KenP/mt5-small-finetuned-amazon-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: 4.0378
• Validation Loss: 3.3712
• 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': 9672, '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
9.9112	4.3131	0
5.8947	3.7701	1
5.1149	3.5826	2
4.6940	3.5080	3
4.4064	3.4388	4
4.2301	3.4012	5
4.1037	3.3755	6
4.0378	3.3712	7

Framework versions

• Transformers 4.18.0
• TensorFlow 2.8.0
• Datasets 2.1.0
• Tokenizers 0.12.1