xlmr-sold_mrp0.25_s13_pre_ep4
xlm-roberta-base Finetuning
Model Description
Base Model: xlm-roberta-base
Intermediate Task: mrp-
Pre-Finetuned Model: None
Training Information
Epochs: 4
Steps: 0
Validation Time: 0.01s
Performance Metrics
Main Metrics
Validation Loss: 0.035226
Validation Accuracy: 0.944152
Validation F1: 0.626610
Classification Report
{'0': {'precision': 0.9517377697249217, 'recall': 0.9909446388145708, 'f1-score': 0.970945571258129, 'support': 29154.0}, '1': {'precision': 0.5629139072847682, 'recall': 0.1883656509695291, 'f1-score': 0.282274802822748, 'support': 1805.0}, 'accuracy': 0.9441519428922123, 'macro avg': {'precision': 0.7573258385048449, 'recall': 0.58965514489205, 'f1-score': 0.6266101870404385, 'support': 30959.0}, 'weighted avg': {'precision': 0.9290682044384306, 'recall': 0.9441519428922123, 'f1-score': 0.9307940567703916, 'support': 30959.0}}
Masked Metrics
Masked Accuracy: 0.988603
Masked F1: 0.948002
Masked Classification Report
{'0': {'precision': 0.9919487103026688, 'recall': 0.9959580838323353, 'f1-score': 0.9939493538507508, 'support': 6680.0}, '1': {'precision': 0.9325, 'recall': 0.8735362997658079, 'f1-score': 0.9020556227327691, 'support': 427.0}, 'accuracy': 0.988602785985648, 'macro avg': {'precision': 0.9622243551513344, 'recall': 0.9347471917990716, 'f1-score': 0.9480024882917599, 'support': 7107.0}, 'weighted avg': {'precision': 0.988376936094249, 'recall': 0.988602785985648, 'f1-score': 0.9884282305656265, '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