RobCaamano/T5_En_to_Es_Take2

This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.5949
• Validation Loss: 0.5687
• Train Bleu: 18.1264
• Train Gen Len: 53.5263
• Epoch: 8

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': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
• training_precision: float32

Training results

Train Loss	Validation Loss	Train Bleu	Train Gen Len	Epoch
1.0171	0.7827	9.3294	57.7548	0
0.8284	0.7058	12.1991	56.1406	1
0.7588	0.6633	13.9507	55.3832	2
0.7134	0.6363	15.0824	54.9393	3
0.6799	0.6153	16.0321	54.3347	4
0.6529	0.5995	16.6384	54.1043	5
0.6308	0.5862	17.2840	53.9972	6
0.6116	0.5753	17.6554	53.8169	7
0.5949	0.5687	18.1264	53.5263	8

Framework versions

• Transformers 4.35.2
• TensorFlow 2.10.1
• Datasets 2.15.0
• Tokenizers 0.15.0