results

This model is a fine-tuned version of unitary/toxic-bert on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1722
• Accuracy: 71.6771
• Hamming Loss: 0.0620

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: 0.001
• train_batch_size: 32
• eval_batch_size: 128
• 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
• lr_scheduler_warmup_steps: 500
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Hamming Loss
0.1662	1.0	259	0.2600	19.9613	0.1367
0.1763	2.0	518	0.1722	71.6771	0.0620
0.1825	3.0	777	0.1750	71.6771	0.0620
0.1677	4.0	1036	0.1722	71.6771	0.0620
0.1827	5.0	1295	0.1696	71.6771	0.0620
0.1542	6.0	1554	0.1698	71.6771	0.0620
0.1803	7.0	1813	0.1746	71.6771	0.0620
0.1691	8.0	2072	0.1702	71.6771	0.0620
0.1989	9.0	2331	0.1702	71.6771	0.0620
0.1884	10.0	2590	0.1693	71.6771	0.0620

Framework versions

• Transformers 4.46.3
• Pytorch 2.4.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3