liputan6-lora-16

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: 0.2652
• Rouge1: 43.1279
• Rouge2: 34.4893
• Rougel: 39.464
• Rougelsum: 41.6727
• Gen Len: 58.936

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
1.2779	1.0	63	0.3734	40.6247	32.4945	37.6262	39.2634	52.145
0.533	2.0	126	0.2652	42.9261	34.4419	39.4137	41.4698	53.098
0.4176	3.0	189	0.2285	40.0567	30.7942	36.765	38.66	50.993
0.364	4.0	252	0.2309	42.2149	33.065	38.5226	40.8353	55.49
0.3343	5.0	315	0.2211	41.3186	32.0318	37.7094	39.8931	54.221

Framework versions

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