RoBERTa_Combined_Generated_v2

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: 0.0086
• Precision: 0.9055
• Recall: 0.8647
• F1: 0.8846
• Accuracy: 0.9969
• Report: {'PER': {'precision': 0.905511811023622, 'recall': 0.8646616541353384, 'f1-score': 0.8846153846153845, 'support': 133}, 'micro avg': {'precision': 0.905511811023622, 'recall': 0.8646616541353384, 'f1-score': 0.8846153846153845, 'support': 133}, 'macro avg': {'precision': 0.905511811023622, 'recall': 0.8646616541353384, 'f1-score': 0.8846153846153845, 'support': 133}, 'weighted avg': {'precision': 0.905511811023622, 'recall': 0.8646616541353384, 'f1-score': 0.8846153846153845, '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	0.0104	0.8768	0.9098	0.8930	0.9965	{'PER': {'precision': 0.8768115942028986, 'recall': 0.9097744360902256, 'f1-score': 0.8929889298892988, 'support': 133}, 'micro avg': {'precision': 0.8768115942028986, 'recall': 0.9097744360902256, 'f1-score': 0.8929889298892988, 'support': 133}, 'macro avg': {'precision': 0.8768115942028986, 'recall': 0.9097744360902256, 'f1-score': 0.8929889298892988, 'support': 133}, 'weighted avg': {'precision': 0.8768115942028986, 'recall': 0.9097744360902256, 'f1-score': 0.8929889298892988, 'support': 133}}
No log	2.0	400	0.0083	0.9058	0.9398	0.9225	0.9974	{'PER': {'precision': 0.9057971014492754, 'recall': 0.9398496240601504, 'f1-score': 0.9225092250922509, 'support': 133}, 'micro avg': {'precision': 0.9057971014492754, 'recall': 0.9398496240601504, 'f1-score': 0.9225092250922509, 'support': 133}, 'macro avg': {'precision': 0.9057971014492754, 'recall': 0.9398496240601504, 'f1-score': 0.9225092250922509, 'support': 133}, 'weighted avg': {'precision': 0.9057971014492754, 'recall': 0.9398496240601504, 'f1-score': 0.9225092250922509, 'support': 133}}
0.0207	3.0	600	0.0086	0.9055	0.8647	0.8846	0.9969	{'PER': {'precision': 0.905511811023622, 'recall': 0.8646616541353384, 'f1-score': 0.8846153846153845, 'support': 133}, 'micro avg': {'precision': 0.905511811023622, 'recall': 0.8646616541353384, 'f1-score': 0.8846153846153845, 'support': 133}, 'macro avg': {'precision': 0.905511811023622, 'recall': 0.8646616541353384, 'f1-score': 0.8846153846153845, 'support': 133}, 'weighted avg': {'precision': 0.905511811023622, 'recall': 0.8646616541353384, 'f1-score': 0.8846153846153845, 'support': 133}}

Framework versions

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