sentiment_model

This model is a fine-tuned version of indobenchmark/indobert-base-p2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1665
• Accuracy: 0.9720
• F1: 0.9259
• Precision: 0.9615
• Recall: 0.8929

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
No log	1.0	72	0.2060	0.9510	0.8727	0.8889	0.8571
No log	2.0	144	0.2337	0.9580	0.8846	0.9583	0.8214
No log	3.0	216	0.2416	0.9441	0.8571	0.8571	0.8571
No log	4.0	288	0.1905	0.9580	0.8846	0.9583	0.8214
No log	5.0	360	0.2029	0.9580	0.8929	0.8929	0.8929
No log	6.0	432	0.1665	0.9720	0.9259	0.9615	0.8929
0.0706	7.0	504	0.1899	0.9580	0.8889	0.9231	0.8571
0.0706	8.0	576	0.1990	0.9580	0.8889	0.9231	0.8571
0.0706	9.0	648	0.2139	0.9580	0.8889	0.9231	0.8571
0.0706	10.0	720	0.2171	0.9580	0.8889	0.9231	0.8571

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0