indonesia-election-sentiment-classification-finetuned-2

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: 0.8733
• Accuracy: 0.6833
• F1 Weighted: 0.6636

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	13	0.7972	0.6606	0.6205
No log	2.0	26	0.7066	0.6878	0.6463
No log	3.0	39	0.7554	0.6516	0.6125
No log	4.0	52	0.7646	0.6742	0.6339
No log	5.0	65	0.8643	0.6742	0.6401
No log	6.0	78	0.9029	0.6787	0.6560
No log	7.0	91	0.8733	0.6833	0.6636

Framework versions

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