arthd24/pegasus_informative_xtreme_tuned_tpuv4-16

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: 1.0464
• Validation Loss: 1.6654
• Epoch: 16

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': 4.35288e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.09475626145662722}
• training_precision: float32

Training results

Train Loss	Validation Loss	Epoch
1.5945	1.8309	0
1.4635	1.7809	1
1.4002	1.7559	2
1.3529	1.7335	3
1.3137	1.7176	4
1.2783	1.7031	5
1.2453	1.6915	6
1.2169	1.6844	7
1.1921	1.6749	8
1.1704	1.6652	9
1.1508	1.6620	10
1.1308	1.6589	11
1.1130	1.6575	12
1.0957	1.6598	13
1.0784	1.6592	14
1.0621	1.6599	15
1.0464	1.6654	16

Framework versions

• Transformers 4.51.3
• TensorFlow 2.16.1
• Datasets 3.5.0
• Tokenizers 0.21.1