This model is a fine-tuned version of hiseulgi/stunting-berita-sentiment on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.3918
Accuracy: 0.9542
Precision: 0.9352
Recall: 0.9004
F1: 0.9169

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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.4224	1.0	751	0.2728	0.9442	0.9145	0.8601	0.8826
0.0762	2.0	1502	0.4584	0.9385	0.9547	0.8248	0.8790
0.039	3.0	2253	0.3609	0.9528	0.9566	0.8739	0.9103
0.0075	4.0	3004	0.3227	0.9628	0.9249	0.9471	0.9357
0.0016	5.0	3755	0.3918	0.9542	0.9352	0.9004	0.9169

Framework versions

Transformers 4.41.2
Pytorch 2.1.2
Datasets 2.19.2
Tokenizers 0.19.1