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: 2.6764
• Validation Loss: 2.7037
• Epoch: 29

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	Epoch
3.6816	3.2452	0
3.4712	3.1450	1
3.3765	3.0794	2
3.3047	3.0326	3
3.2570	2.9933	4
3.2080	2.9615	5
3.1746	2.9332	6
3.1333	2.9143	7
3.1028	2.8946	8
3.0708	2.8776	9
3.0393	2.8598	10
3.0115	2.8493	11
2.9873	2.8367	12
2.9685	2.8243	13
2.9433	2.8105	14
2.9241	2.7994	15
2.8973	2.7886	16
2.8810	2.7765	17
2.8614	2.7694	18
2.8426	2.7597	19
2.8219	2.7544	20
2.8062	2.7482	21
2.7865	2.7489	22
2.7681	2.7336	23
2.7494	2.7268	24
2.7396	2.7188	25
2.7209	2.7168	26
2.7062	2.7109	27
2.6872	2.7096	28
2.6764	2.7037	29

Framework versions

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