Zidan_model_output_v9

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

• Loss: 1.4760
• Accuracy: 0.8

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	248	0.6499	0.7818
No log	2.0	496	0.8322	0.7818
0.7366	3.0	744	0.7805	0.8
0.7366	4.0	992	1.1599	0.8182
0.4101	5.0	1240	0.8254	0.8727
0.4101	6.0	1488	0.9355	0.8364
0.1646	7.0	1736	0.7034	0.9091
0.1646	8.0	1984	0.8547	0.8545
0.0927	9.0	2232	1.2842	0.8182
0.0927	10.0	2480	1.2158	0.8364
0.0457	11.0	2728	1.2863	0.8182
0.0457	12.0	2976	1.4266	0.8182
0.0383	13.0	3224	1.4670	0.8182
0.0383	14.0	3472	1.4547	0.8182
0.0221	15.0	3720	1.4760	0.8

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1