This model is a fine-tuned version of muchad/idt5-base on on translated Indonesian SQUAD dataset.
It achieves the following results on the evaluation set:
Exact: 49.19
F1: 67.36
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
learning_rate: 0.0001
train_batch_size: 4
eval_batch_size: 64
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
