liputan6-seq_bn-rf64

This model is a fine-tuned version of LazarusNLP/IndoNanoT5-base on the id_liputan6 canonical dataset. It achieves the following results on the evaluation set:

• Loss: 0.2748
• Rouge1: 43.4905
• Rouge2: 34.6942
• Rougel: 39.8342
• Rougelsum: 42.0699
• Gen Len: 62.292

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
1.1116	1.0	63	0.3953	39.3374	31.1269	36.447	37.9075	49.406
0.5774	2.0	126	0.3309	43.6615	34.9524	40.0101	42.2478	55.7
0.4729	3.0	189	0.2864	41.4092	32.5453	37.9684	39.9099	52.999
0.4209	4.0	252	0.2845	43.3834	34.6436	39.8104	41.9569	56.612
0.3931	5.0	315	0.2748	43.7351	34.936	40.0408	42.3437	58.611

Framework versions

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