artificially-natural-roberta

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

• Loss: 0.1460
• F1: 0.98

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	F1
No log	1.0	250	0.1378	0.971
0.1033	2.0	500	0.1073	0.985
0.1033	3.0	750	0.1460	0.98

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.17.0
• Tokenizers 0.15.1