brand-safety-model-final

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

• Loss: 0.4598
• Accuracy: 0.8687

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: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.5747	1.0	117	1.3370	0.7036
0.8113	2.0	234	0.7907	0.8053
0.6805	3.0	351	0.6142	0.8440
0.45	4.0	468	0.5336	0.8634
0.3497	5.0	585	0.4891	0.8644
0.3291	6.0	702	0.4719	0.8650
0.2382	7.0	819	0.4598	0.8687
0.2162	8.0	936	0.4764	0.8666
0.2298	9.0	1053	0.4859	0.8661
0.1703	10.0	1170	0.4737	0.8666
0.1245	11.0	1287	0.4816	0.8677
0.163	12.0	1404	0.4938	0.8666
0.1211	13.0	1521	0.4862	0.8661
0.1067	14.0	1638	0.4977	0.8650
0.1269	15.0	1755	0.4906	0.8677

Framework versions

• Transformers 4.46.3
• Pytorch 2.4.0
• Datasets 2.20.0
• Tokenizers 0.20.3