mlm-20230503-indobert-base-p2-002

This model is a fine-tuned version of indobenchmark/indobert-base-p2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.9160

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	4.0534
4.7356	2.0	568	3.3071
4.7356	3.0	852	2.9974
3.166	4.0	1136	2.7331
3.166	5.0	1420	2.5351
2.6688	6.0	1704	2.4613
2.6688	7.0	1988	2.3245
2.4034	8.0	2272	2.2535
2.2327	9.0	2556	2.2014
2.2327	10.0	2840	2.1630
2.0986	11.0	3124	2.1237
2.0986	12.0	3408	2.0577
2.0	13.0	3692	2.0044
2.0	14.0	3976	2.0466
1.9237	15.0	4260	1.9496
1.8744	16.0	4544	1.9517
1.8744	17.0	4828	1.9466
1.8342	18.0	5112	1.8942
1.8342	19.0	5396	1.9457
1.7994	20.0	5680	1.9262

Framework versions

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