Zidan_model_output_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: 0.8558
• Accuracy: 0.6364

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
• lr_scheduler_warmup_steps: 100
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	193	1.0399	0.5114
No log	2.0	386	0.9771	0.5758
1.0347	3.0	579	0.9387	0.5947
1.0347	4.0	772	0.8982	0.6136
1.0347	5.0	965	0.8807	0.625
0.848	6.0	1158	0.8706	0.6288
0.848	7.0	1351	0.8641	0.6515
0.7481	8.0	1544	0.8558	0.6364
0.7481	9.0	1737	0.8595	0.6326
0.7481	10.0	1930	0.8559	0.6439

Framework versions

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