xlm-roberta-base-pre-mrp-14012025-1406-44
xlm-roberta-base Finetuning
Model Description
Base Model: xlm-roberta-base
Intermediate Task: mrp
Pre-Finetuned Model: None
Training Information
Epochs: 4
Steps: 410
Validation Time: 0.01s
Performance Metrics
Main Metrics
Validation Loss: 0.082961
Validation Accuracy: 0.939118
Validation F1: 0.566091
Classification Report
{'0': {'precision': 0.9464033387006671, 'recall': 0.9914624070503993, 'f1-score': 0.968409018308983, 'support': 29048.0}, '1': {'precision': 0.42592592592592593, 'recall': 0.10137741046831956, 'f1-score': 0.16377392078326658, 'support': 1815.0}, 'accuracy': 0.9391180377798659, 'macro avg': {'precision': 0.6861646323132965, 'recall': 0.5464199087593594, 'f1-score': 0.5660914695461248, 'support': 30863.0}, 'weighted avg': {'precision': 0.9157949563598008, 'recall': 0.9391180377798659, 'f1-score': 0.9210898107786335, 'support': 30863.0}}
Masked Metrics
Masked Accuracy: 0.970685
Masked F1: 0.859943
Masked Classification Report
{'0': {'precision': 0.9803409503083061, 'recall': 0.9886604726022387, 'f1-score': 0.9844831354265317, 'support': 13669.0}, '1': {'precision': 0.7925033467202142, 'recall': 0.6859791425260718, 'f1-score': 0.7354037267080745, 'support': 863.0}, 'accuracy': 0.9706853839801817, 'macro avg': {'precision': 0.8864221485142602, 'recall': 0.8373198075641552, 'f1-score': 0.8599434310673031, 'support': 14532.0}, 'weighted avg': {'precision': 0.9691859921541276, 'recall': 0.9706853839801817, 'f1-score': 0.9696912602734881, 'support': 14532.0}}
