{"dataset_revision":"8d51e7e4887a4caaa95b3fbebbf53c0490b58bbb","device":"cuda:0","evaluator_source":true,"evidence":"CodeSOTA execution on White","finished":1792193133,"id":"2baa9449b32fde6f476f7e1f","measured_cost_usd":null,"metric":"accuracy","model":"Qwen/Qwen2.5-0.5B","model_revision":"060db6499f32faf8b98477b0a26969ef7d8b9987","n":32,"notes":"Pilot subset, custom CodeSOTA protocol. Not an official full-benchmark score.","peak_gpu_bytes":1021347840,"profile":"pilot-32","protocol":{"adapter":"sentiment","area":"Language","benchmark":"SST-2","contract":"Movie review \u2192 positive / negative","dataset":"stanfordnlp/sst2","dataset_config":null,"dataset_revision":"8d51e7e4887a4caaa95b3fbebbf53c0490b58bbb","dataset_url":"https://huggingface.co/datasets/stanfordnlp/sst2","direction":"max","id":"sentiment","license":["unknown"],"limit":32,"metric":"accuracy","models":[{"id":"Qwen/Qwen2.5-0.5B","revision":"060db6499f32faf8b98477b0a26969ef7d8b9987"},{"id":"Qwen/Qwen2.5-1.5B","revision":"8faed761d45a263340a0528343f099c05c9a4323"}],"name":"Sentiment classification","protocol_version":"codesota-pilot-v1","source":"https://nlp.stanford.edu/sentiment/","split":"validation"},"runner_sha256":"a71a6c0fe0c3cc3f1694659595be1112cfc36eb190be5ff6e0a3380105415b3e","scope":"e1843d5c329a05094d05157b826e49ecaf8d2d146c41eb15d1287a350638c5b0","score":0.9375,"seconds":1.55905277794227,"seed":42,"selection":"first 32 valid examples in pinned split order","status":"completed","task":"sentiment"}