MT_authorship_att2

This model is a fine-tuned version of ixa-ehu/berteus-base-cased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3781
• Accuracy: 0.8086

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: 2e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 1024
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.5214	0.9994	783	0.4172	0.7824
0.3949	1.9989	1566	0.3966	0.7937
0.3614	2.9996	2350	0.3804	0.8047
0.3315	3.9990	3133	0.3770	0.8071
0.32	4.9972	3915	0.3781	0.8086

Framework versions

• Transformers 4.40.2
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1