LazarusNLP/IndoNanoT5-base-IndoSum

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

• Loss: 0.1086
• Rouge1: 0.7529
• Rouge2: 0.7123
• Rougel: 0.733
• Rougelsum: 0.733
• Gen Len: 110.0391

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: 8
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.3004	1.0	1761	0.1682	0.258	0.2277	0.2549	0.255	19.0
0.1463	2.0	3522	0.1318	0.2596	0.2305	0.2563	0.2565	19.0
0.095	3.0	5283	0.1272	0.2602	0.2314	0.2571	0.257	19.0
0.0705	4.0	7044	0.1186	0.2622	0.2338	0.2592	0.2592	19.0
0.0436	5.0	8805	0.1236	0.2625	0.2342	0.2594	0.2596	19.0

Framework versions

• Transformers 4.36.2
• Pytorch 2.2.0+cu118
• Datasets 2.16.1
• Tokenizers 0.15.1