{ "keep_confidence": 0.0, "tau": 0.3, "MASTER": 0.6587, "control_master": 0.631, "scorer_run": "runs/reranker/en_v2_rr/best", "report": "reranker_en_v2_rr.json", "grid": [ { "keep_confidence": -0.25, "tau": 0.2, "MASTER": 0.6452, "MASTER_V2": 0.6864, "precision": 0.6054, "recall": 0.3411, "f0.5": 0.5242, "group_means": { "native": 0.3526, "learner": 0.4991, "robustness": 0.94, "precision": 0.9355, "typo": 0.7538 }, "fp_clean": 0.9355, "per_eval": { "ndev_native": 0.495, "cweb_g": 0.3111, "cweb_s": 0.2518, "bea_dev": 0.4989, "conll14": 0.4799, "fce_test": 0.5186, "robustness": 0.94, "fp_clean": 0.9355, "github_typo_test": 0.6545, "garble": 0.8476, "native_conf": 0.7593 } }, { "keep_confidence": -0.25, "tau": 0.25, "MASTER": 0.6482, "MASTER_V2": 0.6901, "precision": 0.6206, "recall": 0.3378, "f0.5": 0.5316, "group_means": { "native": 0.3577, "learner": 0.5054, "robustness": 0.9388, "precision": 0.9355, "typo": 0.7621 }, "fp_clean": 0.9355, "per_eval": { "ndev_native": 0.5034, "cweb_g": 0.3147, "cweb_s": 0.2551, "bea_dev": 0.5072, "conll14": 0.4817, "fce_test": 0.5274, "robustness": 0.9388, "fp_clean": 0.9355, "github_typo_test": 0.662, "garble": 0.8562, "native_conf": 0.7681 } }, { "keep_confidence": -0.25, "tau": 0.3, "MASTER": 0.6502, "MASTER_V2": 0.6932, "precision": 0.6367, "recall": 0.3313, "f0.5": 0.5376, "group_means": { "native": 0.3621, "learner": 0.5099, "robustness": 0.9362, "precision": 0.9355, "typo": 0.7716 }, "fp_clean": 0.9355, "per_eval": { "ndev_native": 0.5111, "cweb_g": 0.3163, "cweb_s": 0.259, "bea_dev": 0.5099, "conll14": 0.4821, "fce_test": 0.5376, "robustness": 0.9362, "fp_clean": 0.9355, "github_typo_test": 0.6705, "garble": 0.8671, "native_conf": 0.7771 } }, { "keep_confidence": -0.25, "tau": 0.4, "MASTER": 0.6518, "MASTER_V2": 0.6979, "precision": 0.6765, "recall": 0.3072, "f0.5": 0.5454, "group_means": { "native": 0.3653, "learner": 0.511, "robustness": 0.9058, "precision": 0.9677, "typo": 0.7881 }, "fp_clean": 0.9677, "per_eval": { "ndev_native": 0.5178, "cweb_g": 0.3143, "cweb_s": 0.2639, "bea_dev": 0.5086, "conll14": 0.4734, "fce_test": 0.5511, "robustness": 0.9058, "fp_clean": 0.9677, "github_typo_test": 0.6879, "garble": 0.8917, "native_conf": 0.7846 } }, { "keep_confidence": -0.5, "tau": 0.2, "MASTER": 0.6426, "MASTER_V2": 0.6785, "precision": 0.5737, "recall": 0.3623, "f0.5": 0.5137, "group_means": { "native": 0.3514, "learner": 0.4967, "robustness": 0.9325, "precision": 0.9355, "typo": 0.7247 }, "fp_clean": 0.9355, "per_eval": { "ndev_native": 0.4931, "cweb_g": 0.3102, "cweb_s": 0.251, "bea_dev": 0.4974, "conll14": 0.482, "fce_test": 0.5106, "robustness": 0.9325, "fp_clean": 0.9355, "github_typo_test": 0.6203, "garble": 0.8356, "native_conf": 0.7182 } }, { "keep_confidence": -0.5, "tau": 0.25, "MASTER": 0.6461, "MASTER_V2": 0.6831, "precision": 0.5898, "recall": 0.358, "f0.5": 0.5222, "group_means": { "native": 0.357, "learner": 0.5044, "robustness": 0.9312, "precision": 0.9355, "typo": 0.7364 }, "fp_clean": 0.9355, "per_eval": { "ndev_native": 0.5018, "cweb_g": 0.315, "cweb_s": 0.2543, "bea_dev": 0.5064, "conll14": 0.4866, "fce_test": 0.5203, "robustness": 0.9312, "fp_clean": 0.9355, "github_typo_test": 0.6281, "garble": 0.847, "native_conf": 0.7341 } }, { "keep_confidence": -0.5, "tau": 0.3, "MASTER": 0.6491, "MASTER_V2": 0.6881, "precision": 0.6076, "recall": 0.3503, "f0.5": 0.5298, "group_means": { "native": 0.3632, "learner": 0.5108, "robustness": 0.9283, "precision": 0.9355, "typo": 0.7517 }, "fp_clean": 0.9355, "per_eval": { "ndev_native": 0.5131, "cweb_g": 0.3178, "cweb_s": 0.2587, "bea_dev": 0.5118, "conll14": 0.49, "fce_test": 0.5305, "robustness": 0.9283, "fp_clean": 0.9355, "github_typo_test": 0.6373, "garble": 0.8585, "native_conf": 0.7593 } }, { "keep_confidence": -0.5, "tau": 0.4, "MASTER": 0.6527, "MASTER_V2": 0.6949, "precision": 0.6515, "recall": 0.3212, "f0.5": 0.5404, "group_means": { "native": 0.367, "learner": 0.5145, "robustness": 0.9031, "precision": 0.9677, "typo": 0.7712 }, "fp_clean": 0.9677, "per_eval": { "ndev_native": 0.5213, "cweb_g": 0.3199, "cweb_s": 0.2597, "bea_dev": 0.5108, "conll14": 0.4838, "fce_test": 0.5489, "robustness": 0.9031, "fp_clean": 0.9677, "github_typo_test": 0.6621, "garble": 0.8857, "native_conf": 0.7658 } }, { "keep_confidence": 0.0, "tau": 0.2, "MASTER": 0.6552, "MASTER_V2": 0.7006, "precision": 0.6337, "recall": 0.3147, "f0.5": 0.5269, "group_means": { "native": 0.3549, "learner": 0.489, "robustness": 0.9324, "precision": 1.0, "typo": 0.7714 }, "fp_clean": 1.0, "per_eval": { "ndev_native": 0.5, "cweb_g": 0.3046, "cweb_s": 0.2601, "bea_dev": 0.4921, "conll14": 0.4546, "fce_test": 0.5202, "robustness": 0.9324, "fp_clean": 1.0, "github_typo_test": 0.6787, "garble": 0.8529, "native_conf": 0.7826 } }, { "keep_confidence": 0.0, "tau": 0.25, "MASTER": 0.6577, "MASTER_V2": 0.7033, "precision": 0.6475, "recall": 0.3125, "f0.5": 0.5332, "group_means": { "native": 0.3596, "learner": 0.4941, "robustness": 0.9311, "precision": 1.0, "typo": 0.7763 }, "fp_clean": 1.0, "per_eval": { "ndev_native": 0.5062, "cweb_g": 0.3095, "cweb_s": 0.2631, "bea_dev": 0.4984, "conll14": 0.4558, "fce_test": 0.5282, "robustness": 0.9311, "fp_clean": 1.0, "github_typo_test": 0.6851, "garble": 0.8611, "native_conf": 0.7826 } }, { "keep_confidence": 0.0, "tau": 0.3, "MASTER": 0.6587, "MASTER_V2": 0.7053, "precision": 0.6636, "recall": 0.3076, "f0.5": 0.5389, "group_means": { "native": 0.3622, "learner": 0.499, "robustness": 0.9255, "precision": 1.0, "typo": 0.7854 }, "fp_clean": 1.0, "per_eval": { "ndev_native": 0.5124, "cweb_g": 0.309, "cweb_s": 0.2653, "bea_dev": 0.501, "conll14": 0.4575, "fce_test": 0.5385, "robustness": 0.9255, "fp_clean": 1.0, "github_typo_test": 0.6933, "garble": 0.8711, "native_conf": 0.7918 } }, { "keep_confidence": 0.0, "tau": 0.4, "MASTER": 0.6545, "MASTER_V2": 0.7045, "precision": 0.7013, "recall": 0.2881, "f0.5": 0.545, "group_means": { "native": 0.3656, "learner": 0.4982, "robustness": 0.9024, "precision": 1.0, "typo": 0.8004 }, "fp_clean": 1.0, "per_eval": { "ndev_native": 0.5208, "cweb_g": 0.3057, "cweb_s": 0.2702, "bea_dev": 0.4994, "conll14": 0.4478, "fce_test": 0.5475, "robustness": 0.9024, "fp_clean": 1.0, "github_typo_test": 0.7092, "garble": 0.892, "native_conf": 0.8 } } ] }