indonesia-election-topic-classification-undersampling-oversampling

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

• Loss: 1.9939
• Balanced Accuracy: 0.7280

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	208	1.0429	0.6178
No log	2.0	416	0.9754	0.7203
0.991	3.0	624	1.1439	0.7182
0.991	4.0	832	1.5184	0.7269
0.2241	5.0	1040	1.6560	0.7152
0.2241	6.0	1248	1.8570	0.7161
0.2241	7.0	1456	1.9486	0.7197
0.0818	8.0	1664	1.9939	0.7280
0.0818	9.0	1872	2.1012	0.7144
0.0387	10.0	2080	2.0360	0.7202
0.0387	11.0	2288	2.0796	0.7213
0.0387	12.0	2496	2.0755	0.7237
0.0261	13.0	2704	2.1053	0.7187
0.0261	14.0	2912	2.1177	0.7203

Framework versions

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