alk/mt5-small-finetuned-cnn_dailymail-en-es

This model is a fine-tuned version of google/mt5-small on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 1.9490
• Validation Loss: 1.6920
• Epoch: 7

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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5.6e-05, 'decay_steps': 287112, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
• training_precision: float32

Training results

Train Loss	Validation Loss	Epoch
2.9445	1.9068	0
2.2439	1.8106	1
2.1301	1.7582	2
2.0643	1.7378	3
2.0191	1.7181	4
1.9870	1.7033	5
1.9646	1.7015	6
1.9490	1.6920	7

Framework versions

• Transformers 4.18.0
• TensorFlow 2.8.0
• Datasets 2.2.1
• Tokenizers 0.12.1