MelioAI/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: 2.9407
• Validation Loss: 2.8077
• Epoch: 14

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
3.6834	3.2430	0
3.4664	3.1439	1
3.3758	3.0806	2
3.3119	3.0289	3
3.2570	2.9903	4
3.2105	2.9581	5
3.1684	2.9341	6
3.1278	2.9103	7
3.1003	2.8932	8
3.0670	2.8764	9
3.0360	2.8615	10
3.0159	2.8436	11
2.9895	2.8322	12
2.9633	2.8204	13
2.9407	2.8077	14

Framework versions

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