mrp_0.5_seed43_ep4
xlm-roberta-base Finetuning
Model Description
Base Model: xlm-roberta-base
Intermediate Task: mrp-
Pre-Finetuned Model: None
Training Information
Epochs: 4
Steps: 409
Validation Time: 0.01s
Performance Metrics
Main Metrics
Validation Loss: 0.031007
Validation Accuracy: 0.943811
Validation F1: 0.603630
Classification Report
{'0': {'precision': 0.9537642535572278, 'recall': 0.9885221892987296, 'f1-score': 0.9708322183569709, 'support': 29361.0}, '1': {'precision': 0.44481054365733114, 'recall': 0.16100178890876565, 'f1-score': 0.23642732049036777, 'support': 1677.0}, 'accuracy': 0.9438108125523552, 'macro avg': {'precision': 0.6992873986072795, 'recall': 0.5747619891037477, 'f1-score': 0.6036297694236693, 'support': 31038.0}, 'weighted avg': {'precision': 0.9262652081450837, 'recall': 0.9438108125523552, 'f1-score': 0.9311519227927497, 'support': 31038.0}}
Masked Metrics
Masked Accuracy: 0.989456
Masked F1: 0.949026
Masked Classification Report
{'0': {'precision': 0.991980348240734, 'recall': 0.9968779496115588, 'f1-score': 0.9944231187079018, 'support': 13773.0}, '1': {'precision': 0.9437908496732026, 'recall': 0.8667466986794717, 'f1-score': 0.9036295369211514, 'support': 833.0}, 'accuracy': 0.9894563877858414, 'macro avg': {'precision': 0.9678855989569684, 'recall': 0.9318123241455153, 'f1-score': 0.9490263278145266, 'support': 14606.0}, 'weighted avg': {'precision': 0.9892320357454065, 'recall': 0.9894563877858414, 'f1-score': 0.989245037533839, 'support': 14606.0}}
Trainer Arguments:
"learning_rate": 2e-05
"epochs": 5
"batch_size": 16
"model": xlm-roberta-base
"intermediate_task": mrp
"n_tk_label": 2
"mask_ratio": 0.5
"seed": 43
"dataset": sold
"finetuning_stage": pre
"val_int": 1000
"patience": 3
"skip_empty_rat": True