malay_classification

This model is a fine-tuned version of rmtariq/malay_classification on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0001
• Accuracy: 1.0
• F1: 1.0
• Precision: 1.0
• Recall: 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: 5e-05
• train_batch_size: 8
• 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: 500
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.1691	0.2720	500	0.1373	0.9717	0.9717	0.9730	0.9717
0.0493	0.5441	1000	0.0369	0.9943	0.9943	0.9945	0.9943
0.0669	0.8161	1500	0.0406	0.9952	0.9952	0.9954	0.9952
0.0287	1.0881	2000	0.0276	0.9943	0.9944	0.9948	0.9943
0.0061	1.3602	2500	0.0168	0.9971	0.9971	0.9972	0.9971
0.0137	1.6322	3000	0.0128	0.9981	0.9981	0.9981	0.9981
0.0178	1.9042	3500	0.0179	0.9968	0.9968	0.9969	0.9968
0.0112	2.1763	4000	0.0110	0.9975	0.9975	0.9975	0.9975
0.0001	2.4483	4500	0.0079	0.9987	0.9987	0.9988	0.9987
0.0001	2.7203	5000	0.0021	0.9987	0.9987	0.9987	0.9987
0.0003	2.9924	5500	0.0024	0.9990	0.9990	0.9991	0.9990

Framework versions

• Transformers 4.53.1
• Pytorch 2.7.1
• Datasets 3.6.0
• Tokenizers 0.21.2