indonesia-election-sentiment-classification-finetuned-indobertweet-3

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: 1.0145
• Accuracy: 0.7412
• F1 Weighted: 0.7321

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	0.6475	0.7118	0.7159
No log	2.0	76	0.6968	0.7275	0.6896
No log	3.0	114	0.9040	0.7275	0.6895
No log	4.0	152	0.9666	0.7333	0.7069
No log	5.0	190	1.0145	0.7412	0.7321
No log	6.0	228	1.0651	0.7412	0.7292
No log	7.0	266	1.0731	0.7373	0.7273

Framework versions

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