indobert-squad-qasina-LR-5e-06-BS-16-ML-384 – AI Model by mhdafifan | AlphaNeural AI

You can deploy this model and start earning money today!

mhdafifan/
indobert-squad-qasina-LR-5e-06-BS-16-ML-384

like

0

question-answering

generated_from_trainer

mhdafifan/indobert-squad-id-LR-2e-05-BS-8-ML-384

endpoints_compatible

Views

No views yet

indobert-squad-qasina-LR-5e-06-BS-16-ML-384

This model is a fine-tuned version of mhdafifan/indobert-squad-id-LR-2e-05-BS-8-ML-384 on the QASiNa dataset. It achieves the following results on the evaluation set:

Loss: 2.5573
F1: 54.0207
Exact Match: 45.283

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-06
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.2
num_epochs: 7

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Exact Match
3.0211	1.0	30	2.7692	53.6874	44.3396
2.0406	2.0	60	2.4884	55.006	44.3396
1.8498	3.0	90	2.4717	54.7259	44.3396
1.5152	4.0	120	2.5207	54.6419	45.283
1.4731	5.0	150	2.5573	54.0207	45.283

Framework versions

Transformers 4.57.1
Pytorch 2.9.1+cu128
Datasets 4.4.1
Tokenizers 0.22.1