roberta-base-detect-cheapfake-co1-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: 0.3239
• Accuracy: 0.905
• F1: 0.9026

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	0.6857	0.52	0.6643
No log	2.0	76	0.5835	0.78	0.7284
No log	3.0	114	0.3515	0.87	0.8646
No log	4.0	152	0.3897	0.845	0.8517
No log	5.0	190	0.4177	0.845	0.8268
No log	6.0	228	0.3364	0.895	0.8889
No log	7.0	266	0.3319	0.89	0.8842
No log	8.0	304	0.3597	0.885	0.8770
No log	9.0	342	0.3205	0.91	0.9072
No log	10.0	380	0.3239	0.905	0.9026

Framework versions

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