Zidan_model_output_v10

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: 0.7422
• Accuracy: 0.7455

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: 1e-06
• 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	1.0211	0.5273
No log	2.0	496	0.9519	0.6727
1.0031	3.0	744	0.8800	0.6545
1.0031	4.0	992	0.8159	0.6909
0.8477	5.0	1240	0.8053	0.6909
0.8477	6.0	1488	0.8047	0.7455
0.7504	7.0	1736	0.7551	0.7455
0.7504	8.0	1984	0.7315	0.7273
0.6811	9.0	2232	0.7451	0.7273
0.6811	10.0	2480	0.7716	0.7273
0.6299	11.0	2728	0.7615	0.7636
0.6299	12.0	2976	0.7530	0.7455
0.5932	13.0	3224	0.7416	0.7455
0.5932	14.0	3472	0.7476	0.7455
0.5699	15.0	3720	0.7422	0.7455

Framework versions

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