mrp_0.9_seed66_ep4
xlm-roberta-base Finetuning
Model Description
Base Model: xlm-roberta-base
Intermediate Task: mrp-
Pre-Finetuned Model: None
Training Information
Epochs: 4
Steps: 410
Validation Time: 0.01s
Performance Metrics
Main Metrics
Validation Loss: 0.085999
Validation Accuracy: 0.937141
Validation F1: 0.567427
Classification Report
{'0': {'precision': 0.9467428571428571, 'recall': 0.9888475836431226, 'f1-score': 0.9673372702098555, 'support': 29321.0}, '1': {'precision': 0.37595419847328243, 'recall': 0.10776805251641138, 'f1-score': 0.16751700680272108, 'support': 1828.0}, 'accuracy': 0.9371408391922694, 'macro avg': {'precision': 0.6613485278080697, 'recall': 0.548307818079767, 'f1-score': 0.5674271385062883, 'support': 31149.0}, 'weighted avg': {'precision': 0.9132457410862266, 'recall': 0.9371408391922694, 'f1-score': 0.9203992804988457, 'support': 31149.0}}
Masked Metrics
Masked Accuracy: 0.967038
Masked F1: 0.857914
Masked Classification Report
{'0': {'precision': 0.9833649614406267, 'recall': 0.9815023776900137, 'f1-score': 0.9824327867529901, 'support': 24814.0}, '1': {'precision': 0.7229933614966807, 'recall': 0.7440993788819876, 'f1-score': 0.7333945515763698, 'support': 1610.0}, 'accuracy': 0.9670375416288223, 'macro avg': {'precision': 0.8531791614686537, 'recall': 0.8628008782860006, 'f1-score': 0.8579136691646799, 'support': 26424.0}, 'weighted avg': {'precision': 0.9675006609596339, 'recall': 0.9670375416288223, 'f1-score': 0.9672590220453622, 'support': 26424.0}}
Trainer Arguments:
"learning_rate": 2e-05
"epochs": 5
"batch_size": 16
"model": xlm-roberta-base
"intermediate_task": mrp
"n_tk_label": 2
"mask_ratio": 0.9
"seed": 66
"dataset": sold
"finetuning_stage": pre
"val_int": 1000
"patience": 3
"skip_empty_rat": True