Noctuaru/tone_berita_large-p2_v1

results

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

• Accuracy: 0.8
• F1 Weighted: 0.7852
• Loss: 0.7316

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: 2.7820079535067715e-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: 17
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Accuracy	F1 Weighted	Validation Loss
No log	1.0	6	0.24	0.1029	1.2189
1.2118	2.0	12	0.32	0.2521	1.1035
1.2118	3.0	18	0.64	0.5214	1.0049
1.0516	4.0	24	0.68	0.6394	0.8500
1.0014	5.0	30	0.64	0.628	0.8799
1.0014	6.0	36	0.68	0.6835	0.7949
1.1235	7.0	42	0.72	0.6931	0.8320
1.1235	8.0	48	0.64	0.6368	0.7677
1.0837	9.0	54	0.8	0.7852	0.7316
0.9824	10.0	60	0.76	0.7324	0.7318
0.9824	11.0	66	0.72	0.6966	0.7191
0.8334	12.0	72	0.76	0.7346	0.7128
0.8334	13.0	78	0.68	0.6430	0.7165
0.7175	14.0	84	0.68	0.6430	0.7259
0.6813	15.0	90	0.68	0.6430	0.7139
0.6813	16.0	96	0.72	0.6981	0.6977
0.6765	17.0	102	0.72	0.6981	0.6941

Framework versions

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