mlm-20230503-indobert-base-p1-combined-001

This model is a fine-tuned version of intanm/mlm-20230416-003-2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.7241

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	284	2.7523
3.086	2.0	568	2.4679
3.086	3.0	852	2.3475
2.4695	4.0	1136	2.2232
2.4695	5.0	1420	2.0961
2.1859	6.0	1704	2.0702
2.1859	7.0	1988	1.9730
2.0172	8.0	2272	1.9398
1.9008	9.0	2556	1.9195
1.9008	10.0	2840	1.8858
1.8025	11.0	3124	1.8617
1.8025	12.0	3408	1.8328
1.7298	13.0	3692	1.7851
1.7298	14.0	3976	1.8226
1.6727	15.0	4260	1.7434
1.6347	16.0	4544	1.7531
1.6347	17.0	4828	1.7514
1.5973	18.0	5112	1.7060
1.5973	19.0	5396	1.7437
1.5732	20.0	5680	1.7242

Framework versions

• Transformers 4.28.1
• Pytorch 2.0.0+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3