{"dataset_revision":"ab7a5ac0e35aa22088bdcf23e7fd99b220e53308","device":"cuda:0","evaluator_source":true,"evidence":"CodeSOTA execution on White","finished":1792193315,"id":"f8dd3623ae6e8786284a6ca8","measured_cost_usd":null,"metric":"spearman","model":"sentence-transformers/all-MiniLM-L6-v2","model_revision":"1110a243fdf4706b3f48f1d95db1a4f5529b4d41","n":32,"notes":"Pilot subset, custom CodeSOTA protocol. Not an official full-benchmark score.","peak_gpu_bytes":107248128,"profile":"pilot-32","protocol":{"adapter":"similarity","area":"Embeddings","benchmark":"STS Benchmark","contract":"Two sentences \u2192 semantic similarity","dataset":"sentence-transformers/stsb","dataset_config":null,"dataset_revision":"ab7a5ac0e35aa22088bdcf23e7fd99b220e53308","dataset_url":"https://huggingface.co/datasets/sentence-transformers/stsb","direction":"max","id":"similarity","license":"See upstream terms","limit":32,"metric":"spearman","models":[{"id":"sentence-transformers/all-MiniLM-L6-v2","revision":"1110a243fdf4706b3f48f1d95db1a4f5529b4d41"}],"name":"Sentence similarity","protocol_version":"codesota-pilot-v1","source":"https://ixa2.si.ehu.eus/stswiki/index.php/STSbenchmark","split":"test"},"runner_sha256":"a71a6c0fe0c3cc3f1694659595be1112cfc36eb190be5ff6e0a3380105415b3e","scope":"5048133e477a3c13bf97c614b99b2d36a458391bb2a9480cd9b38189f2608b67","score":0.9241385507168905,"seconds":0.8793051829561591,"seed":42,"selection":"first 32 valid examples in pinned split order","status":"completed","task":"similarity"}