final_wo_mrp_0.5_seed42_no_ckpy_ep3

final_wo_mrp_0.5_seed42_no_ckpy_ep3

xlm-roberta-base Finetuning

Model Description

Base Model: xlm-roberta-base

Intermediate Task:

Pre-Finetuned Model: xlm-roberta-base

Wandb Run URL: https://wandb.ai/s_haturusinghe-university-of-kelaniya/baseline-without-augmented-2-seed42-no-pre/runs/h32q8dy6

Training Information

Epochs: 3

Steps: 0

Validation Time: 0.02s

Performance Metrics

Main Metrics

Validation Loss: 0.452772

Validation Accuracy: 0.808000

Validation F1: 0.799549

Classification Report

{'0': {'precision': 0.7723577235772358, 'recall': 0.9223300970873787, 'f1-score': 0.8407079646017699, 'support': 412.0}, '1': {'precision': 0.875968992248062, 'recall': 0.6686390532544378, 'f1-score': 0.7583892617449665, 'support': 338.0}, 'accuracy': 0.808, 'macro avg': {'precision': 0.8241633579126488, 'recall': 0.7954845751709083, 'f1-score': 0.7995486131733682, 'support': 750.0}, 'weighted avg': {'precision': 0.8190518686582214, 'recall': 0.808, 'f1-score': 0.8036096691809704, 'support': 750.0}}

Trainer Arguments:

                "learning_rate": 2e-05
                "epochs": 5
                "batch_size": 16
                "model": xlm-roberta-base
                "intermediate_task": False
                "n_tk_label": 2
                "mask_ratio": 0.5
                "seed": 42
                "dataset": sold
                "finetuning_stage": final
                "val_int": 10000
                "patience": 3
                "skip_empty_rat": False