Noctuaru/topik_syariah_p2_v3

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:

• Loss: 0.7460
• Accuracy: 0.8261
• F1 Weighted: 0.8246

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: 2.731340121428407e-05
• train_batch_size: 32
• eval_batch_size: 32
• 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: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Weighted
1.0295	1.0	16	0.7273	0.7681	0.7574
0.4548	2.0	32	0.4092	0.8261	0.8301
0.3792	3.0	48	0.3946	0.8551	0.8549
0.266	4.0	64	0.4173	0.8551	0.8527
0.2277	5.0	80	0.3995	0.8696	0.8669
0.1261	6.0	96	0.3956	0.8696	0.8681
0.1185	7.0	112	0.4345	0.8841	0.8825
0.0919	8.0	128	0.5224	0.8406	0.8380
0.0568	9.0	144	0.3773	0.8986	0.9011
0.0418	10.0	160	0.6079	0.8986	0.8952
0.0317	11.0	176	0.6254	0.8551	0.8503
0.0584	12.0	192	0.5806	0.8551	0.8544
0.0304	13.0	208	0.6636	0.8551	0.8510
0.018	14.0	224	0.6549	0.8406	0.8376
0.0022	15.0	240	0.8044	0.8696	0.8609
0.018	16.0	256	0.7892	0.8551	0.8538
0.0264	17.0	272	0.7013	0.8551	0.8475
0.0122	18.0	288	0.7056	0.8261	0.8210
0.0128	19.0	304	0.7460	0.8261	0.8246

Framework versions

• Transformers 4.56.1
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.0