xlmr-sold_mrp0.75_s13_pre_ep1
xlm-roberta-base Finetuning
Model Description
Base Model: xlm-roberta-base
Intermediate Task: mrp-
Pre-Finetuned Model: None
Training Information
Epochs: 1
Steps: 0
Validation Time: 0.01s
Performance Metrics
Main Metrics
Validation Loss: 0.113754
Validation Accuracy: 0.944959
Validation F1: 0.569754
Classification Report
{'0': {'precision': 0.9468355254590441, 'recall': 0.9975646566508883, 'f1-score': 0.9715383330549524, 'support': 29154.0}, '1': {'precision': 0.7078189300411523, 'recall': 0.09529085872576178, 'f1-score': 0.16796875, 'support': 1805.0}, 'accuracy': 0.9449594625149391, 'macro avg': {'precision': 0.8273272277500983, 'recall': 0.5464277576883251, 'f1-score': 0.5697535415274761, 'support': 30959.0}, 'weighted avg': {'precision': 0.9329001607919265, 'recall': 0.9449594625149391, 'f1-score': 0.9246878825425267, 'support': 30959.0}}
Masked Metrics
Masked Accuracy: 0.956798
Masked F1: 0.739765
Masked Classification Report
{'0': {'precision': 0.9589317563127757, 'recall': 0.9966341463414634, 'f1-score': 0.9774195091613644, 'support': 20500.0}, '1': {'precision': 0.8733944954128441, 'recall': 0.35233160621761656, 'f1-score': 0.5021097046413502, 'support': 1351.0}, 'accuracy': 0.9567983158665507, 'macro avg': {'precision': 0.9161631258628099, 'recall': 0.67448287627954, 'f1-score': 0.7397646069013573, 'support': 21851.0}, 'weighted avg': {'precision': 0.9536431727479134, 'recall': 0.9567983158665507, 'f1-score': 0.9480321334848948, 'support': 21851.0}}
Trainer Arguments:
"learning_rate": 2e-05
"epochs": 5
"batch_size": 16
"model": xlm-roberta-base
"intermediate_task": mrp
"n_tk_label": 2
"mask_ratio": 0.75
"seed": 13
"dataset": sold
"finetuning_stage": pre
"val_int": 10000
"patience": 3
"skip_empty_rat": True