indosum-lora-4

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: 0.4621
• Rouge1: 73.7537
• Rouge2: 67.0657
• Rougel: 71.1377
• Rougelsum: 72.9002
• Gen Len: 101.8929

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
0.7838	1.0	892	0.5145	69.9783	62.8024	67.0786	69.0962	98.8206
0.6031	2.0	1784	0.4936	71.6523	64.7055	68.9409	70.7517	103.1459
0.5579	3.0	2676	0.4722	72.165	65.403	69.5451	71.3208	100.0388
0.5287	4.0	3568	0.4657	73.1062	66.416	70.5428	72.2864	99.8876
0.5074	5.0	4460	0.4621	73.4114	66.7459	70.7702	72.5939	101.6091

Framework versions

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