roberta-base-detect-cheapfake-3

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

• Loss: 0.1767
• Accuracy: 0.955
• F1: 0.9589

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-06
• 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	1.0	38	0.6686	0.53	0.2167
No log	2.0	76	0.3027	0.92	0.9259
No log	3.0	114	0.1610	0.935	0.9395
No log	4.0	152	0.1561	0.945	0.9502
No log	5.0	190	0.1430	0.955	0.9585
No log	6.0	228	0.1371	0.96	0.9626
No log	7.0	266	0.1459	0.955	0.9585
No log	8.0	304	0.1750	0.955	0.9589
No log	9.0	342	0.1687	0.955	0.9585
No log	10.0	380	0.1767	0.955	0.9589

Framework versions

• Transformers 4.36.2
• Pytorch 2.0.0
• Datasets 2.1.0
• Tokenizers 0.15.0