LucaReggiani/t5-small-nlpfinalproject12_2-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: 3.8830
• Validation Loss: 3.5699
• Train Rouge1: 18.4656
• Train Rouge2: 2.2126
• Train Rougel: 14.7442
• Train Rougelsum: 15.1761
• Train Gen Len: 18.96
• Epoch: 7

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': 'SGD', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 1.9e-05, 'momentum': 0.9, 'nesterov': False}
• training_precision: float32

Training results

Train Loss	Validation Loss	Train Rouge1	Train Rouge2	Train Rougel	Train Rougelsum	Train Gen Len	Epoch
4.3168	4.0297	15.0947	2.1725	12.0181	11.8872	19.0	0
4.1683	3.9156	16.1828	1.9876	12.9115	13.0799	19.0	1
4.0819	3.8338	15.9429	1.9947	13.0026	13.1274	19.0	2
4.0326	3.7649	16.7647	2.5233	13.4735	13.6475	18.96	3
3.9797	3.7033	17.2322	2.6240	13.6267	13.7851	18.95	4
3.9348	3.6524	17.4618	2.0566	13.5028	13.8150	18.98	5
3.8988	3.6090	17.7496	2.1414	13.8788	14.3797	18.98	6
3.8830	3.5699	18.4656	2.2126	14.7442	15.1761	18.96	7

Framework versions

• Transformers 4.26.1
• TensorFlow 2.11.0
• Datasets 2.10.0
• Tokenizers 0.13.2