mlm-20230405-002-3

This model is a fine-tuned version of indobenchmark/indobert-base-p1 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.5498

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	261	4.6412
5.1283	2.0	522	3.9156
5.1283	3.0	783	3.5559
3.6421	4.0	1044	3.2988
3.6421	5.0	1305	3.1616
3.1926	6.0	1566	3.0551
3.1926	7.0	1827	2.9465
2.9067	8.0	2088	2.9188
2.9067	9.0	2349	2.8833
2.7245	10.0	2610	2.7818
2.7245	11.0	2871	2.6725
2.5946	12.0	3132	2.7569
2.5946	13.0	3393	2.6592
2.5204	14.0	3654	2.6180
2.5204	15.0	3915	2.6305
2.4173	16.0	4176	2.6301
2.4173	17.0	4437	2.5706
2.3905	18.0	4698	2.5595
2.3905	19.0	4959	2.5339
2.3455	20.0	5220	2.5753

Framework versions

• Transformers 4.27.4
• Pytorch 2.0.0+cu118
• Datasets 2.11.0
• Tokenizers 0.13.3