roberta-base-detect-cheapfake-ca1-co2

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

• Loss: 0.2524
• Accuracy: 0.94
• F1: 0.9388

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	0.6794	0.645	0.4409
No log	2.0	76	0.4563	0.82	0.8022
No log	3.0	114	0.3002	0.875	0.8718
No log	4.0	152	0.3539	0.87	0.8762
No log	5.0	190	0.2854	0.89	0.8804
No log	6.0	228	0.2317	0.935	0.9333
No log	7.0	266	0.2419	0.93	0.9293
No log	8.0	304	0.2514	0.935	0.9326
No log	9.0	342	0.2549	0.935	0.9340
No log	10.0	380	0.2524	0.94	0.9388

Framework versions

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