fine-tuned-IndoNLI-Augmented-with-indobert-base-uncased

This model is a fine-tuned version of indolem/indobert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.9276
• Accuracy: 0.8014

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: 16
• 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
0.6316	1.0	6298	0.6317	0.7414
0.5501	2.0	12596	0.5378	0.7888
0.4978	3.0	18894	0.5407	0.7948
0.4193	4.0	25192	0.5259	0.8013
0.3766	5.0	31490	0.5447	0.8042
0.328	6.0	37788	0.5820	0.8023
0.2792	7.0	44086	0.6435	0.8012
0.261	8.0	50384	0.6578	0.8008
0.2071	9.0	56682	0.7064	0.8052
0.2004	10.0	62980	0.7446	0.8013
0.1657	11.0	69278	0.7735	0.8044
0.1729	12.0	75576	0.8078	0.8027
0.1399	13.0	81874	0.8660	0.8010
0.132	14.0	88172	0.8871	0.8006
0.1218	15.0	94470	0.9182	0.8001
0.1066	16.0	100768	0.9276	0.8014

Framework versions

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