Police_classfication

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

• Loss: 0.0030
• Accuracy: 1.0

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: 3e-05
• train_batch_size: 16
• eval_batch_size: 16
• 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: 33
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3787	0.2994	50	0.4338	0.8
0.164	0.5988	100	0.1284	0.9642
0.0763	0.8982	150	0.0832	0.9791
0.07	1.1976	200	0.2192	0.9552
0.0362	1.4970	250	0.1090	0.9761
0.011	1.7964	300	0.2009	0.9642
0.0457	2.0958	350	0.0455	0.9881
0.0803	2.3952	400	0.0758	0.9851
0.0383	2.6946	450	0.1699	0.9672
0.0004	2.9940	500	0.0248	0.9940
0.0005	3.2934	550	0.0192	0.9970
0.0006	3.5928	600	0.0026	1.0
0.04	3.8922	650	0.0030	1.0

Framework versions

• Transformers 4.46.1
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.20.3