{ "test_macro_f1_mean": 0.5866979355548291, "test_macro_f1_std": 0.020313865855319885, "test_macro_f1_text": "0.5867 ± 0.0203", "test_accuracy_mean": 0.5879373848987108, "test_accuracy_std": 0.017598079975705685, "test_accuracy_text": "0.5879 ± 0.0176", "test_macro_precision_mean": 0.593654940648605, "test_macro_precision_std": 0.01966614206058216, "test_macro_precision_text": "0.5937 ± 0.0197", "test_macro_recall_mean": 0.5865456513674486, "test_macro_recall_std": 0.017548551221113946, "test_macro_recall_text": "0.5865 ± 0.0175", "dev_macro_f1_mean": 0.5791650674505112, "dev_macro_f1_std": 0.011344163758615055, "dev_macro_f1_text": "0.5792 ± 0.0113", "task": "ViFactCheck-full-context", "dataset": "ViFactCheck", "model_key": "distilbert", "model_name": "Multilingual DistilBERT", "base_model": "distilbert-base-multilingual-cased", "seeds": [ 22, 42, 202 ], "representative_seed": 42, "selection_rule": "maximum development Macro-F1; seed ascending tie-break", "split_policy": "merged_stratified_80_10_10", "split_seed": 42, "max_length": 256, "epochs": 3, "effective_batch_size": 8 }