bert-base-cased-sentweet-profane

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

• Loss: 0.4166
• Accuracy: 0.8194
• Precision: 0.8273
• Recall: 0.8249
• F1: 0.8194

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: 5e-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: 6

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
No log	1.0	81	0.4166	0.8194	0.8273	0.8249	0.8194
No log	2.0	162	0.4605	0.8021	0.8023	0.8038	0.8019
No log	3.0	243	0.4922	0.8021	0.8022	0.7994	0.8003
No log	4.0	324	0.5997	0.7882	0.7871	0.7874	0.7873
No log	5.0	405	0.8504	0.8056	0.8084	0.8090	0.8055
No log	6.0	486	0.9631	0.7951	0.7947	0.7929	0.7936

Framework versions

• Transformers 4.24.0
• Pytorch 1.13.1+cu117
• Datasets 2.6.1
• Tokenizers 0.11.0