xlmr-sold_mrp0.25_s13_pre_ep3
xlm-roberta-base Finetuning
Model Description
Base Model: xlm-roberta-base
Intermediate Task: mrp-
Pre-Finetuned Model: None
Training Information
Epochs: 3
Steps: 0
Validation Time: 0.01s
Performance Metrics
Main Metrics
Validation Loss: 0.041010
Validation Accuracy: 0.944507
Validation F1: 0.631189
Classification Report
{'0': {'precision': 0.9521423862887277, 'recall': 0.9908760375934692, 'f1-score': 0.9711231384677447, 'support': 29154.0}, '1': {'precision': 0.5702746365105008, 'recall': 0.1955678670360111, 'f1-score': 0.29125412541254125, 'support': 1805.0}, 'accuracy': 0.9445072515262121, 'macro avg': {'precision': 0.7612085113996143, 'recall': 0.5932219523147402, 'f1-score': 0.631188631940143, 'support': 30959.0}, 'weighted avg': {'precision': 0.9298783826597442, 'recall': 0.9445072515262121, 'f1-score': 0.9314847919912873, 'support': 30959.0}}
Masked Metrics
Masked Accuracy: 0.987618
Masked F1: 0.947370
Masked Classification Report
{'0': {'precision': 0.991905261579973, 'recall': 0.9948879867689069, 'f1-score': 0.9933943852274433, 'support': 6651.0}, '1': {'precision': 0.9220183486238532, 'recall': 0.881578947368421, 'f1-score': 0.9013452914798207, 'support': 456.0}, 'accuracy': 0.9876178415646546, 'macro avg': {'precision': 0.9569618051019131, 'recall': 0.938233467068664, 'f1-score': 0.947369838353632, 'support': 7107.0}, 'weighted avg': {'precision': 0.9874211709217501, 'recall': 0.9876178415646546, 'f1-score': 0.9874883226484484, 'support': 7107.0}}
Trainer Arguments:
"learning_rate": 2e-05
"epochs": 5
"batch_size": 16
"model": xlm-roberta-base
"intermediate_task": mrp
"n_tk_label": 2
"mask_ratio": 0.25
"seed": 13
"dataset": sold
"finetuning_stage": pre
"val_int": 10000
"patience": 3
"skip_empty_rat": True