question stringlengths 7 989 | answer stringlengths 0 28 | task_config stringclasses 14 values | task_source stringclasses 6 values | prompt listlengths 1 1 | model_responses listlengths 0 0 | model_responses__eval_is_correct listlengths 0 0 | all_other_columns stringlengths 90 1.36k | original_split stringclasses 1 value | acronym stringclasses 341 values | answer_index int64 0 4 ⌀ | answer_key stringclasses 5 values | choices dict | difficulty stringclasses 1 value | domain stringclasses 1 value | evaluation_type stringclasses 1 value | expected_answer_format stringclasses 1 value | formed_acronym stringclasses 341 values | id stringlengths 7 34 ⌀ | length int64 4 8 ⌀ | letters stringclasses 600 values | metadata stringlengths 41 152 ⌀ | original_answer stringlengths 48 1.07k ⌀ | source stringclasses 601 values | task_type stringclasses 1 value | variant stringclasses 1 value | word_count int64 4 8 ⌀ | words listlengths 4 8 ⌀ | model_responses__best_of_n_atags listlengths 4 4 | model_responses__best_of_n_atags__finish_reason_length_flags listlengths 4 4 | model_responses__best_of_n_atags__length_partial_responses listlengths 4 4 | prompt__best_of_n_atags__metadata dict | model_responses__best_of_n_atags__metadata dict | model_responses__best_of_n_atags__eval_is_correct listlengths 4 4 | model_responses__best_of_n_atags__eval_extracted_answers listlengths 4 4 | model_responses__best_of_n_atags__eval_extraction_metadata stringlengths 120 5.54k | model_responses__best_of_n_atags__eval_evaluation_metadata stringlengths 224 5.46k | model_responses__best_of_n_atags__internal_answers__eval_is_correct listlengths 4 4 ⌀ | model_responses__best_of_n_atags__internal_answers__eval_extracted_answers listlengths 4 4 ⌀ | model_responses__best_of_n_atags__internal_answers__eval_extraction_metadata stringlengths 189 10.7k ⌀ | model_responses__best_of_n_atags__internal_answers__eval_evaluation_metadata stringlengths 70 5.47k ⌀ | model_responses__best_of_n_atags__metrics dict | eval_date stringdate 2025-11-16 00:00:00 2025-11-16 00:00:00 | split stringclasses 1 value | revision_name stringclasses 1 value | model_path stringclasses 1 value | checkpoint_step int64 0 0 | stage_name stringclasses 1 value | stage_number int64 1 1 | timestamp stringdate 2025-11-16 23:27:28 2025-11-16 23:27:28 | eval_repo_id stringclasses 1 value |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(your answer)</answer>.
# Problem
Using the numbers in the list [96, 97, 68], create an equation that equals 125. You can use basic arithmetic operations (+, -, *, /) and each number can only be used once. Your solution should include a series of steps "Step X:" where each step is a mathematical operation and the final step ultimately leads to the target number or it should be a single equation that results in the target.
Give your answer in the following format:
<answer>
(your answer)
</answer>
Where "(your answer)" is the list of steps to reach the target number or it should be a single equation that results in the target.
For example:
If the list of numbers was [1, 2, 3] and the target was 1, you could write:
<answer>
Step 1: 1 + 2 = 3
Step 2: 3 / 3 = 1
</answer>
or
<answer>
(1 + 2) / 3
</answer>
Let's think step by step. | 97 + 96 - 68 | countdown_3arg | countdown | [
{
"content": "Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(your answer)</answer>.\n\n# Problem\nUsing the numbers in the list [96, 97, 68], create an equation that equals 125. You can use basic arithmetic operations (+, -, *,... | [] | [] | {"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 5000, \"numbers\": [96, 97, 68], \"target\": 125, \"expression\": \"97 + 96 - 68\"}", "task_source": "countdown"} | test | null | null | null | null | null | null | null | null | null | null | null | null | {"source_dataset": "countdown", "source_index": 5000, "numbers": [96, 97, 68], "target": 125, "expression": "97 + 96 - 68"} | null | null | null | null | null | null | [
"To solve for 125 using the given numbers [96, 97, 68], we need to find a combination of these numbers through addition, subtraction, multiplication, and division that will result in 125. Let's break down the process:\n\n### Step-by-Step Reasoning\n\n1. **Identify Possible Combinations**:\n - We start with three ... | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {
"api_url": "http://127.0.0.1:40441/v1",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 16384,
"n": 1,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8
},
"model_name": "hosted_vllm/TAUR-dev/M-AT_star_sft-sft",
"prompt": [
{
"content": "Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(your answer)</answer>.\n\n# Problem\nUsing the numbers in the list [96, 97, 68], create an equation that equals 125. You can use basic arithmetic operations (+, -, *, /) and each number can only be used once. Your solution should include a series of steps \"Step X:\" where each step is a mathematical operation and the final step ultimately leads to the target number or it should be a single equation that results in the target.\n\nGive your answer in the following format:\n<answer>\n(your answer)\n</answer>\n\nWhere \"(your answer)\" is the list of steps to reach the target number or it should be a single equation that results in the target. \n\nFor example:\nIf the list of numbers was [1, 2, 3] and the target was 1, you could write:\n<answer>\nStep 1: 1 + 2 = 3\nStep 2: 3 / 3 = 1\n</answer>\n\nor \n\n<answer>\n(1 + 2) / 3\n</answer>\n\nLet's think step by step.",
"role": "user"
}
]
} | {
"backend": "litellm",
"model_name": "hosted_vllm/TAUR-dev/M-AT_star_sft-sft",
"n_responses": 4
} | [
true,
false,
true,
true
] | [
"Step 1: 97 - 68 = 29\nStep 2: 96 + 29 = 125",
"((96 + 97) * 68)",
"(96 + 97) - 68 = 125",
"((97 - 68) + 96)"
] | [{"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 1090, "span_end": 1134, "original_span": "Step 1: 97 - 68 = 29\nStep 2: 96 + 29 = 125"}, {"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 537, "span_end": 553, "original_span": "((96 + 97) * 68)"}, {"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 456, "span_end": 476, "original_span": "(96 + 97) - 68 = 125"}, {"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 986, "span_end": 1004, "original_span": "((97 - 68) + 96)"}] | [{"is_correct": true, "error": null, "answer_block": "Step 1: 97 - 68 = 29\nStep 2: 96 + 29 = 125", "final_answer": 125.0}, {"is_correct": false, "error": "Expression does not equal stated result", "answer_block": "((96 + 97) * 68)", "final_answer": 125.0}, {"is_correct": true, "error": null, "answer_block": "(96 + 97) - 68 = 125", "final_answer": 125.0}, {"is_correct": true, "error": null, "answer_block": "((97 - 68) + 96)", "final_answer": 125.0}] | [
[
true
],
[
false
],
[
true
],
[
true
]
] | [
[
"Step 1: 97 - 68 = 29\nStep 2: 96 + 29 = 125"
],
[
"((96 + 97) * 68)"
],
[
"(96 + 97) - 68 = 125"
],
[
"((97 - 68) + 96)"
]
] | [[{"pattern_used": "answer tag", "confidence": 1.0, "position": 1090, "span_text": "Step 1: 97 - 68 = 29\nStep 2: 96 + 29 = 125", "extraction_type": "internal", "span_start": 1090, "span_end": 1134, "original_span": "Step 1: 97 - 68 = 29\nStep 2: 96 + 29 = 125"}], [{"pattern_used": "answer tag", "confidence": 1.0, "position": 537, "span_text": "((96 + 97) * 68)", "extraction_type": "internal", "span_start": 537, "span_end": 553, "original_span": "((96 + 97) * 68)"}], [{"pattern_used": "answer tag", "confidence": 1.0, "position": 456, "span_text": "(96 + 97) - 68 = 125", "extraction_type": "internal", "span_start": 456, "span_end": 476, "original_span": "(96 + 97) - 68 = 125"}], [{"pattern_used": "answer tag", "confidence": 1.0, "position": 986, "span_text": "((97 - 68) + 96)", "extraction_type": "internal", "span_start": 986, "span_end": 1004, "original_span": "((97 - 68) + 96)"}]] | [[{"is_correct": true, "error": null, "answer_block": "Step 1: 97 - 68 = 29\nStep 2: 96 + 29 = 125", "final_answer": 125.0}], [{"is_correct": false, "error": "Expression does not equal stated result", "answer_block": "((96 + 97) * 68)", "final_answer": 125.0}], [{"is_correct": true, "error": null, "answer_block": "(96 + 97) - 68 = 125", "final_answer": 125.0}], [{"is_correct": true, "error": null, "answer_block": "((97 - 68) + 96)", "final_answer": 125.0}]] | {
"flips_by": [
0,
0,
0,
0
],
"flips_total": 0,
"num_correct": 3,
"pass_at_n": 1,
"percent_correct": 0.75,
"skill_count": {
"answer_revision": [
0,
0,
0,
0
],
"best_of_n": [
0,
0,
0,
0
],
"reflect_close": [
0,
0,
0,
0
],
"reflect_open": [
0,
0,
0,
0
],
"reflection_sbon": [
0,
0,
0,
0
],
"sample_close": [
0,
0,
0,
0
],
"sample_open": [
0,
0,
0,
0
],
"vote_close": [
0,
0,
0,
0
],
"vote_open": [
0,
0,
0,
0
],
"voting": [
0,
0,
0,
0
]
},
"total_responses": 4
} | 2025-11-16 | test | main | TAUR-dev/M-AT_star_sft-sft | 0 | eval_sft | 1 | 2025-11-16T23:27:28.966899 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_AT_STAR_sft-eval_sft |
Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(your answer)</answer>.
# Problem
Using the numbers in the list [21, 80, 46], create an equation that equals 105. You can use basic arithmetic operations (+, -, *, /) and each number can only be used once. Your solution should include a series of steps "Step X:" where each step is a mathematical operation and the final step ultimately leads to the target number or it should be a single equation that results in the target.
Give your answer in the following format:
<answer>
(your answer)
</answer>
Where "(your answer)" is the list of steps to reach the target number or it should be a single equation that results in the target.
For example:
If the list of numbers was [1, 2, 3] and the target was 1, you could write:
<answer>
Step 1: 1 + 2 = 3
Step 2: 3 / 3 = 1
</answer>
or
<answer>
(1 + 2) / 3
</answer>
Let's think step by step. | 46 + 80 - 21 | countdown_3arg | countdown | [
{
"content": "Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(your answer)</answer>.\n\n# Problem\nUsing the numbers in the list [21, 80, 46], create an equation that equals 105. You can use basic arithmetic operations (+, -, *,... | [] | [] | {"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 5001, \"numbers\": [21, 80, 46], \"target\": 105, \"expression\": \"46 + 80 - 21\"}", "task_source": "countdown"} | test | null | null | null | null | null | null | null | null | null | null | null | null | {"source_dataset": "countdown", "source_index": 5001, "numbers": [21, 80, 46], "target": 105, "expression": "46 + 80 - 21"} | null | null | null | null | null | null | [
"To solve for 105 using the numbers [21, 80, 46], we need to combine these numbers through addition, subtraction, multiplication, and division while ensuring all numbers are utilized exactly once.\n\nHere’s one way to achieve this:\n\n1. Start with the largest number available.\n - Use 80 because it's close to ou... | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {
"api_url": "http://127.0.0.1:40441/v1",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 16384,
"n": 1,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8
},
"model_name": "hosted_vllm/TAUR-dev/M-AT_star_sft-sft",
"prompt": [
{
"content": "Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(your answer)</answer>.\n\n# Problem\nUsing the numbers in the list [21, 80, 46], create an equation that equals 105. You can use basic arithmetic operations (+, -, *, /) and each number can only be used once. Your solution should include a series of steps \"Step X:\" where each step is a mathematical operation and the final step ultimately leads to the target number or it should be a single equation that results in the target.\n\nGive your answer in the following format:\n<answer>\n(your answer)\n</answer>\n\nWhere \"(your answer)\" is the list of steps to reach the target number or it should be a single equation that results in the target. \n\nFor example:\nIf the list of numbers was [1, 2, 3] and the target was 1, you could write:\n<answer>\nStep 1: 1 + 2 = 3\nStep 2: 3 / 3 = 1\n</answer>\n\nor \n\n<answer>\n(1 + 2) / 3\n</answer>\n\nLet's think step by step.",
"role": "user"
}
]
} | {
"backend": "litellm",
"model_name": "hosted_vllm/TAUR-dev/M-AT_star_sft-sft",
"n_responses": 4
} | [
false,
false,
false,
false
] | [
"(80 + 21) + 4",
"None Found",
"21 + 80",
"80 + 21 - 46 = 105"
] | [{"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 879, "span_end": 894, "original_span": "(80 + 21) + 4"}, {"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 4052, "span_end": 4062, "original_span": "None Found"}, {"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 814, "span_end": 821, "original_span": "21 + 80"}, {"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 2268, "span_end": 2289, "original_span": "80 + 21 - 46 = 105"}] | [{"is_correct": false, "error": "Expression uses an unavailable or repeated number", "answer_block": "(80 + 21) + 4", "final_answer": 105.0}, {"is_correct": false, "error": "Could not evaluate expression", "answer_block": "None Found", "final_answer": null}, {"is_correct": false, "error": "Expression does not equal stated result", "answer_block": "21 + 80", "final_answer": 105.0}, {"is_correct": false, "error": "Expression does not equal stated result", "answer_block": "80 + 21 - 46 = 105", "final_answer": 105.0}] | [
[
false
],
[
false
],
[
false
],
[
false
]
] | [
[
"(80 + 21) + 4"
],
[
"None Found"
],
[
"21 + 80"
],
[
"80 + 21 - 46 = 105"
]
] | [[{"pattern_used": "answer tag", "confidence": 1.0, "position": 879, "span_text": "(80 + 21) + 4", "extraction_type": "internal", "span_start": 879, "span_end": 894, "original_span": "(80 + 21) + 4"}], [{"pattern_used": "answer tag", "confidence": 1.0, "position": 4052, "span_text": "None Found", "extraction_type": "internal", "span_start": 4052, "span_end": 4062, "original_span": "None Found"}], [{"pattern_used": "answer tag", "confidence": 1.0, "position": 814, "span_text": "21 + 80", "extraction_type": "internal", "span_start": 814, "span_end": 821, "original_span": "21 + 80"}], [{"pattern_used": "answer tag", "confidence": 1.0, "position": 2268, "span_text": "80 + 21 - 46 = 105", "extraction_type": "internal", "span_start": 2268, "span_end": 2289, "original_span": "80 + 21 - 46 = 105"}]] | [[{"is_correct": false, "error": "Expression uses an unavailable or repeated number", "answer_block": "(80 + 21) + 4", "final_answer": 105.0}], [{"is_correct": false, "error": "Could not evaluate expression", "answer_block": "None Found", "final_answer": null}], [{"is_correct": false, "error": "Expression does not equal stated result", "answer_block": "21 + 80", "final_answer": 105.0}], [{"is_correct": false, "error": "Expression does not equal stated result", "answer_block": "80 + 21 - 46 = 105", "final_answer": 105.0}]] | {
"flips_by": [
0,
0,
0,
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": 0,
"percent_correct": 0,
"skill_count": {
"answer_revision": [
0,
0,
0,
0
],
"best_of_n": [
0,
0,
0,
0
],
"reflect_close": [
0,
0,
0,
0
],
"reflect_open": [
0,
0,
0,
0
],
"reflection_sbon": [
0,
0,
0,
0
],
"sample_close": [
0,
0,
0,
0
],
"sample_open": [
0,
0,
0,
0
],
"vote_close": [
0,
0,
0,
0
],
"vote_open": [
0,
0,
0,
0
],
"voting": [
0,
0,
0,
0
]
},
"total_responses": 4
} | 2025-11-16 | test | main | TAUR-dev/M-AT_star_sft-sft | 0 | eval_sft | 1 | 2025-11-16T23:27:28.966909 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_AT_STAR_sft-eval_sft |
Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(your answer)</answer>.
# Problem
Using the numbers in the list [6, 76, 96], create an equation that equals 500. You can use basic arithmetic operations (+, -, *, /) and each number can only be used once. Your solution should include a series of steps "Step X:" where each step is a mathematical operation and the final step ultimately leads to the target number or it should be a single equation that results in the target.
Give your answer in the following format:
<answer>
(your answer)
</answer>
Where "(your answer)" is the list of steps to reach the target number or it should be a single equation that results in the target.
For example:
If the list of numbers was [1, 2, 3] and the target was 1, you could write:
<answer>
Step 1: 1 + 2 = 3
Step 2: 3 / 3 = 1
</answer>
or
<answer>
(1 + 2) / 3
</answer>
Let's think step by step. | 6*96 - 76 | countdown_3arg | countdown | [
{
"content": "Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(your answer)</answer>.\n\n# Problem\nUsing the numbers in the list [6, 76, 96], create an equation that equals 500. You can use basic arithmetic operations (+, -, *, ... | [] | [] | {"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 5002, \"numbers\": [6, 76, 96], \"target\": 500, \"expression\": \"6*96 - 76\"}", "task_source": "countdown"} | test | null | null | null | null | null | null | null | null | null | null | null | null | {"source_dataset": "countdown", "source_index": 5002, "numbers": [6, 76, 96], "target": 500, "expression": "6*96 - 76"} | null | null | null | null | null | null | [
"First, I'll try to understand the problem better by writing out a plan and go really deep into detail about how I should solve this.\nThe goal is to create an equation using the numbers from the given list [6, 76, 96] which will result in the target number 500.\nOne possible approach would be to start with one of ... | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {
"api_url": "http://127.0.0.1:40441/v1",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 16384,
"n": 1,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8
},
"model_name": "hosted_vllm/TAUR-dev/M-AT_star_sft-sft",
"prompt": [
{
"content": "Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(your answer)</answer>.\n\n# Problem\nUsing the numbers in the list [6, 76, 96], create an equation that equals 500. You can use basic arithmetic operations (+, -, *, /) and each number can only be used once. Your solution should include a series of steps \"Step X:\" where each step is a mathematical operation and the final step ultimately leads to the target number or it should be a single equation that results in the target.\n\nGive your answer in the following format:\n<answer>\n(your answer)\n</answer>\n\nWhere \"(your answer)\" is the list of steps to reach the target number or it should be a single equation that results in the target. \n\nFor example:\nIf the list of numbers was [1, 2, 3] and the target was 1, you could write:\n<answer>\nStep 1: 1 + 2 = 3\nStep 2: 3 / 3 = 1\n</answer>\n\nor \n\n<answer>\n(1 + 2) / 3\n</answer>\n\nLet's think step by step.",
"role": "user"
}
]
} | {
"backend": "litellm",
"model_name": "hosted_vllm/TAUR-dev/M-AT_star_sft-sft",
"n_responses": 4
} | [
false,
false,
false,
false
] | [
"((76 - 6) + 96) * 3 - 6",
null,
"76*96/6=500",
"6 + 76 + 96 = 178"
] | [{"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 1129, "span_end": 1155, "original_span": "((76 - 6) + 96) * 3 - 6"}, {"extraction_type": "final"}, {"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 2365, "span_end": 2376, "original_span": "76*96/6=500"}, {"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 549, "span_end": 568, "original_span": "6 + 76 + 96 = 178"}] | [{"is_correct": false, "error": "Expression does not equal stated result", "answer_block": "((76 - 6) + 96) * 3 - 6", "final_answer": 500.0}, {"evaluation_method": "response_processor", "reason": "no_extracted_answer", "extraction_result": "{'extraction_type': 'final'}"}, {"is_correct": false, "error": "Expression does not equal stated result", "answer_block": "76*96/6=500", "final_answer": 500.0}, {"is_correct": false, "error": "Incorrect final answer", "answer_block": "6 + 76 + 96 = 178", "final_answer": 178.0}] | [
[
false
],
[],
[
false
],
[
false
]
] | [
[
"((76 - 6) + 96) * 3 - 6"
],
[],
[
"76*96/6=500"
],
[
"6 + 76 + 96 = 178"
]
] | [[{"pattern_used": "answer tag", "confidence": 1.0, "position": 1129, "span_text": "((76 - 6) + 96) * 3 - 6", "extraction_type": "internal", "span_start": 1129, "span_end": 1155, "original_span": "((76 - 6) + 96) * 3 - 6"}], [], [{"pattern_used": "answer tag", "confidence": 1.0, "position": 2365, "span_text": "76*96/6=500", "extraction_type": "internal", "span_start": 2365, "span_end": 2376, "original_span": "76*96/6=500"}], [{"pattern_used": "answer tag", "confidence": 1.0, "position": 549, "span_text": "6 + 76 + 96 = 178", "extraction_type": "internal", "span_start": 549, "span_end": 568, "original_span": "6 + 76 + 96 = 178"}]] | [[{"is_correct": false, "error": "Expression does not equal stated result", "answer_block": "((76 - 6) + 96) * 3 - 6", "final_answer": 500.0}], [], [{"is_correct": false, "error": "Expression does not equal stated result", "answer_block": "76*96/6=500", "final_answer": 500.0}], [{"is_correct": false, "error": "Incorrect final answer", "answer_block": "6 + 76 + 96 = 178", "final_answer": 178.0}]] | {
"flips_by": [
0,
0,
0,
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": 0,
"percent_correct": 0,
"skill_count": {
"answer_revision": [
0,
0,
0,
0
],
"best_of_n": [
0,
0,
0,
0
],
"reflect_close": [
0,
0,
0,
0
],
"reflect_open": [
0,
0,
0,
0
],
"reflection_sbon": [
0,
0,
0,
0
],
"sample_close": [
0,
0,
0,
0
],
"sample_open": [
0,
0,
0,
0
],
"vote_close": [
0,
0,
0,
0
],
"vote_open": [
0,
0,
0,
0
],
"voting": [
0,
0,
0,
0
]
},
"total_responses": 4
} | 2025-11-16 | test | main | TAUR-dev/M-AT_star_sft-sft | 0 | eval_sft | 1 | 2025-11-16T23:27:28.966911 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_AT_STAR_sft-eval_sft |
Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(your answer)</answer>.
# Problem
Using the numbers in the list [42, 12, 3], create an equation that equals 630. You can use basic arithmetic operations (+, -, *, /) and each number can only be used once. Your solution should include a series of steps "Step X:" where each step is a mathematical operation and the final step ultimately leads to the target number or it should be a single equation that results in the target.
Give your answer in the following format:
<answer>
(your answer)
</answer>
Where "(your answer)" is the list of steps to reach the target number or it should be a single equation that results in the target.
For example:
If the list of numbers was [1, 2, 3] and the target was 1, you could write:
<answer>
Step 1: 1 + 2 = 3
Step 2: 3 / 3 = 1
</answer>
or
<answer>
(1 + 2) / 3
</answer>
Let's think step by step. | 42*(12 + 3) | countdown_3arg | countdown | [
{
"content": "Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(your answer)</answer>.\n\n# Problem\nUsing the numbers in the list [42, 12, 3], create an equation that equals 630. You can use basic arithmetic operations (+, -, *, ... | [] | [] | {"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 5003, \"numbers\": [42, 12, 3], \"target\": 630, \"expression\": \"42*(12 + 3)\"}", "task_source": "countdown"} | test | null | null | null | null | null | null | null | null | null | null | null | null | {"source_dataset": "countdown", "source_index": 5003, "numbers": [42, 12, 3], "target": 630, "expression": "42*(12 + 3)"} | null | null | null | null | null | null | [
"Rewritten Question:\n\nCreate an equation using the numbers from the set {42, 12, 3} such that the result equals 630.\n- Step 1: Multiply 42 by 12.\n- Step 2: Divide the product obtained in Step 1 by 3.\n\nFinal Equation: (42 * 12) / 3\n\n<answer>\n(42 * 12) / 3\n</answer>",
"First, I'll try to understand the pr... | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {
"api_url": "http://127.0.0.1:40441/v1",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 16384,
"n": 1,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8
},
"model_name": "hosted_vllm/TAUR-dev/M-AT_star_sft-sft",
"prompt": [
{
"content": "Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(your answer)</answer>.\n\n# Problem\nUsing the numbers in the list [42, 12, 3], create an equation that equals 630. You can use basic arithmetic operations (+, -, *, /) and each number can only be used once. Your solution should include a series of steps \"Step X:\" where each step is a mathematical operation and the final step ultimately leads to the target number or it should be a single equation that results in the target.\n\nGive your answer in the following format:\n<answer>\n(your answer)\n</answer>\n\nWhere \"(your answer)\" is the list of steps to reach the target number or it should be a single equation that results in the target. \n\nFor example:\nIf the list of numbers was [1, 2, 3] and the target was 1, you could write:\n<answer>\nStep 1: 1 + 2 = 3\nStep 2: 3 / 3 = 1\n</answer>\n\nor \n\n<answer>\n(1 + 2) / 3\n</answer>\n\nLet's think step by step.",
"role": "user"
}
]
} | {
"backend": "litellm",
"model_name": "hosted_vllm/TAUR-dev/M-AT_star_sft-sft",
"n_responses": 4
} | [
false,
false,
false,
false
] | [
"(42 * 12) / 3",
"42 * 12 + 126",
"42 * 12 + 3",
"((42 - 12) * 3)"
] | [{"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 239, "span_end": 254, "original_span": "(42 * 12) / 3"}, {"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 1236, "span_end": 1249, "original_span": "42 * 12 + 126"}, {"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 204, "span_end": 215, "original_span": "42 * 12 + 3"}, {"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 2265, "span_end": 2283, "original_span": "((42 - 12) * 3)"}] | [{"is_correct": false, "error": "Expression does not equal stated result", "answer_block": "(42 * 12) / 3", "final_answer": 630.0}, {"is_correct": false, "error": "Expression uses an unavailable or repeated number", "answer_block": "42 * 12 + 126", "final_answer": 630.0}, {"is_correct": false, "error": "Expression does not equal stated result", "answer_block": "42 * 12 + 3", "final_answer": 630.0}, {"is_correct": false, "error": "Expression does not equal stated result", "answer_block": "((42 - 12) * 3)", "final_answer": 630.0}] | [
[
false
],
[
false
],
[
false
],
[
false
]
] | [
[
"(42 * 12) / 3"
],
[
"42 * 12 + 126"
],
[
"42 * 12 + 3"
],
[
"((42 - 12) * 3)"
]
] | [[{"pattern_used": "answer tag", "confidence": 1.0, "position": 239, "span_text": "(42 * 12) / 3", "extraction_type": "internal", "span_start": 239, "span_end": 254, "original_span": "(42 * 12) / 3"}], [{"pattern_used": "answer tag", "confidence": 1.0, "position": 1236, "span_text": "42 * 12 + 126", "extraction_type": "internal", "span_start": 1236, "span_end": 1249, "original_span": "42 * 12 + 126"}], [{"pattern_used": "answer tag", "confidence": 1.0, "position": 204, "span_text": "42 * 12 + 3", "extraction_type": "internal", "span_start": 204, "span_end": 215, "original_span": "42 * 12 + 3"}], [{"pattern_used": "answer tag", "confidence": 1.0, "position": 2265, "span_text": "((42 - 12) * 3)", "extraction_type": "internal", "span_start": 2265, "span_end": 2283, "original_span": "((42 - 12) * 3)"}]] | [[{"is_correct": false, "error": "Expression does not equal stated result", "answer_block": "(42 * 12) / 3", "final_answer": 630.0}], [{"is_correct": false, "error": "Expression uses an unavailable or repeated number", "answer_block": "42 * 12 + 126", "final_answer": 630.0}], [{"is_correct": false, "error": "Expression does not equal stated result", "answer_block": "42 * 12 + 3", "final_answer": 630.0}], [{"is_correct": false, "error": "Expression does not equal stated result", "answer_block": "((42 - 12) * 3)", "final_answer": 630.0}]] | {
"flips_by": [
0,
0,
0,
0
],
"flips_total": 0,
"num_correct": 0,
"pass_at_n": 0,
"percent_correct": 0,
"skill_count": {
"answer_revision": [
0,
0,
0,
0
],
"best_of_n": [
0,
0,
0,
0
],
"reflect_close": [
0,
0,
0,
0
],
"reflect_open": [
0,
0,
0,
0
],
"reflection_sbon": [
0,
0,
0,
0
],
"sample_close": [
0,
0,
0,
0
],
"sample_open": [
0,
0,
0,
0
],
"vote_close": [
0,
0,
0,
0
],
"vote_open": [
0,
0,
0,
0
],
"voting": [
0,
0,
0,
0
]
},
"total_responses": 4
} | 2025-11-16 | test | main | TAUR-dev/M-AT_star_sft-sft | 0 | eval_sft | 1 | 2025-11-16T23:27:28.966914 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_AT_STAR_sft-eval_sft |
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED) | 86 + 69 - 52 | countdown_3arg | countdown | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 5005, \\\"number(...TRUNCATED) | test | null | null | null | null | null | null | null | null | null | null | null | null | "{\"source_dataset\": \"countdown\", \"source_index\": 5005, \"numbers\": [86, 69, 52], \"target\": (...TRUNCATED) | null | null | null | null | null | null | ["First, I'll try to understand the problem better by writing out a plan and go really deep into det(...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {"api_url":"http://127.0.0.1:40441/v1","backend":"litellm","chat_template_applied":true,"generation_(...TRUNCATED) | {
"backend": "litellm",
"model_name": "hosted_vllm/TAUR-dev/M-AT_star_sft-sft",
"n_responses": 4
} | [
false,
false,
true,
false
] | ["(86 + 52) - 69 = 103","Step 1: 86 + 69 = 155</step>\nStep 2: 155 - 52 = 103","86 - 52 + 69 = 103",(...TRUNCATED) | "[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED) | "[{\"is_correct\": false, \"error\": \"Expression does not equal stated result\", \"answer_block\": (...TRUNCATED) | [
[
false
],
[
false
],
[
true
],
[]
] | [["(86 + 52) - 69 = 103"],["Step 1: 86 + 69 = 155</step>\nStep 2: 155 - 52 = 103"],["86 - 52 + 69 = (...TRUNCATED) | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 1584, \"span_text\": \"(86 (...TRUNCATED) | "[[{\"is_correct\": false, \"error\": \"Expression does not equal stated result\", \"answer_block\":(...TRUNCATED) | {"flips_by":[0,0,0,0],"flips_total":0,"num_correct":1,"pass_at_n":1,"percent_correct":0.25,"skill_co(...TRUNCATED) | 2025-11-16 | test | main | TAUR-dev/M-AT_star_sft-sft | 0 | eval_sft | 1 | 2025-11-16T23:27:28.966916 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_AT_STAR_sft-eval_sft |
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED) | 63*7 - 87 | countdown_3arg | countdown | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 5006, \\\"number(...TRUNCATED) | test | null | null | null | null | null | null | null | null | null | null | null | null | "{\"source_dataset\": \"countdown\", \"source_index\": 5006, \"numbers\": [63, 7, 87], \"target\": 3(...TRUNCATED) | null | null | null | null | null | null | ["Rewritten Question:\n\nCreate an equation using the numbers from the given set {63, 7, 87} such th(...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {"api_url":"http://127.0.0.1:40441/v1","backend":"litellm","chat_template_applied":true,"generation_(...TRUNCATED) | {
"backend": "litellm",
"model_name": "hosted_vllm/TAUR-dev/M-AT_star_sft-sft",
"n_responses": 4
} | [
false,
false,
false,
true
] | [
"((63 + 7) * 87) - 63",
"87 - 63 + 7 + 63 - 7 = 354",
"(87 - 7) * 63 = 354",
"(63 * 7 - 87)"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED) | "[{\"is_correct\": false, \"error\": \"Expression does not equal stated result\", \"answer_block\": (...TRUNCATED) | [
[
false
],
[
false
],
[
false
],
[
true
]
] | [
[
"((63 + 7) * 87) - 63"
],
[
"87 - 63 + 7 + 63 - 7 = 354"
],
[
"(87 - 7) * 63 = 354"
],
[
"(63 * 7 - 87)"
]
] | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 374, \"span_text\": \"((63 (...TRUNCATED) | "[[{\"is_correct\": false, \"error\": \"Expression does not equal stated result\", \"answer_block\":(...TRUNCATED) | {"flips_by":[0,0,0,0],"flips_total":0,"num_correct":1,"pass_at_n":1,"percent_correct":0.25,"skill_co(...TRUNCATED) | 2025-11-16 | test | main | TAUR-dev/M-AT_star_sft-sft | 0 | eval_sft | 1 | 2025-11-16T23:27:28.966918 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_AT_STAR_sft-eval_sft |
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED) | 19*8 - 50 | countdown_3arg | countdown | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 5007, \\\"number(...TRUNCATED) | test | null | null | null | null | null | null | null | null | null | null | null | null | "{\"source_dataset\": \"countdown\", \"source_index\": 5007, \"numbers\": [8, 50, 19], \"target\": 1(...TRUNCATED) | null | null | null | null | null | null | ["Rewritten Question:\n\nCreate an equation using the numbers from the given set {8, 50, 19} that eq(...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {"api_url":"http://127.0.0.1:40441/v1","backend":"litellm","chat_template_applied":true,"generation_(...TRUNCATED) | {
"backend": "litellm",
"model_name": "hosted_vllm/TAUR-dev/M-AT_star_sft-sft",
"n_responses": 4
} | [
false,
false,
false,
false
] | [
"50 * 2 + 19",
"50 - 19 + 8 + 63",
"((8*19)+50)-19=102",
null
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED) | "[{\"is_correct\": false, \"error\": \"Expression does not equal stated result\", \"answer_block\": (...TRUNCATED) | [
[
false
],
[
false
],
[
false
],
[]
] | [
[
"50 * 2 + 19"
],
[
"50 - 19 + 8 + 63"
],
[
"((8*19)+50)-19=102"
],
[]
] | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 327, \"span_text\": \"50 * (...TRUNCATED) | "[[{\"is_correct\": false, \"error\": \"Expression does not equal stated result\", \"answer_block\":(...TRUNCATED) | {"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED) | 2025-11-16 | test | main | TAUR-dev/M-AT_star_sft-sft | 0 | eval_sft | 1 | 2025-11-16T23:27:28.966921 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_AT_STAR_sft-eval_sft |
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED) | 40 + 46 + 38 | countdown_3arg | countdown | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 5008, \\\"number(...TRUNCATED) | test | null | null | null | null | null | null | null | null | null | null | null | null | "{\"source_dataset\": \"countdown\", \"source_index\": 5008, \"numbers\": [38, 46, 40], \"target\": (...TRUNCATED) | null | null | null | null | null | null | ["Rewritten Question:\n\nCreate an equation using the numbers from the given set [38, 46, 40] which (...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {"api_url":"http://127.0.0.1:40441/v1","backend":"litellm","chat_template_applied":true,"generation_(...TRUNCATED) | {
"backend": "litellm",
"model_name": "hosted_vllm/TAUR-dev/M-AT_star_sft-sft",
"n_responses": 4
} | [
true,
false,
false,
true
] | [
"(46 + 40) + 38",
"(40 * 3) + 6",
"(46 + 40) = 86\n86 + 38 = 124",
"((38 + 46) + 40)"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED) | "[{\"is_correct\": true, \"error\": null, \"answer_block\": \"(46 + 40) + 38\", \"final_answer\": 12(...TRUNCATED) | [
[
true
],
[
false
],
[
false
],
[
true
]
] | [
[
"(46 + 40) + 38"
],
[
"(40 * 3) + 6"
],
[
"(46 + 40) = 86\n86 + 38 = 124"
],
[
"((38 + 46) + 40)"
]
] | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 615, \"span_text\": \"(46 +(...TRUNCATED) | "[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"(46 + 40) + 38\", \"final_answer\": 1(...TRUNCATED) | {"flips_by":[0,0,0,0],"flips_total":0,"num_correct":2,"pass_at_n":1,"percent_correct":0.5,"skill_cou(...TRUNCATED) | 2025-11-16 | test | main | TAUR-dev/M-AT_star_sft-sft | 0 | eval_sft | 1 | 2025-11-16T23:27:28.966923 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_AT_STAR_sft-eval_sft |
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED) | 19 + 92 + 21 | countdown_3arg | countdown | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 5009, \\\"number(...TRUNCATED) | test | null | null | null | null | null | null | null | null | null | null | null | null | "{\"source_dataset\": \"countdown\", \"source_index\": 5009, \"numbers\": [92, 21, 19], \"target\": (...TRUNCATED) | null | null | null | null | null | null | ["First, I'll try to understand the problem better by writing out a plan and go really deep into det(...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {"api_url":"http://127.0.0.1:40441/v1","backend":"litellm","chat_template_applied":true,"generation_(...TRUNCATED) | {
"backend": "litellm",
"model_name": "hosted_vllm/TAUR-dev/M-AT_star_sft-sft",
"n_responses": 4
} | [
false,
false,
false,
false
] | [
"92 - 19 + 59 = 132",
"92 + 21 - 19",
null,
"\\( 92 * 21 = 1932 \\\\\n1932 / 19 ≈ 101.7368 \\)"
] | "[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED) | "[{\"is_correct\": false, \"error\": \"Expression uses an unavailable or repeated number\", \"answer(...TRUNCATED) | [
[
false
],
[
false
],
[],
[
false
]
] | [
[
"92 - 19 + 59 = 132"
],
[
"92 + 21 - 19"
],
[],
[
"\\( 92 * 21 = 1932 \\\\\n1932 / 19 ≈ 101.7368 \\)"
]
] | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 628, \"span_text\": \"92 - (...TRUNCATED) | "[[{\"is_correct\": false, \"error\": \"Expression uses an unavailable or repeated number\", \"answe(...TRUNCATED) | {"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED) | 2025-11-16 | test | main | TAUR-dev/M-AT_star_sft-sft | 0 | eval_sft | 1 | 2025-11-16T23:27:28.966925 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_AT_STAR_sft-eval_sft |
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED) | 23*(21 - 7) | countdown_3arg | countdown | [{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED) | [] | [] | "{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 5010, \\\"number(...TRUNCATED) | test | null | null | null | null | null | null | null | null | null | null | null | null | "{\"source_dataset\": \"countdown\", \"source_index\": 5010, \"numbers\": [23, 21, 7], \"target\": 3(...TRUNCATED) | null | null | null | null | null | null | ["Rewritten Question:\n\nCreate an equation using the numbers from the given set {23, 21, 7} that eq(...TRUNCATED) | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {"api_url":"http://127.0.0.1:40441/v1","backend":"litellm","chat_template_applied":true,"generation_(...TRUNCATED) | {
"backend": "litellm",
"model_name": "hosted_vllm/TAUR-dev/M-AT_star_sft-sft",
"n_responses": 4
} | [
false,
false,
false,
false
] | ["(23 + 21 + 7) ÷ 7 = 322","((23 * 7) + 21) - 7","No valid equation found for creating 322 using th(...TRUNCATED) | "[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED) | "[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"(23 + 21(...TRUNCATED) | [
[
false
],
[
false
],
[
false
],
[]
] | [["(23 + 21 + 7) ÷ 7 = 322"],["((23 * 7) + 21) - 7"],["No valid equation found for creating 322 usi(...TRUNCATED) | "[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 834, \"span_text\": \"(23 +(...TRUNCATED) | "[[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"(23 + 2(...TRUNCATED) | {"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED) | 2025-11-16 | test | main | TAUR-dev/M-AT_star_sft-sft | 0 | eval_sft | 1 | 2025-11-16T23:27:28.966927 | TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_AT_STAR_sft-eval_sft |
End of preview. Expand
in Data Studio
Experiment Tracker: FinEval_16k_fulleval_AT_STAR_sft
Experiment Description: Simple test experiment for Skill Factory workflows.
Start Time: 2025-11-16T16:54:31.037358
Tracker Dataset: TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_AT_STAR_sft__v1
Stages Completed
Total stages: 1
Models Created
Dataset Configurations
This tracker dataset contains the following configurations with immediate upload as stages complete:
Training Data (Complete Datasets)
Hyperparameters (Complete Configurations)
Logs (Stage-Specific)
Evaluation Results (Complete with Annotations)
Metadata
- experiment_metadata: Timeline and stage information
Usage
Load specific configurations with:
from datasets import load_dataset
# Load experiment metadata
metadata = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_AT_STAR_sft__v1', 'experiment_metadata')
# Load complete training datasets
sft_data = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_AT_STAR_sft__v1', 'training_data__sft')
sft_metadata = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_AT_STAR_sft__v1', 'training_data__sft_metadata')
# Load complete configurations
sft_hyperparams = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_AT_STAR_sft__v1', 'hyperparameters__sft')
rl_hyperparams = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_AT_STAR_sft__v1', 'hyperparameters__rl')
# Load stage-specific logs
sft_logs = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_AT_STAR_sft__v1', 'logs__sft')
rl_logs = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_AT_STAR_sft__v1', 'logs__rl')
# Load evaluation results with annotations
sft_eval_results = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_AT_STAR_sft__v1', 'evals_eval_sft')
rl_eval_results = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_AT_STAR_sft__v1', 'evals_eval_rl')
Models
Registry
All models from this experiment are automatically registered in the SkillFactory Model Registry with:
- Complete training configuration (hyperparameters, datasets, methods)
- Experiment lineage (links back to this tracker dataset)
- Stage-specific metadata (SFT vs RL training details)
- Structured input data references (training datasets and configurations)
Registry entries follow the naming pattern: Model - FinEval_16k_fulleval_AT_STAR_sft - {stage_name} - {SFT/RL}
Generated by SkillFactory Experiment Management System All artifacts uploaded immediately as stages complete with perfect data provenance
- Downloads last month
- 7