LucaReggiani/t5-small-nlpfinalprojectFinal-xsum

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: 3.2016
• Validation Loss: 3.0312
• Train Rouge1: 0.2288
• Train Rouge2: 0.0492
• Train Rougel: 0.1822
• Train Rougelsum: 0.1820
• Train Gen Len: 18.54
• Epoch: 6

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': 3e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.1}
• training_precision: float32

Training results

Train Loss	Validation Loss	Train Rouge1	Train Rouge2	Train Rougel	Train Rougelsum	Train Gen Len	Epoch
3.8756	3.3188	0.2061	0.0431	0.1546	0.1552	18.73	0
3.5085	3.1797	0.2136	0.0476	0.1684	0.1689	18.15	1
3.3992	3.1213	0.2087	0.0436	0.1704	0.1708	18.15	2
3.3368	3.0864	0.2237	0.0497	0.1762	0.1767	18.45	3
3.2760	3.0625	0.2301	0.0509	0.1794	0.1794	18.48	4
3.2278	3.0434	0.2254	0.0476	0.1814	0.1816	18.39	5
3.2016	3.0312	0.2288	0.0492	0.1822	0.1820	18.54	6

Framework versions

• Transformers 4.26.1
• TensorFlow 2.11.0
• Datasets 2.10.1
• Tokenizers 0.13.2