arthd24/pegasus_informative_canon_hyperparameter_tuned

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: 1.0324
• Validation Loss: 1.2397
• Epoch: 11

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': 7.15031e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.02365212417840069}
• training_precision: float32

Training results

Train Loss	Validation Loss	Epoch
1.5627	1.3677	0
1.4182	1.3199	1
1.3440	1.2872	2
1.2875	1.2683	3
1.2384	1.2499	4
1.1982	1.2424	5
1.1645	1.2335	6
1.1344	1.2335	7
1.1076	1.2298	8
1.0806	1.2320	9
1.0560	1.2341	10
1.0324	1.2397	11

Framework versions

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