IGustavsen/t5-small-finetuned-english-wikilingua

This model is a fine-tuned version of t5-small, ran 2 epochs on the WikiLingua dataset. It achieves the following results on the evaluation set:

• Train Loss: 2.1459
• Validation Loss: 2.0552
• Train Rouge1: 30.7998
• Train Rouge2: 12.1882
• Train Rougel: 26.4570
• Train Rougelsum: 29.9915
• Train Gen Len: 18.0
• Epoch: 1

Training hyperparameters

The following hyperparameters were used during training:

• optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 1e-04, '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 Rouge1	Train Rouge2	Train Rougel	Train Rougelsum	Train Gen Len	Epoch
2.1459	2.0552	30.7998	12.1882	26.4570	29.9915	18.0	0

Framework versions

• Transformers 4.29.1
• TensorFlow 2.12.0
• Datasets 2.12.0
• Tokenizers 0.13.3