liputan6-lora-8

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: 0.2482
• Rouge1: 44.041
• Rouge2: 35.4021
• Rougel: 40.435
• Rougelsum: 42.6248
• Gen Len: 60.602

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
1.4611	1.0	63	0.4168	20.2294	15.1672	18.3462	19.5551	26.342
0.6123	2.0	126	0.3030	42.4943	33.9837	39.042	40.9843	54.709
0.4836	3.0	189	0.2516	39.2983	30.3972	36.1696	37.7681	48.258
0.4256	4.0	252	0.2482	42.8202	33.9496	39.2137	41.343	54.56
0.4014	5.0	315	0.2389	42.5107	33.6017	39.0118	41.0601	55.005

Framework versions

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