roberta-base-detect-cheapfake-combined-train-test-2200-2-8

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

• Loss: 0.4708
• Accuracy: 0.8
• F1: 0.7701

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	1.0	69	0.6564	0.535	0.0971
No log	2.0	138	0.5171	0.725	0.6995
No log	3.0	207	0.4709	0.77	0.7195
No log	4.0	276	0.4611	0.795	0.7630
No log	5.0	345	0.4708	0.8	0.7701

Framework versions

• Transformers 4.37.0
• Pytorch 2.1.2
• Datasets 2.1.0
• Tokenizers 0.15.1