firqaaa-indo-sentence-bert-base

This model is a fine-tuned version of firqaaa/indo-sentence-bert-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.4549
• Accuracy: 0.3349

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: 5e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.34	1.0	2857	1.3546	0.3258
1.2482	2.0	5714	1.4019	0.3378
1.1038	3.0	8571	1.4549	0.3349

Framework versions

• Transformers 4.39.0.dev0
• Pytorch 2.2.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.0