mrizalf7/indobert-qa-finetuned-small-squad-indonesian-rizal

indobert-finetuned-small-squad-indonesian-rizal

This model is a fine-tuned version of indolem/indobert-base-uncased on the small-squad indonesian dataset. It achieves the following results on the evaluation set:

• Loss: 2.3344

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.2921	1.0	2700	2.1491
1.0084	2.0	5400	2.1961
0.814	3.0	8100	2.3344

Framework versions

• Transformers 4.25.1
• Pytorch 1.13.0+cu116
• Datasets 2.8.0
• Tokenizers 0.13.2