mlm-20230403-001-1

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: 0.7205

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
2.2253	1.0	913	1.6319
1.548	2.0	1826	1.3652
1.3394	3.0	2739	1.2166
1.2098	4.0	3652	1.1025
1.1165	5.0	4565	1.0387
1.0774	6.0	5478	0.9896
1.0021	7.0	6391	0.9372
0.9598	8.0	7304	0.9025
0.9144	9.0	8217	0.8720
0.8858	10.0	9130	0.8518
0.8561	11.0	10043	0.8142
0.8344	12.0	10956	0.8189
0.8102	13.0	11869	0.7833
0.7964	14.0	12782	0.7783
0.7834	15.0	13695	0.7577
0.7483	16.0	14608	0.7441
0.7437	17.0	15521	0.7408
0.7507	18.0	16434	0.7268
0.7382	19.0	17347	0.7223
0.7263	20.0	18260	0.7301

Framework versions

• Transformers 4.27.4
• Pytorch 1.13.1+cu116
• Datasets 2.11.0
• Tokenizers 0.13.2