distilroberta-clickbait

This model is a fine-tuned version of distilroberta-base on a dataset of headlines. It achieves the following results on the evaluation set:

• Loss: 0.0268
• Acc: 0.9963

Training and evaluation data

The following data sources were used:

• 32k headlines classified as clickbait/not-clickbait from kaggle
• A dataset of headlines from https://github.com/MotiBaadror/Clickbait-Detection

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 12345
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 16
• num_epochs: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Acc
0.0195	1.0	981	0.0192	0.9954
0.0026	2.0	1962	0.0172	0.9963
0.0031	3.0	2943	0.0275	0.9945
0.0003	4.0	3924	0.0268	0.9963

Framework versions

• Transformers 4.11.3
• Pytorch 1.10.1
• Datasets 1.17.0
• Tokenizers 0.10.3