IndobertTopicClassify02

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

• Loss: 0.7167
• Accuracy: 0.8175

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: 6
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	100	2.0074	0.4875
No log	2.0	200	1.1501	0.6975
No log	3.0	300	0.8570	0.7825
No log	4.0	400	0.7629	0.8075
1.195	5.0	500	0.7194	0.8175
1.195	6.0	600	0.7167	0.8175

Framework versions

• Transformers 4.28.0
• Pytorch 2.1.0+cu121
• Datasets 2.15.0
• Tokenizers 0.13.3