{ "rows": { "train": 288, "validation": 144, "test": 144 }, "zero_shot_verify": { "validation": { "categorical": "89/126", "categorical_accuracy": 0.7063492063492064, "completion_found": "21/24", "false_completions": "0/48", "unknown": "1/24", "score_mae": 0.28145276563851634 }, "test": { "categorical": "85/126", "categorical_accuracy": 0.6746031746031746, "completion_found": "22/24", "false_completions": "0/48", "unknown": "0/24", "score_mae": 0.42307032748062895 } }, "candidates": [ { "l2": 0.0001, "validation_nll": 0.010317740071604856, "validation": { "categorical": "125/126", "categorical_accuracy": 0.9920634920634921, "completion_found": "24/24", "false_completions": "0/48", "unknown": "24/24", "score_mae": 0.0004602126554537731 }, "train": { "categorical": "246/246", "categorical_accuracy": 1.0, "completion_found": "48/48", "false_completions": "0/96", "unknown": "48/48", "score_mae": 4.989935418984657e-05 } }, { "l2": 0.001, "validation_nll": 0.010762290137645349, "validation": { "categorical": "125/126", "categorical_accuracy": 0.9920634920634921, "completion_found": "24/24", "false_completions": "0/48", "unknown": "24/24", "score_mae": 0.0018140511359126523 }, "train": { "categorical": "246/246", "categorical_accuracy": 1.0, "completion_found": "48/48", "false_completions": "0/96", "unknown": "48/48", "score_mae": 0.0003728628331370325 } }, { "l2": 0.01, "validation_nll": 0.012511289827795442, "validation": { "categorical": "125/126", "categorical_accuracy": 0.9920634920634921, "completion_found": "24/24", "false_completions": "0/48", "unknown": "24/24", "score_mae": 0.007914584885551698 }, "train": { "categorical": "246/246", "categorical_accuracy": 1.0, "completion_found": "48/48", "false_completions": "0/96", "unknown": "48/48", "score_mae": 0.0027551349573122588 } }, { "l2": 0.03, "validation_nll": 0.015579639968586186, "validation": { "categorical": "125/126", "categorical_accuracy": 0.9920634920634921, "completion_found": "24/24", "false_completions": "0/48", "unknown": "24/24", "score_mae": 0.015240309919228874 }, "train": { "categorical": "246/246", "categorical_accuracy": 1.0, "completion_found": "48/48", "false_completions": "0/96", "unknown": "48/48", "score_mae": 0.0068053722403096945 } }, { "l2": 0.1, "validation_nll": 0.02337755861566644, "validation": { "categorical": "125/126", "categorical_accuracy": 0.9920634920634921, "completion_found": "24/24", "false_completions": "0/48", "unknown": "24/24", "score_mae": 0.03018260889306569 }, "train": { "categorical": "246/246", "categorical_accuracy": 1.0, "completion_found": "48/48", "false_completions": "0/96", "unknown": "48/48", "score_mae": 0.01768083592835426 } }, { "l2": 0.3, "validation_nll": 0.03863210478984501, "validation": { "categorical": "125/126", "categorical_accuracy": 0.9920634920634921, "completion_found": "24/24", "false_completions": "0/48", "unknown": "24/24", "score_mae": 0.05465809329027363 }, "train": { "categorical": "246/246", "categorical_accuracy": 1.0, "completion_found": "48/48", "false_completions": "0/96", "unknown": "48/48", "score_mae": 0.04015321627012537 } }, { "l2": 1.0, "validation_nll": 0.07221928214550037, "validation": { "categorical": "126/126", "categorical_accuracy": 1.0, "completion_found": "24/24", "false_completions": "0/48", "unknown": "24/24", "score_mae": 0.10031443697789943 }, "train": { "categorical": "244/246", "categorical_accuracy": 0.991869918699187, "completion_found": "48/48", "false_completions": "0/96", "unknown": "47/48", "score_mae": 0.09034251097401509 } } ], "selected_l2": 1.0, "test": { "categorical": "115/126", "categorical_accuracy": 0.9126984126984127, "completion_found": "24/24", "false_completions": "0/48", "unknown": "24/24", "score_mae": 0.1781372601465551 }, "margin_weight": 0.9012869778818261, "type_bias": { "choice": 6.874923957629764e-17, "noul": -1.9873536525856503e-17, "score": -7.646542884907737e-17 } }