fine-tuned-IndoNLI-Translated-with-indobert-large-p2

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: 1.6126
• Accuracy: 0.8090

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: 64
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.06
• num_epochs: 16

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.549	1.0	6136	0.5307	0.7896
0.498	2.0	12272	0.4908	0.8072
0.3704	3.0	18408	0.5087	0.8105
0.3102	4.0	24544	0.5708	0.8111
0.2226	5.0	30680	0.6435	0.8053
0.1601	6.0	36816	0.7676	0.8034
0.1133	7.0	42952	0.8197	0.8083
0.1091	8.0	49088	0.9384	0.8059
0.066	9.0	55224	1.0333	0.8066
0.058	10.0	61360	1.1211	0.8061
0.0539	11.0	67496	1.2260	0.8080
0.0357	12.0	73632	1.3470	0.8058
0.0256	13.0	79768	1.4499	0.8079
0.0289	14.0	85904	1.5078	0.8070
0.0259	15.0	92040	1.5818	0.8078
0.0193	16.0	98176	1.6126	0.8090

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu117
• Datasets 2.2.0
• Tokenizers 0.13.2