indosum-base-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: 0.6288
• Rouge1: 72.0825
• Rouge2: 64.9891
• Rougel: 69.2273
• Rougelsum: 71.1983
• Gen Len: 98.2637

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
1.1965	1.0	892	0.7377	66.7755	58.7089	63.5735	65.9275	101.1593
0.691	2.0	1784	0.6472	70.9085	63.6467	67.9945	70.0311	100.5703
0.4907	3.0	2676	0.6098	70.4573	63.2612	67.6711	69.6221	96.9545
0.3404	4.0	3568	0.6288	71.5505	64.3094	68.674	70.6452	97.5743
0.2018	5.0	4460	0.6917	70.7161	63.2661	67.7431	69.8153	98.4471

Framework versions

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