This model is a fine-tuned version of bert-base-uncased on the toxic-comment-classification dataset. It achieves the following results on the evaluation set:

Loss: 0.1438
Accuracy: 0.965
Recall: 0.7143
Precision: 0.9375
F1: 0.8108

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: 6e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Recall	Precision	F1
0.2792	1.0	100	0.2226	0.96	0.6190	1.0	0.7647
0.154	2.0	200	0.1438	0.965	0.7143	0.9375	0.8108
0.0488	3.0	300	0.2012	0.965	0.9524	0.7692	0.8511
0.015	4.0	400	0.2588	0.955	0.7143	0.8333	0.7692
0.0035	5.0	500	0.2444	0.965	0.7619	0.8889	0.8205
0.0001	6.0	600	0.2524	0.965	0.7619	0.8889	0.8205
0.0001	7.0	700	0.2580	0.965	0.7619	0.8889	0.8205
0.0001	8.0	800	0.2621	0.965	0.7619	0.8889	0.8205
0.0001	9.0	900	0.2646	0.965	0.7619	0.8889	0.8205
0.0001	10.0	1000	0.2654	0.965	0.7619	0.8889	0.8205

Framework versions

Transformers 4.41.2
Pytorch 2.3.1+cu121
Datasets 2.20.0
Tokenizers 0.19.1

Salmamoori/Bert-finetuned-toxic-comment-classification-v2

Bert-finetuned-toxic-comment-classification-v2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Salmamoori/
Bert-finetuned-toxic-comment-classification-v2