{ "evaluation_dtype": "bfloat16", "base_validation": { "choice": { "n": 200, "nll": 1.8233506392094205, "brier": 0.9199781741252144, "hard_label_n": 200, "hard_label_accuracy": 0.135, "mae": null }, "score": { "n": 200, "nll": 1.2868162845555702, "brier": 0.755653917889163, "hard_label_n": 200, "hard_label_accuracy": 0.355, "mae": 0.833484931158023 }, "noul": { "n": 200, "nll": 0.5812086463426769, "brier": 0.3886810789112994, "hard_label_n": 200, "hard_label_accuracy": 0.685, "mae": 0.36346207647013273 } }, "decide_validation": { "choice": { "n": 200, "nll": 0.8005431699930687, "brier": 0.40420523643337797, "hard_label_n": 200, "hard_label_accuracy": 0.74, "mae": null }, "score": { "n": 200, "nll": 0.7330622738796232, "brier": 0.438596593023593, "hard_label_n": 200, "hard_label_accuracy": 0.635, "mae": 0.5985458431827447 }, "noul": { "n": 200, "nll": 0.2804184128570066, "brier": 0.18566711737282862, "hard_label_n": 200, "hard_label_accuracy": 0.865, "mae": 0.17999652788487253 } }, "decide_test_uncalibrated": { "choice": { "n": 300, "nll": 0.8291260863610138, "brier": 0.43582428224932407, "hard_label_n": 300, "hard_label_accuracy": 0.68, "mae": null }, "score": { "n": 300, "nll": 0.7432575400592191, "brier": 0.4429180549709099, "hard_label_n": 300, "hard_label_accuracy": 0.63, "mae": 0.5857725157580695 }, "noul": { "n": 300, "nll": 0.1734100737580112, "brier": 0.11055894969304025, "hard_label_n": 300, "hard_label_accuracy": 0.93, "mae": 0.13128673404692287 } }, "decide_test_calibrated": { "choice": { "n": 300, "nll": 0.804358669731068, "brier": 0.42891276915451876, "hard_label_n": 300, "hard_label_accuracy": 0.68, "mae": null }, "score": { "n": 300, "nll": 0.7420130093340176, "brier": 0.44234142225539114, "hard_label_n": 300, "hard_label_accuracy": 0.63, "mae": 0.5816908331595515 }, "noul": { "n": 300, "nll": 0.14012702863107165, "brier": 0.09082276054150111, "hard_label_n": 300, "hard_label_accuracy": 0.93, "mae": 0.09262523968667083 } } }