{ "rows": { "train": 288, "validation": 144, "test": 144 }, "zero_shot_verify": { "validation": { "categorical": "123/126", "categorical_accuracy": 0.9761904761904762, "completion_found": "24/24", "false_completions": "0/48", "unknown": "24/24", "score_mae": 0.11686750791113261 }, "test": { "categorical": "121/126", "categorical_accuracy": 0.9603174603174603, "completion_found": "24/24", "false_completions": "0/48", "unknown": "24/24", "score_mae": 0.14550618702502943 } }, "candidates": [ { "l2": 0.0001, "validation_nll": 0.18247217256887968, "validation": { "categorical": "123/126", "categorical_accuracy": 0.9761904761904762, "completion_found": "24/24", "false_completions": "0/48", "unknown": "24/24", "score_mae": 0.11173399877501998 }, "train": { "categorical": "246/246", "categorical_accuracy": 1.0, "completion_found": "48/48", "false_completions": "0/96", "unknown": "48/48", "score_mae": 4.8515959160162356e-08 } }, { "l2": 0.001, "validation_nll": 0.16204246056729416, "validation": { "categorical": "123/126", "categorical_accuracy": 0.9761904761904762, "completion_found": "24/24", "false_completions": "0/48", "unknown": "24/24", "score_mae": 0.11350317073594818 }, "train": { "categorical": "246/246", "categorical_accuracy": 1.0, "completion_found": "48/48", "false_completions": "0/96", "unknown": "48/48", "score_mae": 4.374837008967003e-06 } }, { "l2": 0.01, "validation_nll": 0.16181720731808594, "validation": { "categorical": "123/126", "categorical_accuracy": 0.9761904761904762, "completion_found": "24/24", "false_completions": "0/48", "unknown": "24/24", "score_mae": 0.11351722802142855 }, "train": { "categorical": "246/246", "categorical_accuracy": 1.0, "completion_found": "48/48", "false_completions": "0/96", "unknown": "48/48", "score_mae": 4.2544173717232745e-06 } }, { "l2": 0.03, "validation_nll": 0.15771313672593024, "validation": { "categorical": "123/126", "categorical_accuracy": 0.9761904761904762, "completion_found": "24/24", "false_completions": "0/48", "unknown": "24/24", "score_mae": 0.11370932208449076 }, "train": { "categorical": "246/246", "categorical_accuracy": 1.0, "completion_found": "48/48", "false_completions": "0/96", "unknown": "48/48", "score_mae": 5.492167578932061e-06 } }, { "l2": 0.1, "validation_nll": 0.19399516842887435, "validation": { "categorical": "123/126", "categorical_accuracy": 0.9761904761904762, "completion_found": "24/24", "false_completions": "0/48", "unknown": "24/24", "score_mae": 0.11240459839262999 }, "train": { "categorical": "246/246", "categorical_accuracy": 1.0, "completion_found": "48/48", "false_completions": "0/96", "unknown": "48/48", "score_mae": 5.972145274715241e-07 } }, { "l2": 0.3, "validation_nll": 0.19563403145598923, "validation": { "categorical": "123/126", "categorical_accuracy": 0.9761904761904762, "completion_found": "24/24", "false_completions": "0/48", "unknown": "24/24", "score_mae": 0.1123652855554822 }, "train": { "categorical": "246/246", "categorical_accuracy": 1.0, "completion_found": "48/48", "false_completions": "0/96", "unknown": "48/48", "score_mae": 5.420496353040122e-07 } }, { "l2": 1.0, "validation_nll": 0.1911423442346843, "validation": { "categorical": "123/126", "categorical_accuracy": 0.9761904761904762, "completion_found": "24/24", "false_completions": "0/48", "unknown": "24/24", "score_mae": 0.11248062833000944 }, "train": { "categorical": "246/246", "categorical_accuracy": 1.0, "completion_found": "48/48", "false_completions": "0/96", "unknown": "48/48", "score_mae": 7.112265638759484e-07 } } ], "selected_l2": 0.03, "test": { "categorical": "121/126", "categorical_accuracy": 0.9603174603174603, "completion_found": "24/24", "false_completions": "0/48", "unknown": "24/24", "score_mae": 0.14242517774349603 }, "margin_weight": 1.4427485794947605, "type_bias": { "choice": -3.1960769556669856e-14, "noul": -1.5039732381612254e-14, "score": -2.5901815656082795e-14 } }