RoBERTa_Combined_Generated_v1.1_epoch_8

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: 0.0076
• Precision: 0.9219
• Recall: 0.8872
• F1: 0.9042
• Accuracy: 0.9971
• Report: {'PER': {'precision': 0.921875, 'recall': 0.8872180451127819, 'f1-score': 0.9042145593869733, 'support': 133}, 'micro avg': {'precision': 0.921875, 'recall': 0.8872180451127819, 'f1-score': 0.9042145593869733, 'support': 133}, 'macro avg': {'precision': 0.921875, 'recall': 0.8872180451127819, 'f1-score': 0.9042145593869733, 'support': 133}, 'weighted avg': {'precision': 0.921875, 'recall': 0.8872180451127819, 'f1-score': 0.9042145593869733, 'support': 133}}

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	0.0087	0.8562	0.9398	0.8961	0.9967	{'PER': {'precision': 0.8561643835616438, 'recall': 0.9398496240601504, 'f1-score': 0.8960573476702508, 'support': 133}, 'micro avg': {'precision': 0.8561643835616438, 'recall': 0.9398496240601504, 'f1-score': 0.8960573476702508, 'support': 133}, 'macro avg': {'precision': 0.8561643835616438, 'recall': 0.9398496240601504, 'f1-score': 0.8960573476702508, 'support': 133}, 'weighted avg': {'precision': 0.8561643835616438, 'recall': 0.9398496240601504, 'f1-score': 0.8960573476702508, 'support': 133}}
No log	2.0	400	0.0072	0.9111	0.9248	0.9179	0.9973	{'PER': {'precision': 0.9111111111111111, 'recall': 0.924812030075188, 'f1-score': 0.917910447761194, 'support': 133}, 'micro avg': {'precision': 0.9111111111111111, 'recall': 0.924812030075188, 'f1-score': 0.917910447761194, 'support': 133}, 'macro avg': {'precision': 0.9111111111111111, 'recall': 0.924812030075188, 'f1-score': 0.917910447761194, 'support': 133}, 'weighted avg': {'precision': 0.9111111111111111, 'recall': 0.924812030075188, 'f1-score': 0.917910447761194, 'support': 133}}
0.0267	3.0	600	0.0076	0.9219	0.8872	0.9042	0.9971	{'PER': {'precision': 0.921875, 'recall': 0.8872180451127819, 'f1-score': 0.9042145593869733, 'support': 133}, 'micro avg': {'precision': 0.921875, 'recall': 0.8872180451127819, 'f1-score': 0.9042145593869733, 'support': 133}, 'macro avg': {'precision': 0.921875, 'recall': 0.8872180451127819, 'f1-score': 0.9042145593869733, 'support': 133}, 'weighted avg': {'precision': 0.921875, 'recall': 0.8872180451127819, 'f1-score': 0.9042145593869733, 'support': 133}}

Framework versions

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