Dataset Viewer
Auto-converted to Parquet Duplicate
question
string
answer
string
task_config
string
task_source
string
prompt
list
model_responses
list
model_responses__eval_is_correct
list
all_other_columns
string
original_split
string
length
int64
letters
string
source
string
model_responses__best_of_n_atags
list
model_responses__best_of_n_atags__finish_reason_length_flags
list
model_responses__best_of_n_atags__length_partial_responses
list
prompt__best_of_n_atags__metadata
dict
model_responses__best_of_n_atags__metadata
dict
model_responses__best_of_n_atags__eval_is_correct
list
model_responses__best_of_n_atags__eval_extracted_answers
list
model_responses__best_of_n_atags__eval_extraction_metadata
string
model_responses__best_of_n_atags__eval_evaluation_metadata
string
model_responses__best_of_n_atags__internal_answers__eval_is_correct
list
model_responses__best_of_n_atags__internal_answers__eval_extracted_answers
list
model_responses__best_of_n_atags__internal_answers__eval_extraction_metadata
string
model_responses__best_of_n_atags__internal_answers__eval_evaluation_metadata
string
model_responses__best_of_n_atags__metrics
dict
eval_date
string
split
string
revision_name
string
model_path
string
checkpoint_step
int64
stage_name
string
stage_number
int64
timestamp
string
eval_repo_id
string
Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer> (your answer) </answer>. ### Problem Given a list of letters, rearrange the letters to create a valid English word. You should satisfy the following conditions: 1) Only use the lette...
letter_countdown_5o
letter_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\n\n\nGiven a list of letters, rearrange the letters to create a valid English word. You should satisfy the following conditi...
[]
[]
{"letters": "tansd", "source": "stand", "length": 5, "task_config": "letter_countdown_5o", "task_source": "letter_countdown"}
test
5
tansd
stand
[ "<think>\nFirst, I need to analyze the given input letters: ['t', 'a', 'n', 's', 'd']. These are all single-letter strings.\n\nThe task is to use these letters to form a valid English word that meets certain criteria:\n\n1. Only use the letters from the input.\n2. Create a word with at least 5 characters.\n3. Give ...
[ 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 ]
[ "(your answer)", "tands", "tandas", "tands" ]
[{"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 4494, "span_end": 4509, "original_span": "(your answer)"}, {"extraction_type": "final", "total_spans_found": 4, "non_overlapping_spans": 4, "span_start": 6909, "span_end": 6916, "original_span": "tands"}, {"extraction_type":...
[{"is_correct": false, "final_answer": "youranswer", "errors": "not_a_valid_word, length_constraint_violated, cannot_be_formed_from_letters", "length": 10}, {"is_correct": false, "final_answer": "tands", "errors": "not_a_valid_word", "length": 5}, {"is_correct": false, "final_answer": "tandas", "errors": "not_a_valid_w...
[ [ false ], [ false, false, false, false ], [ false, false, false ], [ false, false, false, false, false, false, false, false ] ]
[ [ "(your answer)" ], [ "(your answer)", "faster", "tands", "tands" ], [ "tandas", "(your answer)", "tandas" ], [ "tands", "faster", "tands", "(your answer)", "tands", "(your answer)", "tands", "tands" ] ]
[[{"pattern_used": "answer tag", "confidence": 1.0, "position": 4494, "span_text": "(your answer)", "extraction_type": "internal", "span_start": 4494, "span_end": 4509, "original_span": "(your answer)"}], [{"pattern_used": "answer tag", "confidence": 1.0, "position": 4226, "span_text": "(your answer)", "extraction_type...
[[{"is_correct": false, "final_answer": "youranswer", "errors": "not_a_valid_word, length_constraint_violated, cannot_be_formed_from_letters", "length": 10}], [{"is_correct": false, "final_answer": "youranswer", "errors": "not_a_valid_word, length_constraint_violated, cannot_be_formed_from_letters", "length": 10}, {"is...
{ "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, ...
2025-10-27
test
main
TAUR-dev/M-R1_distilled_baseline_cd3args_only
0
eval_0
1
2025-10-27T12:28:15.067524
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-letter_countdown_5o-eval_0
Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer> (your answer) </answer>. ### Problem Given a list of letters, rearrange the letters to create a valid English word. You should satisfy the following conditions: 1) Only use the lette...
letter_countdown_5o
letter_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\n\n\nGiven a list of letters, rearrange the letters to create a valid English word. You should satisfy the following conditi...
[]
[]
{"letters": "ftusf", "source": "stuff", "length": 5, "task_config": "letter_countdown_5o", "task_source": "letter_countdown"}
test
5
ftusf
stuff
[ "<think>\nFirst, I have the list of letters: ['f', 't', 'u', 's', 'f'].\n\nI need to form a valid English word using only these letters, without adding any extra ones from elsewhere. Each letter can only be used once.\n\nThe condition says that the word must be at least 5 characters long. So I need to find a combin...
[ 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 ]
[ "fsut", "faster", "ufsf", "faster" ]
[{"extraction_type": "final", "total_spans_found": 1, "non_overlapping_spans": 1, "span_start": 7589, "span_end": 7595, "original_span": "fsut"}, {"extraction_type": "final", "total_spans_found": 5, "non_overlapping_spans": 5, "span_start": 6482, "span_end": 6490, "original_span": "faster"}, {"extraction_type": "final"...
[{"is_correct": false, "final_answer": "fsut", "errors": "not_a_valid_word, length_constraint_violated", "length": 4}, {"is_correct": false, "final_answer": "faster", "errors": "length_constraint_violated, cannot_be_formed_from_letters", "length": 6}, {"is_correct": false, "final_answer": "ufsf", "errors": "not_a_valid...
[ [ false ], [ false, false, false, false, false ], [ false, false, false, false ], [ false, false, false, false, false ] ]
[ [ "fsut" ], [ "faster", "faster", "faster", "faster", "faster" ], [ "faster", "(your answer)", "(your answer)", "ufsf" ], [ "faster", "fustes", "(your answer)", "fustes", "faster" ] ]
[[{"pattern_used": "answer tag", "confidence": 1.0, "position": 7589, "span_text": "fsut", "extraction_type": "internal", "span_start": 7589, "span_end": 7595, "original_span": "fsut"}], [{"pattern_used": "answer tag", "confidence": 1.0, "position": 3189, "span_text": "faster", "extraction_type": "internal", "span_star...
[[{"is_correct": false, "final_answer": "fsut", "errors": "not_a_valid_word, length_constraint_violated", "length": 4}], [{"is_correct": false, "final_answer": "faster", "errors": "length_constraint_violated, cannot_be_formed_from_letters", "length": 6}, {"is_correct": false, "final_answer": "faster", "errors": "length...
{ "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, ...
2025-10-27
test
main
TAUR-dev/M-R1_distilled_baseline_cd3args_only
0
eval_0
1
2025-10-27T12:28:15.067533
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-letter_countdown_5o-eval_0
Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer> (your answer) </answer>. ### Problem Given a list of letters, rearrange the letters to create a valid English word. You should satisfy the following conditions: 1) Only use the lette...
letter_countdown_5o
letter_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\n\n\nGiven a list of letters, rearrange the letters to create a valid English word. You should satisfy the following conditi...
[]
[]
{"letters": "daidv", "source": "david", "length": 5, "task_config": "letter_countdown_5o", "task_source": "letter_countdown"}
test
5
daidv
david
[ "<think>\nFirst, I need to analyze the given list of letters: ['d', 'a', 'i', 'd', 'v']. I have to form a valid English word using only these letters, without adding any extra ones.\n\nThe conditions are:\n\n1. Use only the letters from the input.\n2. Create exactly one word.\n3. The word must be at least 5 charact...
[ 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 }
[ true, true, true, false ]
[ "david", "david", "david", "faster" ]
[{"extraction_type": "final", "total_spans_found": 6, "non_overlapping_spans": 6, "span_start": 6275, "span_end": 6282, "original_span": "david"}, {"extraction_type": "final", "total_spans_found": 2, "non_overlapping_spans": 2, "span_start": 5761, "span_end": 5766, "original_span": "david"}, {"extraction_type": "final"...
[{"is_correct": true, "final_answer": "david", "errors": "", "length": 5}, {"is_correct": true, "final_answer": "david", "errors": "", "length": 5}, {"is_correct": true, "final_answer": "david", "errors": "", "length": 5}, {"is_correct": false, "final_answer": "faster", "errors": "length_constraint_violated, cannot_be_...
[ [ false, false, true, false, true, true ], [ false, true ], [ true, true ], [ false, false, false ] ]
[ [ "(your answer)", "faster", "david", "(your answer)", "david", "david" ], [ "...", "david" ], [ "david", "david" ], [ "(your answer)", "faster", "faster" ] ]
[[{"pattern_used": "answer tag", "confidence": 1.0, "position": 4011, "span_text": "(your answer)", "extraction_type": "internal", "span_start": 4011, "span_end": 4026, "original_span": "(your answer)"}, {"pattern_used": "answer tag", "confidence": 1.0, "position": 4077, "span_text": "faster", "extraction_type": "inter...
[[{"is_correct": false, "final_answer": "youranswer", "errors": "not_a_valid_word, length_constraint_violated, cannot_be_formed_from_letters", "length": 10}, {"is_correct": false, "final_answer": "faster", "errors": "length_constraint_violated, cannot_be_formed_from_letters", "length": 6}, {"is_correct": true, "final_a...
{ "flips_by": [ 1, 0, 0, 0 ], "flips_total": 1, "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, ...
2025-10-27
test
main
TAUR-dev/M-R1_distilled_baseline_cd3args_only
0
eval_0
1
2025-10-27T12:28:15.067535
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-letter_countdown_5o-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
letter_countdown_5o
letter_countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"letters\": \"viedr\", \"source\": \"drive\", \"length\": 5, \"task_config\": \"letter_countdown_(...TRUNCATED)
test
5
viedr
drive
["<think>\nI have a list of letters: ['v', 'i', 'e', 'd', 'r'].\n\nThe task is to use these letters (...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, false, false ]
[ "verdi", "driver", "verder", "viedr" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 4, \"non_overlapping_spans\": 4, \"span_st(...TRUNCATED)
"[{\"is_correct\": true, \"final_answer\": \"verdi\", \"errors\": \"\", \"length\": 5}, {\"is_correc(...TRUNCATED)
[ [ false, true, false, true ], [ false, false, false ], [ false, false ], [ false, false ] ]
[["faster","verdi","faster","verdi"],["(your answer)","faster","driver"],["verder","verder"],["faste(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 2581, \"span_text\": \"fast(...TRUNCATED)
"[[{\"is_correct\": false, \"final_answer\": \"faster\", \"errors\": \"length_constraint_violated, c(...TRUNCATED)
{"flips_by":[1,0,0,0],"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
2025-10-27T12:28:15.067536
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-letter_countdown_5o-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
letter_countdown_5o
letter_countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"letters\": \"enreg\", \"source\": \"green\", \"length\": 5, \"task_config\": \"letter_countdown_(...TRUNCATED)
test
5
enreg
green
["<think>\nI have a list of letters: ['e', 'n', 'r', 'e', 'g'].\n\nThe task is to use these letters (...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 ]
[ "engineer", "enregge", "father", "faster" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 4, \"non_overlapping_spans\": 4, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"final_answer\": \"engineer\", \"errors\": \"length_constraint_violated, (...TRUNCATED)
[ [ false, false, false, false ], [ false ], [ false, false, false, false, false, false ], [ false, false, false ] ]
[["<your answer>","engineeer","engineer","engineer"],["enregge"],["(your answer)","faster","(your an(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 3724, \"span_text\": \"<you(...TRUNCATED)
"[[{\"is_correct\": false, \"final_answer\": \"youranswer\", \"errors\": \"not_a_valid_word, length_(...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
2025-10-27T12:28:15.067538
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-letter_countdown_5o-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
letter_countdown_5o
letter_countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"letters\": \"chtma\", \"source\": \"match\", \"length\": 5, \"task_config\": \"letter_countdown_(...TRUNCATED)
test
5
chtma
match
["<think>\nFirst, I need to consider what letters are given and how they can form a valid English wo(...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 ]
[ "chtma", "No valid word found.", "chtha", "ham" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non_overlapping_spans\": 2, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"final_answer\": \"chtma\", \"errors\": \"not_a_valid_word\", \"length\":(...TRUNCATED)
[[false,false],[false,false,false,false,false,false],[false,false,false,false,false],[false,false,fa(...TRUNCATED)
[["faster","chtma"],["(your answer)","faster","(your answer)","(your answer)","faster","No valid wor(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 3398, \"span_text\": \"fast(...TRUNCATED)
"[[{\"is_correct\": false, \"final_answer\": \"faster\", \"errors\": \"length_constraint_violated, c(...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
2025-10-27T12:28:15.067539
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-letter_countdown_5o-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
letter_countdown_5o
letter_countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"letters\": \"demlo\", \"source\": \"model\", \"length\": 5, \"task_config\": \"letter_countdown_(...TRUNCATED)
test
5
demlo
model
["<think>\nFirst, I have the input list of letters: ['d', 'e', 'm', 'l', 'o'].\n\nI need to rearrang(...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 ]
[ "DEMLO", "demolish", "demelo", "demel" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 3, \"non_overlapping_spans\": 3, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"final_answer\": \"DEMLO\", \"errors\": \"not_a_valid_word\", \"length\":(...TRUNCATED)
[ [ false, false, false ], [ false ], [ false, false, false, false, false, false, false ], [ false, false ] ]
[["DEMLO","DEMLO","DEMLO"],["demolish"],["faster","faster","(your answer)","(your answer)","delmo","(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 5013, \"span_text\": \"DEML(...TRUNCATED)
"[[{\"is_correct\": false, \"final_answer\": \"DEMLO\", \"errors\": \"not_a_valid_word\", \"length\"(...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
2025-10-27T12:28:15.067541
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-letter_countdown_5o-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
letter_countdown_5o
letter_countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"letters\": \"rttsu\", \"source\": \"trust\", \"length\": 5, \"task_config\": \"letter_countdown_(...TRUNCATED)
test
5
rttsu
trust
["<think>\nI have a list of letters: ['r', 't', 't', 's', 'u']. I need to use these letters to make (...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 ]
[ "trut", "trtsu", "faster", "rust" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 2, \"non_overlapping_spans\": 2, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"final_answer\": \"trut\", \"errors\": \"not_a_valid_word, length_constra(...TRUNCATED)
[ [ false, false ], [ false, false ], [ false, false ], [ false, false, false, false, false, false, false ] ]
[["(your answer)","trut"],["faster","trtsu"],["(your answer)","faster"],["(your answer)","rust","rus(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 3483, \"span_text\": \"(you(...TRUNCATED)
"[[{\"is_correct\": false, \"final_answer\": \"youranswer\", \"errors\": \"not_a_valid_word, length_(...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
2025-10-27T12:28:15.067542
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-letter_countdown_5o-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
letter_countdown_5o
letter_countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"letters\": \"nraeg\", \"source\": \"range\", \"length\": 5, \"task_config\": \"letter_countdown_(...TRUNCATED)
test
5
nraeg
range
["<think>\nFirst, I need to consider what the task is asking. I have a list of letters, and I need t(...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 ]
[ "faster", "nager", "nerag", "anger" ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 3, \"non_overlapping_spans\": 3, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"final_answer\": \"faster\", \"errors\": \"length_constraint_violated, ca(...TRUNCATED)
[ [ false, false, false ], [ false, false ], [ false, false, false, false, false ], [ false, true, true ] ]
[["(your answer)","faster","faster"],["(your answer)","nager"],["(your answer)","nerag","faster","fa(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 2913, \"span_text\": \"(you(...TRUNCATED)
"[[{\"is_correct\": false, \"final_answer\": \"youranswer\", \"errors\": \"not_a_valid_word, length_(...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
2025-10-27T12:28:15.067544
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-letter_countdown_5o-eval_0
"Answer the following problem. Explain your reasoning step by step. When you are finished, give your(...TRUNCATED)
letter_countdown_5o
letter_countdown
[{"content":"Answer the following problem. Explain your reasoning step by step. When you are finishe(...TRUNCATED)
[]
[]
"{\"letters\": \"reatd\", \"source\": \"trade\", \"length\": 5, \"task_config\": \"letter_countdown_(...TRUNCATED)
test
5
reatd
trade
["<think>\nI have a list of letters: ['r', 'e', 'a', 't', 'd'].\n\nThe task is to use these letters (...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 ]
[ "read", "radar", "reata", null ]
"[{\"extraction_type\": \"final\", \"total_spans_found\": 4, \"non_overlapping_spans\": 4, \"span_st(...TRUNCATED)
"[{\"is_correct\": false, \"final_answer\": \"read\", \"errors\": \"length_constraint_violated\", \"(...TRUNCATED)
[ [ false, false, false, false ], [ false, false ], [ false, false, false, false ], [] ]
[["read","(your answer)","fast","read"],["faster","radar"],["(your answer)","reata","(your answer)",(...TRUNCATED)
"[[{\"pattern_used\": \"answer tag\", \"confidence\": 1.0, \"position\": 2835, \"span_text\": \"read(...TRUNCATED)
"[[{\"is_correct\": false, \"final_answer\": \"read\", \"errors\": \"length_constraint_violated\", \(...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
2025-10-27T12:28:15.067545
TAUR-dev/D-EVAL__standard_eval_v3__FinEval_16k_fulleval_3args_r1-letter_countdown_5o-eval_0
End of preview. Expand in Data Studio

Experiment Tracker: FinEval_16k_fulleval_3args_r1-letter_countdown_5o

Experiment Description: Evaluation experiment for task letter_countdown_5o from FinEval_16k_fulleval_3args_r1

Start Time: 2025-10-27T12:13:24.046274

Tracker Dataset: TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-letter_countdown_5o__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-letter_countdown_5o__v1', 'experiment_metadata')

# Load complete training datasets
sft_data = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-letter_countdown_5o__v1', 'training_data__sft')
sft_metadata = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-letter_countdown_5o__v1', 'training_data__sft_metadata')

# Load complete configurations
sft_hyperparams = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-letter_countdown_5o__v1', 'hyperparameters__sft')
rl_hyperparams = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-letter_countdown_5o__v1', 'hyperparameters__rl')

# Load stage-specific logs
sft_logs = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-letter_countdown_5o__v1', 'logs__sft')
rl_logs = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-letter_countdown_5o__v1', 'logs__rl')

# Load evaluation results with annotations
sft_eval_results = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-letter_countdown_5o__v1', 'evals_eval_sft')
rl_eval_results = load_dataset('TAUR-dev/D-ExpTracker__FinEval_16k_fulleval_3args_r1-letter_countdown_5o__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-letter_countdown_5o - {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