t5-small-indonesian-summarization

This model is a fine-tuned version of panggi/t5-small-indonesian-summarization-cased on the id_liputan6 dataset. It achieves the following results on the evaluation set:

• Loss: 2.4782

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.0195	0.4126	5000	2.6803
1.9432	0.8252	10000	2.6026
1.9104	1.2378	15000	2.5520
1.8733	1.6504	20000	2.5069
1.8138	2.0630	25000	2.4988
1.805	2.4757	30000	2.4878
1.8078	2.8883	35000	2.4782

Framework versions

• Transformers 4.52.4
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1