bert-large-uncased-Hate_Offensive_or_Normal_Speech

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

• Loss: 0.0443
• Accuracy: 0.9869
• Weighted f1: 0.9869
• Micro f1: 0.9869
• Macro f1: 0.9863
• Weighted recall: 0.9869
• Micro recall: 0.9869
• Macro recall: 0.9857
• Weighted precision: 0.9869
• Micro precision: 0.9869
• Macro precision: 0.9870

Model description

For more information on how it was created, check out the following link: https://github.com/DunnBC22/NLP_Projects/blob/main/Multiclass%20Classification/Transformer%20Comparison/Hate%20%26%20Offensive%20Speech%20-%20BERT-Large.ipynb

Associated Models

This project is part of a comparison that included the following models:

• https://huggingface.co/DunnBC22/bert-base-uncased-Hate_Offensive_or_Normal_Speech
• https://huggingface.co/DunnBC22/distilbert-base-uncased-Hate_Offensive_or_Normal_Speech
• https://huggingface.co/DunnBC22/fBERT-Hate_Offensive_or_Normal_Speech
• https://huggingface.co/DunnBC22/hateBERT-Hate_Offensive_or_Normal_Speech

Intended uses & limitations

This model is intended to demonstrate my ability to solve a complex problem using technology.

The main limitation is the quality of the data source.

Training and evaluation data

Dataset Source: https://www.kaggle.com/datasets/subhajournal/normal-hate-and-offensive-speeches

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
• 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	Weighted f1	Micro f1	Macro f1	Weighted recall	Micro recall	Macro recall	Weighted precision	Micro precision	Macro precision
0.7991	1.0	39	0.4235	0.7430	0.7100	0.7430	0.6902	0.7430	0.7430	0.7049	0.7782	0.7430	0.7886
0.2156	2.0	78	0.1072	0.9607	0.9605	0.9607	0.9585	0.9607	0.9607	0.9569	0.9607	0.9607	0.9605
0.0518	3.0	117	0.0518	0.9869	0.9869	0.9869	0.9863	0.9869	0.9869	0.9857	0.9869	0.9869	0.9870
0.0242	4.0	156	0.0500	0.9853	0.9852	0.9853	0.9845	0.9853	0.9853	0.9841	0.9853	0.9853	0.9850
0.0163	5.0	195	0.0443	0.9869	0.9869	0.9869	0.9863	0.9869	0.9869	0.9857	0.9869	0.9869	0.9870

Framework versions

• Transformers 4.26.0
• Pytorch 1.12.1
• Datasets 2.8.0
• Tokenizers 0.12.1