Zidan_model_output_80_10_10_v3

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: 1.6777
• 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: 2e-05
• train_batch_size: 4
• eval_batch_size: 8
• 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	220	0.6662	0.7636
No log	2.0	440	0.6709	0.7545
0.6918	3.0	660	0.9846	0.7545
0.6918	4.0	880	1.1782	0.7364
0.277	5.0	1100	1.5201	0.7455
0.277	6.0	1320	1.5724	0.7364
0.0809	7.0	1540	1.5310	0.7364
0.0809	8.0	1760	1.6199	0.7455
0.0809	9.0	1980	1.6281	0.7545
0.0375	10.0	2200	1.5576	0.7545
0.0375	11.0	2420	1.6472	0.7455
0.0223	12.0	2640	1.6777	0.7455

Framework versions

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