{ "model": "pluto-typed", "benchmark": "LocalLLaMA/typed-decisions", "mode": "fitted on train", "n_decisions": 2000, "accuracy": 0.711, "ece": 0.10864835740625857, "brier": 0.4019103944301605, "nll": 0.6982178688049316, "per_kind": { "choice": { "n": 600, "accuracy": 0.6433333333333333, "ece": 0.09454844221472741 }, "noul": { "n": 600, "accuracy": 0.8266666666666667, "ece": 0.07666520804166793 }, "score": { "n": 800, "accuracy": 0.675, "ece": 0.14437313050031664 } }, "temperatures": { "choice": 1.2249749898910522, "noul": 1.3188161849975586, "score": 1.3833255767822266 }, "validation": { "n": 300, "accuracy": 0.74, "ece": 0.1383799741665522, "brier": 0.38873958587646484, "nll": 0.6865395903587341, "per_kind": { "choice": { "n": 90, "accuracy": 0.7555555555555555, "ece": 0.20956675708293912 }, "noul": { "n": 90, "accuracy": 0.8888888888888888, "ece": 0.1182247890366448 }, "score": { "n": 120, "accuracy": 0.6166666666666667, "ece": 0.10029492701093357 } } }, "best_val_accuracy": 0.74 }