liputan6-pt-pl5

This model is a fine-tuned version of LazarusNLP/IndoNanoT5-base on the id_liputan6 canonical dataset. It achieves the following results on the evaluation set:

• Loss: 3.8205
• Rouge1: 18.3412
• Rouge2: 4.7361
• Rougel: 15.5136
• Rougelsum: 16.6913
• Gen Len: 35.5

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: 0.001
• train_batch_size: 16
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5.0

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
4.799	1.0	63	4.1142	13.0788	2.2394	10.8409	11.8062	40.873
4.179	2.0	126	3.9928	16.7604	3.2541	13.8889	15.1654	32.962
3.9656	3.0	189	3.8832	18.1366	3.9918	15.2392	16.4266	30.549
3.8038	4.0	252	3.8552	18.2504	4.0948	15.4777	16.7374	28.411
3.6617	5.0	315	3.8205	18.6328	4.2703	15.6625	16.9103	30.177

Framework versions

• Transformers 4.40.2
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1