pertama

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

• Loss: 2.4507
• F1 macro: 0.4131
• Weighted: 0.5840
• Balanced accuracy: 0.5423

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: 1e-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: 14

Training results

Training Loss	Epoch	Step	Validation Loss	F1 macro	Weighted	Balanced accuracy
1.3416	1.0	154	1.5603	0.2942	0.3462	0.4357
0.941	2.0	308	1.3408	0.3530	0.5202	0.4807
0.6965	3.0	462	1.3731	0.3747	0.5629	0.5101
0.4375	4.0	616	1.3137	0.3904	0.5961	0.5002
0.2491	5.0	770	1.5577	0.3772	0.5930	0.4978
0.0793	6.0	924	2.1326	0.3923	0.5382	0.5401
0.0488	7.0	1078	2.2000	0.3861	0.5483	0.5243
0.0206	8.0	1232	2.1568	0.3914	0.5873	0.5096
0.0243	9.0	1386	2.2272	0.4118	0.5851	0.5457
0.0126	10.0	1540	2.3494	0.4029	0.5885	0.5346
0.0449	11.0	1694	2.2914	0.4115	0.6037	0.5387
0.0023	12.0	1848	2.5714	0.3962	0.5675	0.5334
0.0023	13.0	2002	2.4491	0.4155	0.5878	0.5400
0.0024	14.0	2156	2.4507	0.4131	0.5840	0.5423

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1