indonesia-election-topic-classification-undersampling-large-2

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

• Loss: 2.0874
• Balanced Accuracy: 0.6049

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-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 14

Training results

Training Loss	Epoch	Step	Validation Loss	Balanced Accuracy
No log	1.0	187	1.1670	0.4974
No log	2.0	374	1.3128	0.4972
1.0656	3.0	561	1.2442	0.5636
1.0656	4.0	748	1.7556	0.5466
1.0656	5.0	935	1.9800	0.5699
0.3247	6.0	1122	2.0874	0.6049
0.3247	7.0	1309	2.3579	0.5744
0.3247	8.0	1496	2.2183	0.5861
0.0899	9.0	1683	2.2655	0.5765
0.0899	10.0	1870	2.3765	0.5875
0.0534	11.0	2057	2.3331	0.5971
0.0534	12.0	2244	2.4197	0.5922
0.0534	13.0	2431	2.4430	0.5983
0.031	14.0	2618	2.4522	0.5979

Framework versions

• Transformers 4.41.2
• Pytorch 2.1.2
• Datasets 2.19.2
• Tokenizers 0.19.1