indonesia-election-sentiment-classification-finetuned-roberta-1

This model is a fine-tuned version of w11wo/indonesian-roberta-base-sentiment-classifier on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.2566
• Accuracy: 0.5565
• F1 Weighted: 0.5613

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: 7

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Weighted
No log	1.0	38	0.9822	0.4859	0.4578
No log	2.0	76	1.3101	0.5040	0.4872
No log	3.0	114	1.3172	0.5504	0.5300
No log	4.0	152	1.8168	0.5222	0.5283
No log	5.0	190	2.0302	0.5524	0.5515
No log	6.0	228	2.2566	0.5565	0.5613
No log	7.0	266	2.2423	0.5585	0.5607

Framework versions

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