Noctuaru/topik-syariah-p2

results

This model is a fine-tuned version of indobenchmark/indobert-base-p2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1227
• Accuracy: 0.9649
• Precision: 0.9649
• Recall: 0.9649
• F1: 0.9649

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-06
• 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: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
1.1173	1.0	8	1.0626	0.3509	0.3412	0.3509	0.3384
1.0344	2.0	16	1.1812	0.1930	0.0414	0.1930	0.0681
0.9769	3.0	24	1.1062	0.2807	0.6266	0.2807	0.2029
0.9195	4.0	32	0.9446	0.4561	0.5992	0.4561	0.4418
0.8194	5.0	40	0.8509	0.5439	0.6157	0.5439	0.5253
0.7036	6.0	48	0.6097	0.8246	0.8494	0.8246	0.8165
0.6208	7.0	56	0.5003	0.8947	0.9077	0.8947	0.8973
0.5432	8.0	64	0.4162	0.9298	0.9362	0.9298	0.9314
0.4862	9.0	72	0.3117	0.9649	0.9649	0.9649	0.9649
0.4233	10.0	80	0.2689	0.9649	0.9649	0.9649	0.9649
0.3872	11.0	88	0.2193	0.9649	0.9649	0.9649	0.9649
0.3512	12.0	96	0.1933	0.9649	0.9649	0.9649	0.9649
0.328	13.0	104	0.1725	0.9649	0.9649	0.9649	0.9649
0.2959	14.0	112	0.1629	0.9649	0.9649	0.9649	0.9649
0.2815	15.0	120	0.1454	0.9649	0.9649	0.9649	0.9649
0.2699	16.0	128	0.1428	0.9649	0.9649	0.9649	0.9649
0.2513	17.0	136	0.1379	0.9649	0.9649	0.9649	0.9649
0.241	18.0	144	0.1357	0.9649	0.9649	0.9649	0.9649
0.2402	19.0	152	0.1325	0.9649	0.9649	0.9649	0.9649
0.2264	20.0	160	0.1303	0.9649	0.9649	0.9649	0.9649
0.2246	21.0	168	0.1286	0.9649	0.9649	0.9649	0.9649
0.2234	22.0	176	0.1248	0.9649	0.9649	0.9649	0.9649
0.2146	23.0	184	0.1254	0.9649	0.9649	0.9649	0.9649
0.2042	24.0	192	0.1250	0.9649	0.9649	0.9649	0.9649
0.2145	25.0	200	0.1231	0.9649	0.9649	0.9649	0.9649
0.2015	26.0	208	0.1229	0.9649	0.9649	0.9649	0.9649
0.2065	27.0	216	0.1227	0.9649	0.9649	0.9649	0.9649
0.2021	28.0	224	0.1229	0.9649	0.9649	0.9649	0.9649
0.2002	29.0	232	0.1229	0.9649	0.9649	0.9649	0.9649
0.2085	30.0	240	0.1229	0.9649	0.9649	0.9649	0.9649

Framework versions

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