liputan6-pt-pl50

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: 2.6722
• Rouge1: 35.5686
• Rouge2: 23.5102
• Rougel: 31.8451
• Rougelsum: 33.6584
• Gen Len: 49.748

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
4.2782	1.0	63	3.2600	25.0139	13.1669	22.4852	23.5026	38.037
3.3831	2.0	126	3.0118	28.0005	15.5199	25.1006	26.3175	51.621
3.0732	3.0	189	2.8226	31.6641	18.1569	27.8004	29.8463	51.938
2.83	4.0	252	2.7181	34.3328	21.5065	30.323	32.3623	51.327
2.6441	5.0	315	2.6722	34.8229	22.044	30.8324	33.0138	52.623

Framework versions

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