arthd24/pegasus_base_1

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: 1.2501
• Validation Loss: 1.4153
• Train Rouge1: 0.5105
• Train Rouge2: 0.3781
• Train Rougel: 0.4794
• Train Rougelsum: 0.4798
• Train Gen Len: 18.256
• Epoch: 2

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 Gen Len	Epoch
1.5709	1.4221	0.5051	0.3691	0.4735	0.4739	18.268	0
1.3563	1.3804	0.5077	0.372	0.4766	0.4774	18.11	1
1.2501	1.4153	0.5105	0.3781	0.4794	0.4798	18.256	2

Framework versions

• Transformers 4.45.2
• TensorFlow 2.16.1
• Datasets 3.0.1
• Tokenizers 0.20.0