soduhh/mt5-small-finetuned-amazon-en-fr

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: 3.9132
• Validation Loss: 3.2661
• 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': 11184, '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
9.1676	4.1323	0
5.6798	3.6659	1
4.9731	3.5322	2
4.5665	3.4177	3
4.2967	3.3513	4
4.1126	3.3000	5
3.9828	3.2671	6
3.9132	3.2661	7

Framework versions

• Transformers 4.30.2
• TensorFlow 2.12.0
• Datasets 2.13.1
• Tokenizers 0.13.3