Zidan_model_output_v12

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: 0.7765
• Accuracy: 0.7

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: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	220	1.0495	0.4545
No log	2.0	440	0.9717	0.5455
1.0123	3.0	660	0.9364	0.5455
1.0123	4.0	880	0.9131	0.6091
0.8474	5.0	1100	0.8749	0.6182
0.8474	6.0	1320	0.8536	0.6182
0.7489	7.0	1540	0.8442	0.6364
0.7489	8.0	1760	0.8273	0.6545
0.7489	9.0	1980	0.8097	0.6636
0.6829	10.0	2200	0.8013	0.6455
0.6829	11.0	2420	0.7983	0.6636
0.6301	12.0	2640	0.7850	0.6818
0.6301	13.0	2860	0.7800	0.6909
0.6057	14.0	3080	0.7774	0.6909
0.6057	15.0	3300	0.7765	0.7

Framework versions

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