foxxy-hm/mt5-small-finetuned-wikilingua-en-vi

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: 2.0995
• Validation Loss: 1.7594
• 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': 16208, '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: mixed_float16

Training results

Train Loss	Validation Loss	Epoch
4.4772	2.1093	0
2.8808	1.9781	1
2.5121	1.8920	2
2.3034	1.8253	3
2.1755	1.7736	4
2.1104	1.7594	5
2.0990	1.7594	6
2.0995	1.7594	7

Framework versions

• Transformers 4.27.2
• TensorFlow 2.12.0
• Datasets 2.11.0
• Tokenizers 0.13.3