pulf-classifier_roberta_final

This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0165
• Accuracy: 0.9954
• F1-score: 0.9909
• Recall: 0.9917
• Precision: 0.9902

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• 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	Accuracy	F1-score	Recall	Precision
0.0248	1.0	10746	0.0204	0.9937	0.9875	0.9859	0.9891
0.0228	2.0	21492	0.0152	0.9963	0.9926	0.9906	0.9946
0.0201	3.0	32238	0.0165	0.9954	0.9909	0.9917	0.9902

Framework versions

• Transformers 4.28.1
• Pytorch 2.0.0+cu118
• Datasets 2.11.0
• Tokenizers 0.13.3