RoBERTa_Combined_Generated_v1.1

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: 0.0017
• Precision: 0.9980
• Recall: 0.9980
• F1: 0.9980
• Accuracy: 0.9996
• Report: {'AGE': {'precision': 1.0, 'recall': 0.9444444444444444, 'f1-score': 0.9714285714285714, 'support': 18}, 'LOC': {'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 101}, 'NAT': {'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 25}, 'ORG': {'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 173}, 'PER': {'precision': 0.9943502824858758, 'recall': 1.0, 'f1-score': 0.9971671388101983, 'support': 176}, 'micro avg': {'precision': 0.9979716024340771, 'recall': 0.9979716024340771, 'f1-score': 0.9979716024340771, 'support': 493}, 'macro avg': {'precision': 0.9988700564971751, 'recall': 0.9888888888888889, 'f1-score': 0.9937191420477539, 'support': 493}, 'weighted avg': {'precision': 0.9979830623073309, 'recall': 0.9979716024340771, 'f1-score': 0.9979454984103634, 'support': 493}}

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	200	0.0080	0.972	0.9858	0.9789	0.9980	{'AGE': {'precision': 1.0, 'recall': 0.9444444444444444, 'f1-score': 0.9714285714285714, 'support': 18}, 'LOC': {'precision': 0.9339622641509434, 'recall': 0.9801980198019802, 'f1-score': 0.9565217391304348, 'support': 101}, 'NAT': {'precision': 1.0, 'recall': 0.96, 'f1-score': 0.9795918367346939, 'support': 25}, 'ORG': {'precision': 0.9771428571428571, 'recall': 0.9884393063583815, 'f1-score': 0.9827586206896551, 'support': 173}, 'PER': {'precision': 0.9831460674157303, 'recall': 0.9943181818181818, 'f1-score': 0.9887005649717514, 'support': 176}, 'micro avg': {'precision': 0.972, 'recall': 0.9858012170385395, 'f1-score': 0.9788519637462235, 'support': 493}, 'macro avg': {'precision': 0.9788502377419063, 'recall': 0.9734799904845977, 'f1-score': 0.9758002665910214, 'support': 493}, 'weighted avg': {'precision': 0.9724332876878866, 'recall': 0.9858012170385395, 'f1-score': 0.9789305206300083, 'support': 493}}
No log	2.0	400	0.0029	0.9959	0.9959	0.9959	0.9993	{'AGE': {'precision': 1.0, 'recall': 0.9444444444444444, 'f1-score': 0.9714285714285714, 'support': 18}, 'LOC': {'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 101}, 'NAT': {'precision': 1.0, 'recall': 0.96, 'f1-score': 0.9795918367346939, 'support': 25}, 'ORG': {'precision': 0.9942528735632183, 'recall': 1.0, 'f1-score': 0.9971181556195965, 'support': 173}, 'PER': {'precision': 0.9943502824858758, 'recall': 1.0, 'f1-score': 0.9971671388101983, 'support': 176}, 'micro avg': {'precision': 0.9959432048681541, 'recall': 0.9959432048681541, 'f1-score': 0.9959432048681541, 'support': 493}, 'macro avg': {'precision': 0.9977206312098188, 'recall': 0.9808888888888889, 'f1-score': 0.989061140518612, 'support': 493}, 'weighted avg': {'precision': 0.9959663221986833, 'recall': 0.9959432048681541, 'f1-score': 0.9958993256731576, 'support': 493}}
0.0711	3.0	600	0.0017	0.9980	0.9980	0.9980	0.9996	{'AGE': {'precision': 1.0, 'recall': 0.9444444444444444, 'f1-score': 0.9714285714285714, 'support': 18}, 'LOC': {'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 101}, 'NAT': {'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 25}, 'ORG': {'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 173}, 'PER': {'precision': 0.9943502824858758, 'recall': 1.0, 'f1-score': 0.9971671388101983, 'support': 176}, 'micro avg': {'precision': 0.9979716024340771, 'recall': 0.9979716024340771, 'f1-score': 0.9979716024340771, 'support': 493}, 'macro avg': {'precision': 0.9988700564971751, 'recall': 0.9888888888888889, 'f1-score': 0.9937191420477539, 'support': 493}, 'weighted avg': {'precision': 0.9979830623073309, 'recall': 0.9979716024340771, 'f1-score': 0.9979454984103634, 'support': 493}}

Framework versions

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