mrp_0.5_seed66_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: 0.146249
Validation Accuracy: 0.941025
Validation F1: 0.509616
Classification Report
{'0': {'precision': 0.9426620280891638, 'recall': 0.998056000818526, 'f1-score': 0.9695684585438582, 'support': 29321.0}, '1': {'precision': 0.45714285714285713, 'recall': 0.0262582056892779, 'f1-score': 0.04966373512674599, 'support': 1828.0}, 'accuracy': 0.941025394073646, 'macro avg': {'precision': 0.6999024426160104, 'recall': 0.512157103253902, 'f1-score': 0.5096160968353021, 'support': 31149.0}, 'weighted avg': {'precision': 0.9141690092285312, 'recall': 0.941025394073646, 'f1-score': 0.9155832315893339, 'support': 31149.0}}
Masked Metrics
Masked Accuracy: 0.940836
Masked F1: 0.663014
Masked Classification Report
{'0': {'precision': 0.9521870392473496, 'recall': 0.9863990108371518, 'f1-score': 0.9689911403258074, 'support': 13749.0}, '1': {'precision': 0.5630841121495327, 'recall': 0.2613882863340564, 'f1-score': 0.35703703703703704, 'support': 922.0}, 'accuracy': 0.9408356621907163, 'macro avg': {'precision': 0.7576355756984412, 'recall': 0.6238936485856041, 'f1-score': 0.6630140886814222, 'support': 14671.0}, 'weighted avg': {'precision': 0.9277338391393688, 'recall': 0.9408356621907163, 'f1-score': 0.9305328427842461, 'support': 14671.0}}
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": 66
"dataset": sold
"finetuning_stage": pre
"val_int": 1000
"patience": 3
"skip_empty_rat": True