Dataset Viewer
Auto-converted to Parquet Duplicate
question
stringlengths
977
981
answer
stringlengths
8
18
task_config
stringclasses
1 value
task_source
stringclasses
1 value
prompt
listlengths
1
1
model_responses
listlengths
0
0
model_responses__eval_is_correct
listlengths
0
0
all_other_columns
stringlengths
177
192
original_split
stringclasses
1 value
metadata
stringlengths
119
134
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
994
model_responses__best_of_n_atags__eval_evaluation_metadata
stringlengths
370
1.15k
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
211
12.9k
model_responses__best_of_n_atags__internal_answers__eval_evaluation_metadata
stringlengths
111
8.16k
model_responses__best_of_n_atags__metrics
dict
eval_date
stringdate
2025-10-27 00:00:00
2025-10-27 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
2025-10-27 00:40:38
2025-10-27 00:40:38
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 [56, 22, 98, 71], create an equation that equals 853. You can use basic arithmetic operations (+, -, *, /) and each number c...
22*(98 - 56) - 71
countdown_4arg
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 [56, 22, 98, 71], create an equation that equals 853. You can use basic arithmetic operations (+, -...
[]
[]
{"metadata": "{\"source_dataset\": \"countdown\", \"source_index\": 251, \"numbers\": [56, 22, 98, 71], \"target\": 853, \"expression\": \"22*(98 - 56) - 71\"}", "task_source": "countdown"}
test
{"source_dataset": "countdown", "source_index": 251, "numbers": [56, 22, 98, 71], "target": 853, "expression": "22*(98 - 56) - 71"}
[ "<think>\nI have the numbers [56, 22, 98, 71] and need to make 853 using basic arithmetic operations: addition, subtraction, multiplication, and division. Each number can be used only once.\n\nFirst, I should consider what operations might get me close to 853. Since 853 is a fairly large number, multiplication migh...
[ false, false, false, false ]
[ "", "", "", "" ]
{ "api_url": "http://10.32.37.28:9080/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/TAUR-dev/M-R1_distilled_baseline_cd3args_only", "n_responses": 4 }
[ false, false, false, false ]
[ null, null, null, null ]
[{"extraction_type": "final"}, {"extraction_type": "final"}, {"extraction_type": "final"}, {"extraction_type": "final"}]
[{"evaluation_method": "response_processor", "reason": "no_extracted_answer", "extraction_result": "{'extraction_type': 'final'}"}, {"evaluation_method": "response_processor", "reason": "no_extracted_answer", "extraction_result": "{'extraction_type': 'final'}"}, {"evaluation_method": "response_processor", "reason": "no...
null
null
null
null
{ "flips_by": null, "flips_total": null, "num_correct": 0, "pass_at_n": 0, "percent_correct": 0, "skill_count": { "answer_revision": [ 0, 0, 0, 0 ], "best_of_n": [ 0, 0, 0, 0 ], "reflect_close": [ 0, 0, 0, 0 ], ...
2025-10-27
test
main
TAUR-dev/M-R1_distilled_baseline_cd3args_only
0
eval_0
1
2025-10-27T00:40:38.230954
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_4arg-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
58 + 68 + 98 - 26
countdown_4arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 252, \\\"numbers(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 252, \"numbers\": [98, 58, 68, 26], \"target\(...TRUNCATED)
["<think>\nFirst, I have the numbers: 98, 58, 68, and 26. I need to use each exactly once with basic(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.37.28:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED)
{"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only","n_res(...TRUNCATED)
[ true, false, true, false ]
[ "98 + 58 + 68 - 26", null, "((98 + 58) + 68) - 26 = 198", null ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non_overlapping_spans\": 2, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"98 + 58 + 68 - 26\", \"final_answer\":(...TRUNCATED)
[ [ true, true ], [], [ true ], [] ]
[ [ "98 + 58 + 68 - 26 = 198", "98 + 58 + 68 - 26" ], [], [ "((98 + 58) + 68) - 26 = 198" ], [] ]
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 5895, \"span_text\": \"98 +(...TRUNCATED)
"[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"98 + 58 + 68 - 26 = 198\", \"final_an(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":2,"pass_at_n":1,"percent_correct":0.5,"skill_cou(...TRUNCATED)
2025-10-27
test
main
TAUR-dev/M-R1_distilled_baseline_cd3args_only
0
eval_0
1
2025-10-27T00:40:38.230966
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_4arg-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
27*29 - 96 - 39
countdown_4arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 253, \\\"numbers(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 253, \"numbers\": [96, 27, 29, 39], \"target\(...TRUNCATED)
["<think>\nI have the numbers [96, 27, 29, 39] and I need to make an equation that equals 648 using (...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.37.28:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED)
{"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only","n_res(...TRUNCATED)
[ false, false, false, false ]
[ null, null, null, null ]
"[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\(...TRUNCATED)
"[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED)
null
null
null
null
{"flips_by":null,"flips_total":null,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_count(...TRUNCATED)
2025-10-27
test
main
TAUR-dev/M-R1_distilled_baseline_cd3args_only
0
eval_0
1
2025-10-27T00:40:38.230968
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_4arg-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
33 + 48 - 65 + 87
countdown_4arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 254, \\\"numbers(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 254, \"numbers\": [65, 87, 48, 33], \"target\(...TRUNCATED)
["<think>\nI have the numbers [65, 87, 48, 33] and I need to make an equation that equals 103 using (...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.37.28:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED)
{"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only","n_res(...TRUNCATED)
[ false, false, false, false ]
[ null, "(your answer)", "(87 + 48) - 33", null ]
"[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non(...TRUNCATED)
"[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED)
[ [], [ false, false ], [ false, false ], [] ]
[ [], [ "(1 + 2) / 3", "(your answer)" ], [ "(your answer)", "(87 + 48) - 33" ], [] ]
"[[], [{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 9250, \"span_text\": \"(...TRUNCATED)
"[[], [{\"is_correct\": false, \"error\": \"Expression does not equal stated result\", \"answer_bloc(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED)
2025-10-27
test
main
TAUR-dev/M-R1_distilled_baseline_cd3args_only
0
eval_0
1
2025-10-27T00:40:38.230970
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_4arg-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
17 - 38 + 82 + 39
countdown_4arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 255, \\\"numbers(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 255, \"numbers\": [17, 39, 38, 82], \"target\(...TRUNCATED)
["<think>\nI have the numbers [17, 39, 38, 82] and need to make 100 using basic arithmetic operation(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.37.28:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED)
{"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only","n_res(...TRUNCATED)
[ false, false, false, false ]
[ "Step 1: 82 - 39 = 43 \nStep 2: 43 * (38 / 17) = 100", null, "(17 + 39) - 38 = 100", null ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 4, \"non_overlapping_spans\": 4, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"error\": \"Incorrect arithmetic in line: Step 2: 43 * (38 / 17) = 100\",(...TRUNCATED)
[ [ false, false, false, false ], [], [ false, false ], [] ]
[["Step 1: 82 - 39 = 43\nStep 2: 43 * (38 / 17) = 100","Step 1: 82 - 39 = 43 \nStep 2: 43 * (38 / 1(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 5598, \"span_text\": \"Step(...TRUNCATED)
"[[{\"is_correct\": false, \"error\": \"Incorrect arithmetic in line: Step 2: 43 * (38 / 17) = 100\"(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":0,"pass_at_n":0,"percent_correct":0.0,"skill_cou(...TRUNCATED)
2025-10-27
test
main
TAUR-dev/M-R1_distilled_baseline_cd3args_only
0
eval_0
1
2025-10-27T00:40:38.230971
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_4arg-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
93 + 99 + 42 + 20
countdown_4arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 256, \\\"numbers(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 256, \"numbers\": [42, 20, 99, 93], \"target\(...TRUNCATED)
["<think>\nI have the numbers [42, 20, 99, 93] and I need to make an equation that equals 254 using (...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.37.28:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED)
{"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only","n_res(...TRUNCATED)
[ true, true, false, false ]
["42 + 20 + 99 + 93","42 + 20 + 99 + 93 = 254","Step 1: 42 * 93 = 3906\nStep 2: 3906 - 3652 = 254",n(...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"42 + 20 + 99 + 93\", \"final_answer\":(...TRUNCATED)
[ [ true ], [ true ], [ false, false ], [] ]
[["42 + 20 + 99 + 93"],["42 + 20 + 99 + 93 = 254"],["(your answer)","Step 1: 42 * 93 = 3906\nStep 2:(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 12455, \"span_text\": \"42 (...TRUNCATED)
"[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"42 + 20 + 99 + 93\", \"final_answer\"(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":2,"pass_at_n":1,"percent_correct":0.5,"skill_cou(...TRUNCATED)
2025-10-27
test
main
TAUR-dev/M-R1_distilled_baseline_cd3args_only
0
eval_0
1
2025-10-27T00:40:38.230973
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_4arg-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
76*25/2 + 2
countdown_4arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 257, \\\"numbers(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 257, \"numbers\": [2, 2, 25, 76], \"target\":(...TRUNCATED)
["<think>\nI have the numbers [2, 2, 25, 76] and need to make an equation that equals 952 using basi(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.37.28:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED)
{"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only","n_res(...TRUNCATED)
[ false, false, false, true ]
[ null, null, null, "Step 1: 76 * 25 = 1900 \nStep 2: 1900 / 2 = 950 \nStep 3: 950 + 2 = 952" ]
"[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\(...TRUNCATED)
"[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED)
[ [], [], [], [ true, false, true ] ]
[[],[],[],["Step 1: 76 * 25 = 1900\nStep 2: 1900 / 2 = 950\nStep 3: 950 + 2 = 952","(your answer)","(...TRUNCATED)
"[[], [], [], [{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 5901, \"span_te(...TRUNCATED)
"[[], [], [], [{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 76 * 25 = 1900\\n(...TRUNCATED)
{"flips_by":[0,0,0,1],"flips_total":1,"num_correct":1,"pass_at_n":1,"percent_correct":0.25,"skill_co(...TRUNCATED)
2025-10-27
test
main
TAUR-dev/M-R1_distilled_baseline_cd3args_only
0
eval_0
1
2025-10-27T00:40:38.230975
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_4arg-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
26 + 87 + 25 + 97
countdown_4arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 258, \\\"numbers(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 258, \"numbers\": [87, 25, 97, 26], \"target\(...TRUNCATED)
["<think>\nI have the numbers [87, 25, 97, 26] and need to make 235 using them with addition, subtra(...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.37.28:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED)
{"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only","n_res(...TRUNCATED)
[ false, false, true, true ]
[null,"87 + 25 + 97 = 235","(87 + 97) + 25 + 26","Step 1: 87 + 25 = 112 \nStep 2: 112 + 97 = 209 \(...TRUNCATED)
"[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non(...TRUNCATED)
"[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED)
[ [], [ false, false ], [ true ], [ true ] ]
[[],["(your answer)","87 + 25 + 97 = 235"],["(87 + 97) + 25 + 26"],["Step 1: 87 + 25 = 112 \nStep 2(...TRUNCATED)
"[[], [{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 4866, \"span_text\": \"(...TRUNCATED)
"[[], [{\"is_correct\": false, \"error\": \"Could not evaluate expression\", \"answer_block\": \"(yo(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":2,"pass_at_n":1,"percent_correct":0.5,"skill_cou(...TRUNCATED)
2025-10-27
test
main
TAUR-dev/M-R1_distilled_baseline_cd3args_only
0
eval_0
1
2025-10-27T00:40:38.230976
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_4arg-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
10*58 - 37 + 25
countdown_4arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 259, \\\"numbers(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 259, \"numbers\": [58, 25, 10, 37], \"target\(...TRUNCATED)
["<think>\nI have the numbers [58, 25, 10, 37] and I need to make an equation that equals 568 using (...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.37.28:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED)
{"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only","n_res(...TRUNCATED)
[ false, true, false, false ]
[null,"Step 1: 58 * 10 = 580 \nStep 2: 580 + 25 = 605 \nStep 3: 605 - 37 = 568",null,"There is no (...TRUNCATED)
"[{\"extraction_type\": \"final\"}, {\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non(...TRUNCATED)
"[{\"evaluation_method\": \"response_processor\", \"reason\": \"no_extracted_answer\", \"extraction_(...TRUNCATED)
[ [], [ true, true ], [], [ false ] ]
[[],["Step 1: 58 * 10 = 580 \nStep 2: 580 + 25 = 605 \nStep 3: 605 - 37 = 568","Step 1: 58 * 10 = (...TRUNCATED)
"[[], [{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 4709, \"span_text\": \"(...TRUNCATED)
"[[], [{\"is_correct\": true, \"error\": null, \"answer_block\": \"Step 1: 58 * 10 = 580 \\nStep 2:(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":1,"pass_at_n":1,"percent_correct":0.25,"skill_co(...TRUNCATED)
2025-10-27
test
main
TAUR-dev/M-R1_distilled_baseline_cd3args_only
0
eval_0
1
2025-10-27T00:40:38.230978
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_4arg-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
61 + 75 + 12 - 33
countdown_4arg
countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"metadata\": \"{\\\"source_dataset\\\": \\\"countdown\\\", \\\"source_index\\\": 261, \\\"numbers(...TRUNCATED)
test
"{\"source_dataset\": \"countdown\", \"source_index\": 261, \"numbers\": [61, 12, 33, 75], \"target\(...TRUNCATED)
["<think>\nI have the numbers [61, 12, 33, 75] and I need to make an equation that equals 115 using (...TRUNCATED)
[ false, false, false, false ]
[ "", "", "", "" ]
{"api_url":"http://10.32.37.28:9080/v1","backend":"litellm","chat_template_applied":true,"generation(...TRUNCATED)
{"backend":"litellm","model_name":"hosted_vllm/TAUR-dev/M-R1_distilled_baseline_cd3args_only","n_res(...TRUNCATED)
[ true, true, false, false ]
["(61 + 12) + (75 - 33) = 115","(75 + 61) - (33 - 12)","(75 - 12) * (61 + 115/115)","(75 - 33) + 61"(...TRUNCATED)
"[{\"extraction_type\": \"final\", \"total_spans_found\": 1, \"non_overlapping_spans\": 1, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"error\": null, \"answer_block\": \"(61 + 12) + (75 - 33) = 115\", \"final(...TRUNCATED)
[ [ true ], [ false, true ], [ false ], [ false ] ]
[["(61 + 12) + (75 - 33) = 115"],["(your answer)","(75 + 61) - (33 - 12)"],["(75 - 12) * (61 + 115/1(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 27547, \"span_text\": \"(61(...TRUNCATED)
"[[{\"is_correct\": true, \"error\": null, \"answer_block\": \"(61 + 12) + (75 - 33) = 115\", \"fina(...TRUNCATED)
{"flips_by":[0,0,0,0],"flips_total":0,"num_correct":2,"pass_at_n":1,"percent_correct":0.5,"skill_cou(...TRUNCATED)
2025-10-27
test
main
TAUR-dev/M-R1_distilled_baseline_cd3args_only
0
eval_0
1
2025-10-27T00:40:38.230980
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-countdown_4arg-eval_0
End of preview. Expand in Data Studio

Experiment Tracker: FinEval_16k_fulleval_3args_r1-countdown_4arg

Experiment Description: Evaluation experiment for task countdown_4arg from FinEval_16k_fulleval_3args_r1

Start Time: 2025-10-26T21:39:04.570176

Tracker Dataset: TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_4arg__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_3args_r1-countdown_4arg__v1', 'experiment_metadata')

# Load complete training datasets
sft_data = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_4arg__v1', 'training_data__sft')
sft_metadata = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_4arg__v1', 'training_data__sft_metadata')

# Load complete configurations
sft_hyperparams = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_4arg__v1', 'hyperparameters__sft')
rl_hyperparams = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_4arg__v1', 'hyperparameters__rl')

# Load stage-specific logs
sft_logs = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_4arg__v1', 'logs__sft')
rl_logs = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_4arg__v1', 'logs__rl')

# Load evaluation results with annotations
sft_eval_results = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_4arg__v1', 'evals_eval_sft')
rl_eval_results = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-countdown_4arg__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_3args_r1-countdown_4arg - {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