Noctuaru/tone_berita_p1_v1

results

This model is a fine-tuned version of indobenchmark/indobert-base-p1 on the None dataset. It achieves the following results on the evaluation set:

• Accuracy: 0.8
• F1 Weighted: 0.7958
• Loss: 0.6079

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	0.1239	1.1895
1.0907	2.0	12	0.2	0.1752	1.1029
1.0907	3.0	18	0.52	0.5176	0.9490
0.926	4.0	24	0.68	0.6394	0.7883
0.7014	5.0	30	0.68	0.6753	0.7388
0.7014	6.0	36	0.68	0.6635	0.7300
0.5443	7.0	42	0.72	0.7118	0.7249
0.5443	8.0	48	0.68	0.6623	0.7465
0.4661	9.0	54	0.72	0.7199	0.7159
0.3846	10.0	60	0.68	0.6623	0.6771
0.3846	11.0	66	0.76	0.7579	0.6350
0.3058	12.0	72	0.76	0.7482	0.5970
0.3058	13.0	78	0.76	0.7579	0.6114
0.2568	14.0	84	0.76	0.7482	0.6241
0.2434	15.0	90	0.8	0.7958	0.6079
0.2434	16.0	96	0.76	0.7482	0.6150
0.1961	17.0	102	0.76	0.7482	0.6026

Framework versions

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