reward_model

This model is a fine-tuned version of indobenchmark/indobert-base-p2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6126
• Accuracy: 0.8927
• F1: 0.8906
• Precision: 0.8964
• Recall: 0.8878

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
No log	0.56	50	0.3455	0.8757	0.8736	0.8780	0.8713
No log	1.12	100	0.3013	0.8701	0.8687	0.8692	0.8683
No log	1.69	150	0.3773	0.8644	0.8616	0.8683	0.8588
No log	2.25	200	0.3923	0.8927	0.8906	0.8964	0.8878
No log	2.81	250	0.3634	0.8927	0.8913	0.8931	0.8900
No log	3.37	300	0.4554	0.8983	0.8971	0.8982	0.8963
No log	3.93	350	0.5317	0.8870	0.8851	0.8896	0.8827
No log	4.49	400	0.5834	0.8870	0.8851	0.8896	0.8827

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0