Zidan_model_output_v2

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: 0.7630
• Accuracy: 0.6818

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: 8
• 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	220	1.0479	0.5091
No log	2.0	440	0.9568	0.5455
1.0321	3.0	660	0.9094	0.5818
1.0321	4.0	880	0.8748	0.6182
0.8487	5.0	1100	0.8410	0.6182
0.8487	6.0	1320	0.8203	0.6727
0.7405	7.0	1540	0.8106	0.6273
0.7405	8.0	1760	0.7971	0.6636
0.7405	9.0	1980	0.7852	0.6636
0.6747	10.0	2200	0.7788	0.6636
0.6747	11.0	2420	0.7754	0.6455
0.6304	12.0	2640	0.7688	0.6545
0.6304	13.0	2860	0.7656	0.6727
0.6064	14.0	3080	0.7626	0.6727
0.6064	15.0	3300	0.7630	0.6818

Framework versions

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