Dataset Viewer
Auto-converted to Parquet Duplicate
question
stringlengths
7
989
answer
stringlengths
0
28
task_config
stringclasses
14 values
task_source
stringclasses
6 values
prompt
listlengths
1
1
model_responses
listlengths
0
0
model_responses__eval_is_correct
listlengths
0
0
all_other_columns
stringlengths
90
1.36k
original_split
stringclasses
1 value
acronym
stringclasses
341 values
answer_index
int64
0
4
answer_key
stringclasses
5 values
choices
dict
difficulty
stringclasses
1 value
domain
stringclasses
1 value
evaluation_type
stringclasses
1 value
expected_answer_format
stringclasses
1 value
formed_acronym
stringclasses
341 values
id
stringlengths
7
34
length
int64
4
8
letters
stringclasses
600 values
metadata
stringlengths
41
152
original_answer
stringlengths
48
1.07k
source
stringclasses
601 values
task_type
stringclasses
1 value
variant
stringclasses
1 value
word_count
int64
4
8
words
listlengths
4
8
model_responses__best_of_n_atags
listlengths
4
4
model_responses__best_of_n_atags__finish_reason_length_flags
listlengths
4
4
model_responses__best_of_n_atags__length_partial_responses
listlengths
4
4
prompt__best_of_n_atags__metadata
dict
model_responses__best_of_n_atags__metadata
dict
model_responses__best_of_n_atags__eval_is_correct
listlengths
4
4
model_responses__best_of_n_atags__eval_extracted_answers
listlengths
4
4
model_responses__best_of_n_atags__eval_extraction_metadata
stringlengths
120
956
model_responses__best_of_n_atags__eval_evaluation_metadata
stringlengths
224
835
model_responses__best_of_n_atags__internal_answers__eval_is_correct
listlengths
4
4
model_responses__best_of_n_atags__internal_answers__eval_extracted_answers
listlengths
4
4
model_responses__best_of_n_atags__internal_answers__eval_extraction_metadata
stringlengths
192
232k
model_responses__best_of_n_atags__internal_answers__eval_evaluation_metadata
stringlengths
70
162k
model_responses__best_of_n_atags__metrics
dict
eval_date
stringdate
2025-12-01 00:00:00
2025-12-01 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
2025-12-01 00:33:11
2025-12-01 00:33:11
eval_repo_id
stringclasses
1 value
Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(your answer)</answer>. # Problem Using the numbers in the list [96, 97, 68], create an equation that equals 125. You can use basic arithmetic operations (+, -, *, /) and each number can o...
97 + 96 - 68
countdown_3arg
countdown
[ { "content": "Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer>(your answer)</answer>.\n\n# Problem\nUsing the numbers in the list [96, 97, 68], create an equation that equals 125. You can use basic arithmetic operations (+, -, *,...
[]
[]
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 5000, \"numbers\": [96, 97, 68], \"target\": 125, \"expression\": \"97 + 96 - 68\"}", "task_source": "countdown"}
test
null
null
null
null
null
null
null
null
null
null
null
null
{"source_dataset": "countdown", "source_index": 5000, "numbers": [96, 97, 68], "target": 125, "expression": "97 + 96 - 68"}
null
null
null
null
null
null
[ "<think>\nOkay, so I need to use the numbers 96, 97, and 68 to make 125 using basic arithmetic operations. Each number can only be used once. Let me think about how to approach this.\n\nFirst, let me list out the numbers again: 96, 97, 68. The target is 125. Since we can use addition, subtraction, multiplication, a...
[ false, false, false, false ]
[ "", "", "", "" ]
{ "api_url": "http://10.32.37.22:9080/v1", "backend": "litellm", "chat_template_applied": true, "generation_params": { "chat_template_applied": true, "max_tokens": 16384, "n": 1, "repetition_penalty": 1.1, "temperature": 0.7, "top_k": 20, "top_p": 0.8 }, "model_name": "hosted_vll...
{ "backend": "litellm", "model_name": "hosted_vllm/SkillFactory/M-1119_newmodels__qwen7b_sft10k_otdata-rl@checkpoint-step-150", "n_responses": 4 }
[ true, true, true, true ]
[ "(96 + 97) - 68 = 125", "96 + 97 - 68 = 125", "(97 - 68) + 96 = 125", "96 + 97 - 68" ]
[{"extraction_type": "final", "total_spans_found": 29, "non_overlapping_spans": 29, "span_start": 15154, "span_end": 15174, "original_span": "(96 + 97) - 68 = 125"}, {"extraction_type": "final", "total_spans_found": 4, "non_overlapping_spans": 4, "span_start": 17601, "span_end": 17621, "original_span": "96 + 97 - 68 = ...
[{"is_correct": true, "error": null, "answer_block": "(96 + 97) - 68 = 125", "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 = 125", "final_answer": 125.0}, {"is_correct": true, ...
[ [ false, false, true, true, true, true, true, true, true, true, true, true, true, true, true, true, true, true, true, true, true, true, true, true, true, true, true, true, true ], [ false, ...
[ [ "(1 + 2) / 3", "Step 1: 1 + 2 = 3\nStep 2: 3 / 3 = 1", "(96 + 97) - 68", "(96 + 97) - 68 = 125", "96 + 97 - 68 = 125", "96 + 97 - 68 = 125", "96 + 97 - 68 = 125", "(96 + 97) - 68 = 125", "96 + 97 - 68 = 125", "96 + 97 - 68 = 125", "(96 + 97) - 68 = 125", "96 + 97 - ...
[[{"pattern_used": "answer tag", "confidence": 1.0, "position": 3901, "span_text": "(1 + 2) / 3", "extraction_type": "internal", "span_start": 3901, "span_end": 3914, "original_span": "(1 + 2) / 3"}, {"pattern_used": "answer tag", "confidence": 1.0, "position": 3937, "span_text": "Step 1: 1 + 2 = 3\nStep 2: 3 / 3 = 1",...
[[{"is_correct": false, "error": "Expression does not equal stated result", "answer_block": "(1 + 2) / 3", "final_answer": 125.0}, {"is_correct": false, "error": "Line uses unavailable numbers: Step 1: 1 + 2 = 3", "answer_block": "Step 1: 1 + 2 = 3\nStep 2: 3 / 3 = 1", "final_answer": 3.0}, {"is_correct": true, "error"...
{ "flips_by": [ 0, 0, 0, 1 ], "flips_total": 1, "num_correct": 4, "pass_at_n": 1, "percent_correct": 1, "total_responses": 4 }
2025-12-01
test
main
SkillFactory/M-1119_newmodels__qwen7b_sft10k_otdata-rl@checkpoint-step-150
0
eval_rl
1
2025-12-01T00:33:11.981660
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3arg_OT_ot_10k-RL-eval_rl
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
46 + 80 - 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\\\": 5001, \\\"number(...TRUNCATED)
test
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 5001, \"numbers\": [21, 80, 46], \"target\": (...TRUNCATED)
null
null
null
null
null
null
["<think>\nOkay, so I need to use the numbers 21, 80, and 46 to make an equation that equals 105. Ea(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.37.22:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED)
{"backend":"litellm","model_name":"hosted_vllm/SkillFactory/M-1119_newmodels__qwen7b_sft10k_otdata-r(...TRUNCATED)
[ false, true, true, true ]
[ "(your answer)", "(80 + 46) - 21", "80 - 21 + 46 = 105", "(80 + 46) - 21 = 105" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 11, \"non_overlapping_spans\": 11, \"span_(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"(your an(...TRUNCATED)
[[false,false,false,false,false,false,false,false,false,false,false],[true],[false,false,false,false(...TRUNCATED)
[["Step 1: 1 + 2 = 3\nStep 2: 3 / 3 = 1","(your answer)","Step 1: 1 + 2 = 3\nStep 2: 3 / 3 = 1","(yo(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 6757, \"span_text\": \"Step(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Line uses unavailable numbers: Step 1: 1 + 2 = 3\", \"answer(...TRUNCATED)
{"flips_by":[0,0,7,10],"flips_total":17,"num_correct":3,"pass_at_n":1,"percent_correct":0.75,"total_(...TRUNCATED)
2025-12-01
test
main
SkillFactory/M-1119_newmodels__qwen7b_sft10k_otdata-rl@checkpoint-step-150
0
eval_rl
1
2025-12-01T00:33:11.981675
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3arg_OT_ot_10k-RL-eval_rl
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
6*96 - 76
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\\\": 5002, \\\"number(...TRUNCATED)
test
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 5002, \"numbers\": [6, 76, 96], \"target\": 5(...TRUNCATED)
null
null
null
null
null
null
["<think>\nOkay, so I need to use the numbers 6, 76, and 96 to make 500 using basic arithmetic opera(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.37.22:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED)
{"backend":"litellm","model_name":"hosted_vllm/SkillFactory/M-1119_newmodels__qwen7b_sft10k_otdata-r(...TRUNCATED)
[ false, false, false, false ]
["None of the combinations yield exactly 500. The closest is 556.","None of the above","96 \\times 6(...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\": \"None of (...TRUNCATED)
[[false],[false,false,false,false,false,false,false,false,false,false,false,false,false,false,false,(...TRUNCATED)
[["None of the combinations yield exactly 500. The closest is 556."],["76 \\times 6 + 96 = 552","76 (...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 16417, \"span_text\": \"Non(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"None of(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"total_res(...TRUNCATED)
2025-12-01
test
main
SkillFactory/M-1119_newmodels__qwen7b_sft10k_otdata-rl@checkpoint-step-150
0
eval_rl
1
2025-12-01T00:33:11.981678
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3arg_OT_ot_10k-RL-eval_rl
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
42*(12 + 3)
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\\\": 5003, \\\"number(...TRUNCATED)
test
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 5003, \"numbers\": [42, 12, 3], \"target\": 6(...TRUNCATED)
null
null
null
null
null
null
["<think>\nOkay, so I need to use the numbers 42, 12, and 3 exactly once with basic arithmetic opera(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.37.22:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED)
{"backend":"litellm","model_name":"hosted_vllm/SkillFactory/M-1119_newmodels__qwen7b_sft10k_otdata-r(...TRUNCATED)
[ false, false, false, false ]
[ "42 \\times (12 + 3)", null, "(12 + 3) \\times 42", "42 \\times (12 + 3)" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 19, \"non_overlapping_spans\": 19, \"span_(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"42 \\\\t(...TRUNCATED)
[[false,false,false,false,false,false,false,false,false,false,false,false,false,false,false,false,fa(...TRUNCATED)
[["(your answer)","42 \\times (12 + 3)","Step 1: 12 + 3 = 15\nStep 2: 42 \\times 15 = 630","42 \\tim(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 3686, \"span_text\": \"(you(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"(your a(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"total_res(...TRUNCATED)
2025-12-01
test
main
SkillFactory/M-1119_newmodels__qwen7b_sft10k_otdata-rl@checkpoint-step-150
0
eval_rl
1
2025-12-01T00:33:11.981681
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3arg_OT_ot_10k-RL-eval_rl
"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
["<think>\nOkay, so I need to use the numbers 86, 69, and 52 to make 103 using basic arithmetic oper(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.37.22:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED)
{"backend":"litellm","model_name":"hosted_vllm/SkillFactory/M-1119_newmodels__qwen7b_sft10k_otdata-r(...TRUNCATED)
[ true, true, true, true ]
[ "(86 + 69) - 52", "(86 + 69) - 52", "(86 + 69) - 52", "(86 + 69) - 52" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 14, \"non_overlapping_spans\": 14, \"span_(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"(86 + 69) - 52\", \"final_answer\": 10(...TRUNCATED)
[[false,false,false,false,false,false,false,false,false,true,true,true,true,true],[true,true],[false(...TRUNCATED)
[["...","Step 1: 1 + 2 = 3\nStep 2: 3 / 3 = 1","(1 + 2) / 3","(your answer)","(your answer)","Step 1(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 2581, \"span_text\": \"...\(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"...\", (...TRUNCATED)
{"flips_by":[0,0,1,0],"flips_total":1,"num_correct":4,"pass_at_n":1,"percent_correct":1.0,"total_res(...TRUNCATED)
2025-12-01
test
main
SkillFactory/M-1119_newmodels__qwen7b_sft10k_otdata-rl@checkpoint-step-150
0
eval_rl
1
2025-12-01T00:33:11.981683
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3arg_OT_ot_10k-RL-eval_rl
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
63*7 - 87
countdown_3arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 5006, \\\"number(...TRUNCATED)
test
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 5006, \"numbers\": [63, 7, 87], \"target\": 3(...TRUNCATED)
null
null
null
null
null
null
["<think>\nOkay, so I need to use the numbers 63, 7, and 87 to make an equation that equals 354. Eac(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.37.22:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED)
{"backend":"litellm","model_name":"hosted_vllm/SkillFactory/M-1119_newmodels__qwen7b_sft10k_otdata-r(...TRUNCATED)
[ false, false, false, false ]
[ "63 \\times 7 - 87", "(63 \\times 7) - 87 = 354", "None", "87 \\times 4 + 6" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"63 \\\\t(...TRUNCATED)
[[false],[false,false,false,false,false,false,false,false,false,false,false,false,false,false,false,(...TRUNCATED)
[["63 \\times 7 - 87"],["Step 1: 1 + 2 = 3\n\nStep 2: 3 / 3 = 1","(1 + 2) / 3","(your answer)","Step(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 13849, \"span_text\": \"63 (...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"63 \\\\(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"total_res(...TRUNCATED)
2025-12-01
test
main
SkillFactory/M-1119_newmodels__qwen7b_sft10k_otdata-rl@checkpoint-step-150
0
eval_rl
1
2025-12-01T00:33:11.981685
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3arg_OT_ot_10k-RL-eval_rl
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
19*8 - 50
countdown_3arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 5007, \\\"number(...TRUNCATED)
test
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 5007, \"numbers\": [8, 50, 19], \"target\": 1(...TRUNCATED)
null
null
null
null
null
null
["<think>\nOkay, so I need to use the numbers 8, 50, and 19 to make an equation that equals 102. Eac(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.37.22:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED)
{"backend":"litellm","model_name":"hosted_vllm/SkillFactory/M-1119_newmodels__qwen7b_sft10k_otdata-r(...TRUNCATED)
[ false, false, false, false ]
[ "8 \\times 19 - 50 = 102", "8 \\times 19 - 50", "8 \\times 19 - 50", "19 \\times 8 - 50" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 18, \"non_overlapping_spans\": 18, \"span_(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"8 \\\\ti(...TRUNCATED)
[[false,false,false,false,false,false,false,false,false,false,false,false,false,false,false,false,fa(...TRUNCATED)
[["8 \\times 19 - 50 = 102","(your answer)","(your answer)","(your answer)","(your answer)","Step 1:(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 5261, \"span_text\": \"8 \\(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"8 \\\\t(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"total_res(...TRUNCATED)
2025-12-01
test
main
SkillFactory/M-1119_newmodels__qwen7b_sft10k_otdata-rl@checkpoint-step-150
0
eval_rl
1
2025-12-01T00:33:11.981687
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3arg_OT_ot_10k-RL-eval_rl
"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
["<think>\nOkay, so I need to use the numbers 38, 46, and 40 to make the number 124 using basic arit(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.37.22:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED)
{"backend":"litellm","model_name":"hosted_vllm/SkillFactory/M-1119_newmodels__qwen7b_sft10k_otdata-r(...TRUNCATED)
[ true, true, true, true ]
[ "38 + 46 + 40 = 124", "38 + 46 + 40 = 124", "38 + 46 + 40 = 124", "38 + 46 + 40 = 124" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"38 + 46 + 40 = 124\", \"final_answer\"(...TRUNCATED)
[[true],[true],[true,true,false,false,true,true,false,false,true,false,false,false,true,false,false,(...TRUNCATED)
[["38 + 46 + 40 = 124"],["38 + 46 + 40 = 124"],["Step 1: 38 + 46 = 84\nStep 2: 84 + 40 = 124","38 + (...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 11235, \"span_text\": \"38 (...TRUNCATED)
"[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"38 + 46 + 40 = 124\", \"final_answer\(...TRUNCATED)
{"flips_by":[0,0,11,0],"flips_total":11,"num_correct":4,"pass_at_n":1,"percent_correct":1.0,"total_r(...TRUNCATED)
2025-12-01
test
main
SkillFactory/M-1119_newmodels__qwen7b_sft10k_otdata-rl@checkpoint-step-150
0
eval_rl
1
2025-12-01T00:33:11.981692
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3arg_OT_ot_10k-RL-eval_rl
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
19 + 92 + 21
countdown_3arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 5009, \\\"number(...TRUNCATED)
test
null
null
null
null
null
null
null
null
null
null
null
null
"{\"source_dataset\": \"countdown\", \"source_index\": 5009, \"numbers\": [92, 21, 19], \"target\": (...TRUNCATED)
null
null
null
null
null
null
["<think>\nOkay, so I need to use the numbers 92, 21, and 19 to make the number 132 using basic arit(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.37.22:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED)
{"backend":"litellm","model_name":"hosted_vllm/SkillFactory/M-1119_newmodels__qwen7b_sft10k_otdata-r(...TRUNCATED)
[ true, true, true, true ]
[ "92 + 21 + 19", "92 + 21 + 19", "92 + 21 + 19 = 132", "92 + 21 + 19 = 132" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"92 + 21 + 19\", \"final_answer\": 132.(...TRUNCATED)
[[true],[true],[false,true,true,false,true,false,true,true,false,true,true,true,true,false,true,true(...TRUNCATED)
[["92 + 21 + 19"],["92 + 21 + 19"],["(your answer)","92 + 21 + 19","92 + 21 + 19 = 132","(your answe(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 5212, \"span_text\": \"92 +(...TRUNCATED)
"[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"92 + 21 + 19\", \"final_answer\": 132(...TRUNCATED)
{"flips_by":[0,0,14,0],"flips_total":14,"num_correct":4,"pass_at_n":1,"percent_correct":1.0,"total_r(...TRUNCATED)
2025-12-01
test
main
SkillFactory/M-1119_newmodels__qwen7b_sft10k_otdata-rl@checkpoint-step-150
0
eval_rl
1
2025-12-01T00:33:11.981695
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3arg_OT_ot_10k-RL-eval_rl
"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
["<think>\nOkay, so I need to use the numbers 23, 21, and 7 to make 322 using basic arithmetic opera(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.37.22:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED)
{"backend":"litellm","model_name":"hosted_vllm/SkillFactory/M-1119_newmodels__qwen7b_sft10k_otdata-r(...TRUNCATED)
[ false, false, false, false ]
["None of the combinations of 23, 21, and 7 using basic arithmetic operations result in 322.",null,"(...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 57, \"non_overlapping_spans\": 57, \"span_(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"None of (...TRUNCATED)
[[false,false,false,false,false,false,false,false,false,false,false,false,false,false,false,false,fa(...TRUNCATED)
[["\\text{None of the combinations of 23, 21, and 7 using basic arithmetic operations result in 322.(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 15709, \"span_text\": \"\\\(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"\\\\tex(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"total_res(...TRUNCATED)
2025-12-01
test
main
SkillFactory/M-1119_newmodels__qwen7b_sft10k_otdata-rl@checkpoint-step-150
0
eval_rl
1
2025-12-01T00:33:11.981697
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3arg_OT_ot_10k-RL-eval_rl
End of preview. Expand in Data Studio

Experiment Tracker: FinEval_16k_fulleval_3arg_OT_ot_10k-RL

Experiment Description: Simple test experiment for Skill Factory workflows.

Start Time: 2025-12-01T00:13:03.196721

Tracker Dataset: TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3arg_OT_ot_10k-RL__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_3arg_OT_ot_10k-RL__v1', 'experiment_metadata')

# Load complete training datasets
sft_data = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3arg_OT_ot_10k-RL__v1', 'training_data__sft')
sft_metadata = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3arg_OT_ot_10k-RL__v1', 'training_data__sft_metadata')

# Load complete configurations
sft_hyperparams = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3arg_OT_ot_10k-RL__v1', 'hyperparameters__sft')
rl_hyperparams = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3arg_OT_ot_10k-RL__v1', 'hyperparameters__rl')

# Load stage-specific logs
sft_logs = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3arg_OT_ot_10k-RL__v1', 'logs__sft')
rl_logs = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3arg_OT_ot_10k-RL__v1', 'logs__rl')

# Load evaluation results with annotations
sft_eval_results = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3arg_OT_ot_10k-RL__v1', 'evals_eval_sft')
rl_eval_results = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3arg_OT_ot_10k-RL__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_3arg_OT_ot_10k-RL - {stage_name} - {SFT/RL}


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

Downloads last month
4