vladjr/mt5-small-finetuned-americanas-pt

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: 2.3639
• Validation Loss: 2.2243
• 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': 39624, '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
5.6980	2.8237	0
3.3824	2.5473	1
2.8673	2.3947	2
2.6298	2.3175	3
2.5025	2.2665	4
2.4292	2.2444	5
2.3823	2.2295	6
2.3639	2.2243	7

Framework versions

• Transformers 4.33.1
• TensorFlow 2.12.0
• Datasets 2.14.5
• Tokenizers 0.13.3