Noctuaru/topik_syariah_p2_v5

results

This model is a fine-tuned version of indobenchmark/indobert-base-p2 on the None dataset. It achieves the following results on the evaluation set:

• Accuracy: 0.8986
• F1 Weighted: 0.8977
• Loss: 0.4283

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: 5.055195102732862e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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	Accuracy	F1 Weighted	Validation Loss
No log	1.0	8	0.7101	0.6329	0.6705
0.8955	2.0	16	0.8551	0.8506	0.4124
0.5084	3.0	24	0.8696	0.8669	0.4549
0.2717	4.0	32	0.8696	0.8670	0.4035
0.2324	5.0	40	0.8116	0.8077	0.5442
0.2324	6.0	48	0.8986	0.8977	0.4283
0.1582	7.0	56	0.8696	0.8666	0.4911
0.1046	8.0	64	0.8696	0.8666	0.5341
0.0789	9.0	72	0.8841	0.8824	0.5235
0.0502	10.0	80	0.8551	0.8538	0.5476
0.0502	11.0	88	0.8696	0.8666	0.6183
0.0497	12.0	96	0.8696	0.8666	0.6125
0.047	13.0	104	0.8696	0.8670	0.6166
0.0243	14.0	112	0.8696	0.8696	0.5814
0.0328	15.0	120	0.8696	0.8696	0.5820

Framework versions

• Transformers 4.56.2
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1