{ "task": "human", "best_epoch": 6, "training_seconds": 111.95542904100148, "split_sizes": { "train": 880, "validation": 110, "test": 110 }, "validation": { "loss": 1.267178336056796, "accuracy": 0.8363636363636363, "macro_f1": 0.7900596877869606 }, "test": { "loss": 1.4121767195788297, "accuracy": 0.7454545454545455, "macro_f1": 0.6897269397269397 }, "test_confusions": [ { "gold": "multi_intent_with_financial_risk", "predicted": "refund_missing_after_deadline", "count": 5 }, { "gold": "account_takeover", "predicted": "personal_data_or_payment_card_exposed", "count": 5 }, { "gold": "order_marked_delivered_but_not_received", "predicted": "multi_intent_with_financial_risk", "count": 5 }, { "gold": "change_delivery_address_after_dispatch", "predicted": "cancel_order_after_dispatch", "count": 5 }, { "gold": "fraud_or_phishing", "predicted": "account_takeover", "count": 3 }, { "gold": "missing_item_in_delivered_order", "predicted": "refund_amount_dispute", "count": 3 }, { "gold": "fraud_or_phishing", "predicted": "privacy_data_deletion_request", "count": 2 } ], "history": [ { "epoch": 1, "train_loss": 3.0446458036249333, "validation_loss": 2.9481882918964732, "validation_accuracy": 0.3181818181818182, "validation_macro_f1": 0.275695272469466 }, { "epoch": 2, "train_loss": 2.5696960145776924, "validation_loss": 2.4496376210992987, "validation_accuracy": 0.5818181818181818, "validation_macro_f1": 0.5069444444444445 }, { "epoch": 3, "train_loss": 1.8286097873340954, "validation_loss": 1.8624537467956543, "validation_accuracy": 0.7909090909090909, "validation_macro_f1": 0.7550946528219256 }, { "epoch": 4, "train_loss": 1.237558323686773, "validation_loss": 1.5112867398695513, "validation_accuracy": 0.8, "validation_macro_f1": 0.7386363636363636 }, { "epoch": 5, "train_loss": 0.899948058345101, "validation_loss": 1.34841853055087, "validation_accuracy": 0.8272727272727273, "validation_macro_f1": 0.7803030303030304 }, { "epoch": 6, "train_loss": 0.7283082962036133, "validation_loss": 1.267178336056796, "validation_accuracy": 0.8363636363636363, "validation_macro_f1": 0.7900596877869606 }, { "epoch": 7, "train_loss": 0.6527352463115346, "validation_loss": 1.2407976128838278, "validation_accuracy": 0.8090909090909091, "validation_macro_f1": 0.7660697887970614 }, { "epoch": 8, "train_loss": 0.6315497528422963, "validation_loss": 1.2309001250700518, "validation_accuracy": 0.8181818181818182, "validation_macro_f1": 0.7732847960120687 } ] }