xlmr-sold_mrp0.25_s13_pre_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: 0.068140
Validation Accuracy: 0.944055
Validation F1: 0.620364
Classification Report
{'0': {'precision': 0.9511384574888129, 'recall': 0.9915277491939356, 'f1-score': 0.9709132435428073, 'support': 29154.0}, '1': {'precision': 0.564373897707231, 'recall': 0.1772853185595568, 'f1-score': 0.26981450252951095, 'support': 1805.0}, 'accuracy': 0.944055040537485, 'macro avg': {'precision': 0.7577561775980219, 'recall': 0.5844065338767462, 'f1-score': 0.6203638730361591, 'support': 30959.0}, 'weighted avg': {'precision': 0.9285889555538099, 'recall': 0.944055040537485, 'f1-score': 0.9300371420043532, 'support': 30959.0}}
Masked Metrics
Masked Accuracy: 0.974954
Masked F1: 0.877194
Masked Classification Report
{'0': {'precision': 0.9793357933579335, 'recall': 0.9943054098606324, 'f1-score': 0.9867638310529446, 'support': 6673.0}, '1': {'precision': 0.8855421686746988, 'recall': 0.6774193548387096, 'f1-score': 0.7676240208877284, 'support': 434.0}, 'accuracy': 0.9749542704375967, 'macro avg': {'precision': 0.9324389810163162, 'recall': 0.835862382349671, 'f1-score': 0.8771939259703365, 'support': 7107.0}, 'weighted avg': {'precision': 0.9736081399018305, 'recall': 0.9749542704375967, 'f1-score': 0.9733817179796782, '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