arthd24/pegasus_regular_10k

This model is a fine-tuned version of thonyyy/pegasus_indonesian_base-finetune on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 1.1703
• Validation Loss: 1.3565
• Train Rouge1: 0.5233
• Train Rouge2: 0.4007
• Train Rougel: 0.5
• Train Rougelsum: 0.5004
• Train Bertscore F1: 0.8078
• Train Gen Len: 18.4204
• Epoch: 3

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:

• optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
• training_precision: float32

Training results

Train Loss	Validation Loss	Train Rouge1	Train Rouge2	Train Rougel	Train Rougelsum	Train Bertscore F1	Train Gen Len	Epoch
1.4043	1.3755	0.5069	0.3815	0.4823	0.4826	0.8022	18.3283	0
1.3111	1.3439	0.5213	0.3949	0.4955	0.4961	0.8071	18.3433	1
1.2374	1.3496	0.5193	0.3965	0.4958	0.496	0.8063	18.4134	2
1.1703	1.3565	0.5233	0.4007	0.5	0.5004	0.8078	18.4204	3

Framework versions

• Transformers 4.46.1
• TensorFlow 2.16.1
• Datasets 3.1.0
• Tokenizers 0.20.0