Zidan_model_output_v7

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: 0.8382
• Accuracy: 0.6455

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	220	1.0708	0.4727
No log	2.0	440	0.9895	0.5727
1.0281	3.0	660	0.9433	0.6182
1.0281	4.0	880	0.9145	0.6091
0.8506	5.0	1100	0.8845	0.6182
0.8506	6.0	1320	0.8595	0.6455
0.735	7.0	1540	0.8566	0.6455
0.735	8.0	1760	0.8421	0.6455
0.735	9.0	1980	0.8385	0.6545
0.6855	10.0	2200	0.8430	0.6636
0.6855	11.0	2420	0.8426	0.6455
0.6521	12.0	2640	0.8382	0.6455

Framework versions

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