IndoBERT-Sentiment-Analysis2

This model is a fine-tuned version of indobenchmark/indobert-base-p1 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3040
• Accuracy: 0.9077
• F1 Score: 0.9075

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: 6
• eval_batch_size: 6
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Score
0.611	0.0960	50	0.6243	0.6769	0.6674
0.6	0.1919	100	0.5416	0.7308	0.7283
0.5393	0.2879	150	0.6418	0.7462	0.7335
0.609	0.3839	200	0.5666	0.7564	0.7443
0.4985	0.4798	250	0.4277	0.8385	0.8363
0.4525	0.5758	300	0.3436	0.8641	0.8635
0.3403	0.6718	350	0.3050	0.8769	0.8768
0.2759	0.7678	400	0.3428	0.8949	0.8948
0.3942	0.8637	450	0.3512	0.9	0.8996
0.4086	0.9597	500	0.3071	0.9128	0.9126

Framework versions

• Transformers 4.53.1
• Pytorch 2.6.0+cu124
• Datasets 2.14.4
• Tokenizers 0.21.2