results_indobert-large-p2_preprocessing_tuning

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:

• Loss: 1.4637
• Accuracy: 0.4545
• Precision: 0.5084
• Recall: 0.4353
• F1: 0.4145

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: 3.5225350314211635e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Use adafactor and the args are: No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
1.6552	1.0	111	1.5541	0.2545	0.1575	0.2126	0.1676
1.5877	2.0	222	1.5239	0.2977	0.4944	0.2590	0.2152
1.561	3.0	333	1.4980	0.3773	0.4931	0.3403	0.3261
1.5361	4.0	444	1.4807	0.4227	0.4950	0.3978	0.3865
1.5163	5.0	555	1.4637	0.4545	0.5084	0.4353	0.4145
1.496	6.0	666	1.4509	0.4295	0.5107	0.4127	0.3970
1.4931	7.0	777	1.4354	0.4273	0.4916	0.4026	0.3910

Framework versions

• Transformers 4.52.4
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.2