-20
|
test
|
main
|
TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl
| 0 |
eval_rl
| 1 |
2025-08-20T16:03:14.939104
|
TAUR-dev/D-EVAL__standard_eval_v3__SBON_skills_in_rl_v2__1e6_all_tasks_eval-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 [41, 22], create an equation that equals 902. 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.
|
41*22
|
countdown_2arg
|
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 [41, 22], create an equation that equals 902. 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"
}
] |
[] |
[] |
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 5055, \"numbers\": [41, 22], \"target\": 902, \"expression\": \"41*22\"}"}
|
test
| null | null | null | null | null | null | null | null |
{"source_dataset": "countdown", "source_index": 5055, "numbers": [41, 22], "target": 902, "expression": "41*22"}
| null | null | null | null | null |
[
""
] |
[
false
] |
[
""
] |
{
"api_url": "http://127.0.0.1:50231/v1",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"temperature": 0,
"top_p": 1
},
"model_name": "hosted_vllm/TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-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 [41, 22], create an equation that equals 902. 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-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl",
"n_responses": 1
}
|
[
false
] |
[
null
] |
{
"all_spans_summary": null,
"empty_response": true,
"extraction_method": "llm_judge",
"final_span_info": null,
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"total_spans": 0,
"total_spans_found": null
}
|
[
{
"answer_block": null,
"comparison_type": null,
"correct_answer": null,
"error": null,
"evaluation_method": null,
"extracted_answer": null,
"final_answer": null,
"is_correct": null,
"is_equivalent": null,
"method": "llm_judge",
"reason": "no_answer"
}
] |
[
[]
] |
[
[]
] |
{
"empty_response": true,
"extraction_method": "llm_judge",
"internal_spans_detailed": [],
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"span_positions": [],
"total_internal_spans": 0,
"total_spans": 0
}
|
[
[]
] |
{
"flips_by": [
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": null,
"percent_correct": null,
"skill_count": {
"answer_revision": [
0
],
"best_of_n": [
0
],
"reflect_close": [
0
],
"reflect_open": [
0
],
"reflection_sbon": [
0
],
"sample_close": [
0
],
"sample_open": [
0
],
"voting": [
0
]
},
"total_responses": 1
}
|
2025-08-20
|
test
|
main
|
TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl
| 0 |
eval_rl
| 1 |
2025-08-20T16:03:14.939105
|
TAUR-dev/D-EVAL__standard_eval_v3__SBON_skills_in_rl_v2__1e6_all_tasks_eval-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 [61, 64], 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.
|
64 + 61
|
countdown_2arg
|
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 [61, 64], 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"
}
] |
[] |
[] |
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 5846, \"numbers\": [61, 64], \"target\": 125, \"expression\": \"64 + 61\"}"}
|
test
| null | null | null | null | null | null | null | null |
{"source_dataset": "countdown", "source_index": 5846, "numbers": [61, 64], "target": 125, "expression": "64 + 61"}
| null | null | null | null | null |
[
""
] |
[
false
] |
[
""
] |
{
"api_url": "http://127.0.0.1:50231/v1",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"temperature": 0,
"top_p": 1
},
"model_name": "hosted_vllm/TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-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 [61, 64], 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/TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl",
"n_responses": 1
}
|
[
false
] |
[
null
] |
{
"all_spans_summary": null,
"empty_response": true,
"extraction_method": "llm_judge",
"final_span_info": null,
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"total_spans": 0,
"total_spans_found": null
}
|
[
{
"answer_block": null,
"comparison_type": null,
"correct_answer": null,
"error": null,
"evaluation_method": null,
"extracted_answer": null,
"final_answer": null,
"is_correct": null,
"is_equivalent": null,
"method": "llm_judge",
"reason": "no_answer"
}
] |
[
[]
] |
[
[]
] |
{
"empty_response": true,
"extraction_method": "llm_judge",
"internal_spans_detailed": [],
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"span_positions": [],
"total_internal_spans": 0,
"total_spans": 0
}
|
[
[]
] |
{
"flips_by": [
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": null,
"percent_correct": null,
"skill_count": {
"answer_revision": [
0
],
"best_of_n": [
0
],
"reflect_close": [
0
],
"reflect_open": [
0
],
"reflection_sbon": [
0
],
"sample_close": [
0
],
"sample_open": [
0
],
"voting": [
0
]
},
"total_responses": 1
}
|
2025-08-20
|
test
|
main
|
TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl
| 0 |
eval_rl
| 1 |
2025-08-20T16:03:14.939107
|
TAUR-dev/D-EVAL__standard_eval_v3__SBON_skills_in_rl_v2__1e6_all_tasks_eval-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 [97, 55], create an equation that equals 152. 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 + 55
|
countdown_2arg
|
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 [97, 55], create an equation that equals 152. 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"
}
] |
[] |
[] |
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 5013, \"numbers\": [97, 55], \"target\": 152, \"expression\": \"97 + 55\"}"}
|
test
| null | null | null | null | null | null | null | null |
{"source_dataset": "countdown", "source_index": 5013, "numbers": [97, 55], "target": 152, "expression": "97 + 55"}
| null | null | null | null | null |
[
""
] |
[
false
] |
[
""
] |
{
"api_url": "http://127.0.0.1:50231/v1",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"temperature": 0,
"top_p": 1
},
"model_name": "hosted_vllm/TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-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 [97, 55], create an equation that equals 152. 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-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl",
"n_responses": 1
}
|
[
false
] |
[
null
] |
{
"all_spans_summary": null,
"empty_response": true,
"extraction_method": "llm_judge",
"final_span_info": null,
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"total_spans": 0,
"total_spans_found": null
}
|
[
{
"answer_block": null,
"comparison_type": null,
"correct_answer": null,
"error": null,
"evaluation_method": null,
"extracted_answer": null,
"final_answer": null,
"is_correct": null,
"is_equivalent": null,
"method": "llm_judge",
"reason": "no_answer"
}
] |
[
[]
] |
[
[]
] |
{
"empty_response": true,
"extraction_method": "llm_judge",
"internal_spans_detailed": [],
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"span_positions": [],
"total_internal_spans": 0,
"total_spans": 0
}
|
[
[]
] |
{
"flips_by": [
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": null,
"percent_correct": null,
"skill_count": {
"answer_revision": [
0
],
"best_of_n": [
0
],
"reflect_close": [
0
],
"reflect_open": [
0
],
"reflection_sbon": [
0
],
"sample_close": [
0
],
"sample_open": [
0
],
"voting": [
0
]
},
"total_responses": 1
}
|
2025-08-20
|
test
|
main
|
TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl
| 0 |
eval_rl
| 1 |
2025-08-20T16:03:14.939109
|
TAUR-dev/D-EVAL__standard_eval_v3__SBON_skills_in_rl_v2__1e6_all_tasks_eval-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 [76, 43], create an equation that equals 119. 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.
|
76 + 43
|
countdown_2arg
|
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 [76, 43], create an equation that equals 119. 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"
}
] |
[] |
[] |
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 6175, \"numbers\": [76, 43], \"target\": 119, \"expression\": \"76 + 43\"}"}
|
test
| null | null | null | null | null | null | null | null |
{"source_dataset": "countdown", "source_index": 6175, "numbers": [76, 43], "target": 119, "expression": "76 + 43"}
| null | null | null | null | null |
[
""
] |
[
false
] |
[
""
] |
{
"api_url": "http://127.0.0.1:50231/v1",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"temperature": 0,
"top_p": 1
},
"model_name": "hosted_vllm/TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-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 [76, 43], create an equation that equals 119. 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-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl",
"n_responses": 1
}
|
[
false
] |
[
null
] |
{
"all_spans_summary": null,
"empty_response": true,
"extraction_method": "llm_judge",
"final_span_info": null,
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"total_spans": 0,
"total_spans_found": null
}
|
[
{
"answer_block": null,
"comparison_type": null,
"correct_answer": null,
"error": null,
"evaluation_method": null,
"extracted_answer": null,
"final_answer": null,
"is_correct": null,
"is_equivalent": null,
"method": "llm_judge",
"reason": "no_answer"
}
] |
[
[]
] |
[
[]
] |
{
"empty_response": true,
"extraction_method": "llm_judge",
"internal_spans_detailed": [],
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"span_positions": [],
"total_internal_spans": 0,
"total_spans": 0
}
|
[
[]
] |
{
"flips_by": [
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": null,
"percent_correct": null,
"skill_count": {
"answer_revision": [
0
],
"best_of_n": [
0
],
"reflect_close": [
0
],
"reflect_open": [
0
],
"reflection_sbon": [
0
],
"sample_close": [
0
],
"sample_open": [
0
],
"voting": [
0
]
},
"total_responses": 1
}
|
2025-08-20
|
test
|
main
|
TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl
| 0 |
eval_rl
| 1 |
2025-08-20T16:03:14.939111
|
TAUR-dev/D-EVAL__standard_eval_v3__SBON_skills_in_rl_v2__1e6_all_tasks_eval-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 [46, 5], create an equation that equals 230. 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.
|
5*46
|
countdown_2arg
|
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 [46, 5], create an equation that equals 230. 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"
}
] |
[] |
[] |
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 6248, \"numbers\": [46, 5], \"target\": 230, \"expression\": \"5*46\"}"}
|
test
| null | null | null | null | null | null | null | null |
{"source_dataset": "countdown", "source_index": 6248, "numbers": [46, 5], "target": 230, "expression": "5*46"}
| null | null | null | null | null |
[
""
] |
[
false
] |
[
""
] |
{
"api_url": "http://127.0.0.1:50231/v1",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"temperature": 0,
"top_p": 1
},
"model_name": "hosted_vllm/TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-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 [46, 5], create an equation that equals 230. 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-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl",
"n_responses": 1
}
|
[
false
] |
[
null
] |
{
"all_spans_summary": null,
"empty_response": true,
"extraction_method": "llm_judge",
"final_span_info": null,
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"total_spans": 0,
"total_spans_found": null
}
|
[
{
"answer_block": null,
"comparison_type": null,
"correct_answer": null,
"error": null,
"evaluation_method": null,
"extracted_answer": null,
"final_answer": null,
"is_correct": null,
"is_equivalent": null,
"method": "llm_judge",
"reason": "no_answer"
}
] |
[
[]
] |
[
[]
] |
{
"empty_response": true,
"extraction_method": "llm_judge",
"internal_spans_detailed": [],
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"span_positions": [],
"total_internal_spans": 0,
"total_spans": 0
}
|
[
[]
] |
{
"flips_by": [
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": null,
"percent_correct": null,
"skill_count": {
"answer_revision": [
0
],
"best_of_n": [
0
],
"reflect_close": [
0
],
"reflect_open": [
0
],
"reflection_sbon": [
0
],
"sample_close": [
0
],
"sample_open": [
0
],
"voting": [
0
]
},
"total_responses": 1
}
|
2025-08-20
|
test
|
main
|
TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl
| 0 |
eval_rl
| 1 |
2025-08-20T16:03:14.939113
|
TAUR-dev/D-EVAL__standard_eval_v3__SBON_skills_in_rl_v2__1e6_all_tasks_eval-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 [81, 20], create an equation that equals 101. 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.
|
81 + 20
|
countdown_2arg
|
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 [81, 20], create an equation that equals 101. 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"
}
] |
[] |
[] |
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 5899, \"numbers\": [81, 20], \"target\": 101, \"expression\": \"81 + 20\"}"}
|
test
| null | null | null | null | null | null | null | null |
{"source_dataset": "countdown", "source_index": 5899, "numbers": [81, 20], "target": 101, "expression": "81 + 20"}
| null | null | null | null | null |
[
""
] |
[
false
] |
[
""
] |
{
"api_url": "http://127.0.0.1:50231/v1",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"temperature": 0,
"top_p": 1
},
"model_name": "hosted_vllm/TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-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 [81, 20], create an equation that equals 101. 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-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl",
"n_responses": 1
}
|
[
false
] |
[
null
] |
{
"all_spans_summary": null,
"empty_response": true,
"extraction_method": "llm_judge",
"final_span_info": null,
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"total_spans": 0,
"total_spans_found": null
}
|
[
{
"answer_block": null,
"comparison_type": null,
"correct_answer": null,
"error": null,
"evaluation_method": null,
"extracted_answer": null,
"final_answer": null,
"is_correct": null,
"is_equivalent": null,
"method": "llm_judge",
"reason": "no_answer"
}
] |
[
[]
] |
[
[]
] |
{
"empty_response": true,
"extraction_method": "llm_judge",
"internal_spans_detailed": [],
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"span_positions": [],
"total_internal_spans": 0,
"total_spans": 0
}
|
[
[]
] |
{
"flips_by": [
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": null,
"percent_correct": null,
"skill_count": {
"answer_revision": [
0
],
"best_of_n": [
0
],
"reflect_close": [
0
],
"reflect_open": [
0
],
"reflection_sbon": [
0
],
"sample_close": [
0
],
"sample_open": [
0
],
"voting": [
0
]
},
"total_responses": 1
}
|
2025-08-20
|
test
|
main
|
TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl
| 0 |
eval_rl
| 1 |
2025-08-20T16:03:14.939115
|
TAUR-dev/D-EVAL__standard_eval_v3__SBON_skills_in_rl_v2__1e6_all_tasks_eval-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 [20, 90], create an equation that equals 110. 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.
|
20 + 90
|
countdown_2arg
|
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 [20, 90], create an equation that equals 110. 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"
}
] |
[] |
[] |
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 5420, \"numbers\": [20, 90], \"target\": 110, \"expression\": \"20 + 90\"}"}
|
test
| null | null | null | null | null | null | null | null |
{"source_dataset": "countdown", "source_index": 5420, "numbers": [20, 90], "target": 110, "expression": "20 + 90"}
| null | null | null | null | null |
[
""
] |
[
false
] |
[
""
] |
{
"api_url": "http://127.0.0.1:50231/v1",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"temperature": 0,
"top_p": 1
},
"model_name": "hosted_vllm/TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-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 [20, 90], create an equation that equals 110. 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-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl",
"n_responses": 1
}
|
[
false
] |
[
null
] |
{
"all_spans_summary": null,
"empty_response": true,
"extraction_method": "llm_judge",
"final_span_info": null,
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"total_spans": 0,
"total_spans_found": null
}
|
[
{
"answer_block": null,
"comparison_type": null,
"correct_answer": null,
"error": null,
"evaluation_method": null,
"extracted_answer": null,
"final_answer": null,
"is_correct": null,
"is_equivalent": null,
"method": "llm_judge",
"reason": "no_answer"
}
] |
[
[]
] |
[
[]
] |
{
"empty_response": true,
"extraction_method": "llm_judge",
"internal_spans_detailed": [],
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"span_positions": [],
"total_internal_spans": 0,
"total_spans": 0
}
|
[
[]
] |
{
"flips_by": [
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": null,
"percent_correct": null,
"skill_count": {
"answer_revision": [
0
],
"best_of_n": [
0
],
"reflect_close": [
0
],
"reflect_open": [
0
],
"reflection_sbon": [
0
],
"sample_close": [
0
],
"sample_open": [
0
],
"voting": [
0
]
},
"total_responses": 1
}
|
2025-08-20
|
test
|
main
|
TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl
| 0 |
eval_rl
| 1 |
2025-08-20T16:03:14.939117
|
TAUR-dev/D-EVAL__standard_eval_v3__SBON_skills_in_rl_v2__1e6_all_tasks_eval-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 [28, 92], create an equation that equals 120. 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.
|
92 + 28
|
countdown_2arg
|
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 [28, 92], create an equation that equals 120. 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"
}
] |
[] |
[] |
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 5628, \"numbers\": [28, 92], \"target\": 120, \"expression\": \"92 + 28\"}"}
|
test
| null | null | null | null | null | null | null | null |
{"source_dataset": "countdown", "source_index": 5628, "numbers": [28, 92], "target": 120, "expression": "92 + 28"}
| null | null | null | null | null |
[
""
] |
[
false
] |
[
""
] |
{
"api_url": "http://127.0.0.1:50231/v1",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"temperature": 0,
"top_p": 1
},
"model_name": "hosted_vllm/TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-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 [28, 92], create an equation that equals 120. 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-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl",
"n_responses": 1
}
|
[
false
] |
[
null
] |
{
"all_spans_summary": null,
"empty_response": true,
"extraction_method": "llm_judge",
"final_span_info": null,
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"total_spans": 0,
"total_spans_found": null
}
|
[
{
"answer_block": null,
"comparison_type": null,
"correct_answer": null,
"error": null,
"evaluation_method": null,
"extracted_answer": null,
"final_answer": null,
"is_correct": null,
"is_equivalent": null,
"method": "llm_judge",
"reason": "no_answer"
}
] |
[
[]
] |
[
[]
] |
{
"empty_response": true,
"extraction_method": "llm_judge",
"internal_spans_detailed": [],
"is_final_of_multiple": false,
"judge_model": "gpt-4.1-mini",
"question_context": true,
"span_positions": [],
"total_internal_spans": 0,
"total_spans": 0
}
|
[
[]
] |
{
"flips_by": [
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": null,
"percent_correct": null,
"skill_count": {
"answer_revision": [
0
],
"best_of_n": [
0
],
"reflect_close": [
0
],
"reflect_open": [
0
],
"reflection_sbon": [
0
],
"sample_close": [
0
],
"sample_open": [
0
],
"voting": [
0
]
},
"total_responses": 1
}
|
2025-08-20
|
test
|
main
|
TAUR-dev/M-SBON_skills_in_rl_v2__1e6_all_tasks_sft-rl_all_tasks-rl
| 0 |
eval_rl
| 1 |
2025-08-20T16:03:14.939119
|
TAUR-dev/D-EVAL__standard_eval_v3__SBON_skills_in_rl_v2__1e6_all_tasks_eval-eval_rl
|
End of preview. Expand
in Data Studio
Experiment Tracker: SBON_skills_in_rl_v2__1e6_all_tasks_eval
Experiment Description: Simple test experiment for Skill Factory workflows.
Start Time: 2025-08-20T15:49:48.049429
Tracker Dataset: TAUR-dev/D-ExpTracker__SBON_skills_in_rl_v2__1e6_all_tasks_eval__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__SBON_skills_in_rl_v2__1e6_all_tasks_eval__v1', 'experiment_metadata')
# Load complete training datasets
sft_data = load_dataset('TAUR-dev/D-ExpTracker__SBON_skills_in_rl_v2__1e6_all_tasks_eval__v1', 'training_data__sft')
sft_metadata = load_dataset('TAUR-dev/D-ExpTracker__SBON_skills_in_rl_v2__1e6_all_tasks_eval__v1', 'training_data__sft_metadata')
# Load complete configurations
sft_hyperparams = load_dataset('TAUR-dev/D-ExpTracker__SBON_skills_in_rl_v2__1e6_all_tasks_eval__v1', 'hyperparameters__sft')
rl_hyperparams = load_dataset('TAUR-dev/D-ExpTracker__SBON_skills_in_rl_v2__1e6_all_tasks_eval__v1', 'hyperparameters__rl')
# Load stage-specific logs
sft_logs = load_dataset('TAUR-dev/D-ExpTracker__SBON_skills_in_rl_v2__1e6_all_tasks_eval__v1', 'logs__sft')
rl_logs = load_dataset('TAUR-dev/D-ExpTracker__SBON_skills_in_rl_v2__1e6_all_tasks_eval__v1', 'logs__rl')
# Load evaluation results with annotations
sft_eval_results = load_dataset('TAUR-dev/D-ExpTracker__SBON_skills_in_rl_v2__1e6_all_tasks_eval__v1', 'evals_eval_sft')
rl_eval_results = load_dataset('TAUR-dev/D-ExpTracker__SBON_skills_in_rl_v2__1e6_all_tasks_eval__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 - SBON_skills_in_rl_v2__1e6_all_tasks_eval - {stage_name} - {SFT/RL}
Generated by SkillFactory Experiment Management System All artifacts uploaded immediately as stages complete with perfect data provenance
- Downloads last month
- 11