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: 2.8368
• Validation Loss: 2.7589
• Epoch: 19

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
3.6838	3.2453	0
3.4691	3.1443	1
3.3825	3.0814	2
3.3146	3.0386	3
3.2573	2.9959	4
3.2118	2.9596	5
3.1711	2.9370	6
3.1334	2.9129	7
3.1016	2.8917	8
3.0645	2.8773	9
3.0386	2.8628	10
3.0132	2.8475	11
2.9912	2.8321	12
2.9651	2.8218	13
2.9353	2.8102	14
2.9160	2.8004	15
2.8986	2.7861	16
2.8762	2.7746	17
2.8558	2.7692	18
2.8368	2.7589	19

Framework versions

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