Zidan_model_output_v5

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: 0.7981
• Accuracy: 0.6909

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: 12

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	248	1.0235	0.5091
No log	2.0	496	0.9628	0.6545
1.0135	3.0	744	0.9119	0.6545
1.0135	4.0	992	0.8568	0.6545
0.8492	5.0	1240	0.8532	0.6909
0.8492	6.0	1488	0.8556	0.7091
0.7616	7.0	1736	0.8084	0.6909
0.7616	8.0	1984	0.7906	0.7091
0.7031	9.0	2232	0.8081	0.7273
0.7031	10.0	2480	0.8140	0.6909
0.6657	11.0	2728	0.8051	0.7091
0.6657	12.0	2976	0.7981	0.6909

Framework versions

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