lm-001

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: 2.6661

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	206	4.9168
No log	2.0	412	4.1508
5.0799	3.0	618	3.7045
5.0799	4.0	824	3.5202
3.5959	5.0	1030	3.3053
3.5959	6.0	1236	3.2019
3.5959	7.0	1442	3.1049
3.1377	8.0	1648	2.9601
3.1377	9.0	1854	2.9142
2.8985	10.0	2060	2.8329
2.8985	11.0	2266	2.8186
2.8985	12.0	2472	2.8022
2.6988	13.0	2678	2.7455
2.6988	14.0	2884	2.7193
2.5927	15.0	3090	2.6942
2.5927	16.0	3296	2.6657
2.5015	17.0	3502	2.6681
2.5015	18.0	3708	2.6694
2.5015	19.0	3914	2.6911
2.4554	20.0	4120	2.6235

Framework versions

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