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: 0.0610
• Accuracy: 0.9853
• Weighted f1: 0.9853
• Weighted recall: 0.9853
• Weighted precision: 0.9854
• Micro f1: 0.9853
• Micro recall: 0.9853
• Micro precision: 0.9853
• Macro f1: 0.9851
• Macro recall: 0.9850
• Macro precision: 0.9853

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: 16
• eval_batch_size: 16
• 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	Weighted recall	Weighted precision	Micro f1	Micro recall	Micro precision	Macro f1	Macro recall	Macro precision
0.2927	1.0	153	0.1163	0.9462	0.9469	0.9462	0.9512	0.9462	0.9462	0.9462	0.9429	0.9472	0.9427
0.066	2.0	306	0.1119	0.9739	0.9739	0.9739	0.9741	0.9739	0.9739	0.9739	0.9729	0.9742	0.9718
0.0267	3.0	459	0.0805	0.9821	0.9821	0.9821	0.9825	0.9821	0.9821	0.9821	0.9804	0.9815	0.9796
0.0209	4.0	612	0.0610	0.9853	0.9853	0.9853	0.9854	0.9853	0.9853	0.9853	0.9851	0.9850	0.9853
0.0097	5.0	765	0.0673	0.9837	0.9836	0.9837	0.9838	0.9837	0.9837	0.9837	0.9832	0.9833	0.9833

Framework versions

• Transformers 4.34.0.dev0
• Pytorch 2.0.1+cu118
• Datasets 2.14.6.dev0
• Tokenizers 0.13.3