distilbert-base-uncased-finetuned_on_hata_dateset

This model is a fine-tuned version of distilbert/distilbert-base-uncased on the hate_speech18 dataset. It achieves the following results on the evaluation set:

• Loss: 1.0451
• Accuracy: 0.9178
• F1: 0.9155
• Recall: 0.9178
• Precision: 0.9138

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: 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	Recall	Precision
0.3342	1.0	268	0.3774	0.8497	0.8702	0.8497	0.9131
0.2411	2.0	536	0.4330	0.9020	0.9097	0.9020	0.9237
0.1374	3.0	804	0.5690	0.8964	0.9050	0.8964	0.9206
0.0804	4.0	1072	1.0798	0.9188	0.9140	0.9188	0.9117
0.0428	5.0	1340	1.0451	0.9178	0.9155	0.9178	0.9138

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1