indosum-lora-2

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

• Loss: 0.4698
• Rouge1: 73.8688
• Rouge2: 67.6187
• Rougel: 71.1566
• Rougelsum: 73.2002
• Gen Len: 101.4471

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
0.7883	1.0	894	0.5147	70.9781	64.3792	68.0826	70.1936	98.6372
0.6044	2.0	1788	0.4863	72.663	66.2333	69.8132	71.9752	102.0187
0.5609	3.0	2682	0.4760	73.1913	66.8222	70.379	72.525	101.9304
0.5314	4.0	3576	0.4698	73.8131	67.3889	70.9754	73.0829	100.9786
0.5104	5.0	4470	0.4697	73.6281	67.2468	70.8416	72.906	100.8594

Framework versions

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