Indobert-Sentiment-Analysis-with-Bayes-Optimization

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: 1.3349
• Accuracy: 0.8421052631578947
• F1: 0.8389863547758285

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: 32
• eval_batch_size: 8
• 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: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.5574	1.0	51	0.4374	0.8105	0.8056
0.3411	2.0	102	0.5158	0.7860	0.7709
0.1773	3.0	153	0.5325	0.8035	0.8035
0.1188	4.0	204	0.8542	0.7754	0.7544
0.0695	5.0	255	0.9509	0.7860	0.7897
0.0471	6.0	306	0.8823	0.8070	0.8090
0.0335	7.0	357	0.9724	0.8421	0.8390
0.0198	8.0	408	1.1630	0.8316	0.8272
0.0144	9.0	459	1.1610	0.8211	0.8143
0.0126	10.0	510	1.1930	0.8316	0.8286
0.012	11.0	561	1.3413	0.8175	0.8084
0.0106	12.0	612	1.3336	0.8211	0.8125
0.0171	13.0	663	1.2929	0.8246	0.8184
0.0112	14.0	714	1.3248	0.8211	0.8143
0.0109	15.0	765	1.3349	0.8211	0.8143

Framework versions

• Transformers 4.55.1
• Pytorch 2.6.0+cu124
• Datasets 4.0.0
• Tokenizers 0.21.4