mrp_0.25_seed66_ep2
xlm-roberta-base Finetuning
Model Description
Base Model: xlm-roberta-base
Intermediate Task: mrp-
Pre-Finetuned Model: None
Training Information
Epochs: 2
Steps: 0
Validation Time: 0.01s
Performance Metrics
Main Metrics
Validation Loss: 0.178722
Validation Accuracy: 0.941314
Validation F1: 0.484885
Classification Report
{'0': {'precision': 0.941314327907798, 'recall': 1.0, 'f1-score': 0.9697701339507193, 'support': 29321.0}, '1': {'precision': 0.0, 'recall': 0.0, 'f1-score': 0.0, 'support': 1828.0}, 'accuracy': 0.941314327907798, 'macro avg': {'precision': 0.470657163953899, 'recall': 0.5, 'f1-score': 0.48488506697535966, 'support': 31149.0}, 'weighted avg': {'precision': 0.8860726639245095, 'recall': 0.941314327907798, 'f1-score': 0.9128585218648767, 'support': 31149.0}}
Masked Metrics
Masked Accuracy: 0.937875
Masked F1: 0.483971
Masked Classification Report
{'0': {'precision': 0.9378751919586765, 'recall': 1.0, 'f1-score': 0.9679417909372524, 'support': 6718.0}, '1': {'precision': 0.0, 'recall': 0.0, 'f1-score': 0.0, 'support': 445.0}, 'accuracy': 0.9378751919586765, 'macro avg': {'precision': 0.46893759597933826, 'recall': 0.5, 'f1-score': 0.4839708954686262, 'support': 7163.0}, 'weighted avg': {'precision': 0.8796098756915243, 'recall': 0.9378751919586765, 'f1-score': 0.9078085929801007, 'support': 7163.0}}
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": 66
"dataset": sold
"finetuning_stage": pre
"val_int": 1000
"patience": 3
"skip_empty_rat": True