Nohossat/dyu-fr-t5-small

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

• Train Loss: 2.9230
• Validation Loss: 2.8042
• Train Bleu: 1.0521
• Train Gen Len: 17.0863
• Epoch: 9

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
3.1751	2.9401	0.6519	17.6594	0
3.1396	2.9217	0.8306	17.3746	1
3.1072	2.9041	0.9521	17.155	2
3.0776	2.8816	0.8955	17.2039	3
3.0432	2.8647	0.869	16.9266	4
3.0192	2.8487	0.9519	17.3997	5
2.9930	2.8391	0.9774	16.9646	6
2.9699	2.8237	0.8577	17.5139	7
2.9421	2.8129	0.7735	17.0591	8
2.9230	2.8042	1.0521	17.0863	9

Framework versions

• Transformers 4.38.2
• TensorFlow 2.15.0
• Datasets 2.18.0
• Tokenizers 0.15.2