indosum-pt-pl5-1

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: 1.7699
• Rouge1: 51.7237
• Rouge2: 30.6472
• Rougel: 45.7369
• Rougelsum: 49.7038
• Gen Len: 97.3498

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
3.3389	1.0	892	2.3878	41.0873	18.0223	33.3918	38.3574	94.4633
2.9722	2.0	1784	2.1819	44.6005	22.0442	37.6859	42.2047	101.0441
2.7885	3.0	2676	1.9841	47.1857	25.1724	40.8527	44.8931	94.3178
2.6274	4.0	3568	1.8607	49.3734	27.6939	43.2037	47.044	91.7116
2.4853	5.0	4460	1.7699	51.7237	30.6472	45.7369	49.7038	97.3498

Framework versions

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