RoBERTa_Combined_Generated_v2_2000_Fold3

This model is a fine-tuned version of ICT2214Team7/RoBERTa_Test_Training on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0492
• Precision: 0.8777
• Recall: 0.9317
• F1: 0.9039
• Accuracy: 0.9864
• Report: {'AGE': {'precision': 0.956140350877193, 'recall': 0.990909090909091, 'f1-score': 0.9732142857142858, 'support': 110}, 'LOC': {'precision': 0.7917888563049853, 'recall': 0.9342560553633218, 'f1-score': 0.8571428571428571, 'support': 289}, 'NAT': {'precision': 0.9137931034482759, 'recall': 0.9464285714285714, 'f1-score': 0.9298245614035087, 'support': 168}, 'ORG': {'precision': 0.9090909090909091, 'recall': 0.8783783783783784, 'f1-score': 0.8934707903780069, 'support': 148}, 'PER': {'precision': 0.9375, 'recall': 0.9202453987730062, 'f1-score': 0.9287925696594428, 'support': 163}, 'micro avg': {'precision': 0.8776824034334764, 'recall': 0.9316628701594533, 'f1-score': 0.903867403314917, 'support': 878}, 'macro avg': {'precision': 0.9016626439442726, 'recall': 0.9340434989704736, 'f1-score': 0.9164890128596201, 'support': 878}, 'weighted avg': {'precision': 0.8825485352999964, 'recall': 0.9316628701594533, 'f1-score': 0.9050173682107981, 'support': 878}}

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy	Report
No log	1.0	160	0.0674	0.8385	0.9226	0.8785	0.9800	{'AGE': {'precision': 0.9478260869565217, 'recall': 0.990909090909091, 'f1-score': 0.9688888888888889, 'support': 110}, 'LOC': {'precision': 0.7355371900826446, 'recall': 0.9238754325259516, 'f1-score': 0.8190184049079754, 'support': 289}, 'NAT': {'precision': 0.8722222222222222, 'recall': 0.9345238095238095, 'f1-score': 0.9022988505747127, 'support': 168}, 'ORG': {'precision': 0.8680555555555556, 'recall': 0.8445945945945946, 'f1-score': 0.8561643835616439, 'support': 148}, 'PER': {'precision': 0.926829268292683, 'recall': 0.9325153374233128, 'f1-score': 0.9296636085626913, 'support': 163}, 'micro avg': {'precision': 0.8385093167701864, 'recall': 0.9225512528473804, 'f1-score': 0.878524945770065, 'support': 878}, 'macro avg': {'precision': 0.8700940646219253, 'recall': 0.925283652995352, 'f1-score': 0.8952068272991823, 'support': 878}, 'weighted avg': {'precision': 0.8461387742441511, 'recall': 0.9225512528473804, 'f1-score': 0.8805328025689936, 'support': 878}}
No log	2.0	320	0.0455	0.8674	0.9237	0.8946	0.9857	{'AGE': {'precision': 0.9557522123893806, 'recall': 0.9818181818181818, 'f1-score': 0.968609865470852, 'support': 110}, 'LOC': {'precision': 0.7800586510263929, 'recall': 0.9204152249134948, 'f1-score': 0.8444444444444444, 'support': 289}, 'NAT': {'precision': 0.8920454545454546, 'recall': 0.9345238095238095, 'f1-score': 0.9127906976744186, 'support': 168}, 'ORG': {'precision': 0.896551724137931, 'recall': 0.8783783783783784, 'f1-score': 0.8873720136518771, 'support': 148}, 'PER': {'precision': 0.9375, 'recall': 0.9202453987730062, 'f1-score': 0.9287925696594428, 'support': 163}, 'micro avg': {'precision': 0.8673796791443851, 'recall': 0.9236902050113895, 'f1-score': 0.894649751792609, 'support': 878}, 'macro avg': {'precision': 0.8923816084198318, 'recall': 0.9270761986813743, 'f1-score': 0.908401918180207, 'support': 878}, 'weighted avg': {'precision': 0.8723638781839517, 'recall': 0.9236902050113895, 'f1-score': 0.8959733641577534, 'support': 878}}
No log	3.0	480	0.0492	0.8777	0.9317	0.9039	0.9864	{'AGE': {'precision': 0.956140350877193, 'recall': 0.990909090909091, 'f1-score': 0.9732142857142858, 'support': 110}, 'LOC': {'precision': 0.7917888563049853, 'recall': 0.9342560553633218, 'f1-score': 0.8571428571428571, 'support': 289}, 'NAT': {'precision': 0.9137931034482759, 'recall': 0.9464285714285714, 'f1-score': 0.9298245614035087, 'support': 168}, 'ORG': {'precision': 0.9090909090909091, 'recall': 0.8783783783783784, 'f1-score': 0.8934707903780069, 'support': 148}, 'PER': {'precision': 0.9375, 'recall': 0.9202453987730062, 'f1-score': 0.9287925696594428, 'support': 163}, 'micro avg': {'precision': 0.8776824034334764, 'recall': 0.9316628701594533, 'f1-score': 0.903867403314917, 'support': 878}, 'macro avg': {'precision': 0.9016626439442726, 'recall': 0.9340434989704736, 'f1-score': 0.9164890128596201, 'support': 878}, 'weighted avg': {'precision': 0.8825485352999964, 'recall': 0.9316628701594533, 'f1-score': 0.9050173682107981, 'support': 878}}

Framework versions

• Transformers 4.40.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1