LucaReggiani/t5-small-nlpfinalproject2-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: 3.1399
• Validation Loss: 3.0183
• Train Rouge1: 23.2180
• Train Rouge2: 5.1740
• Train Rougel: 18.3975
• Train Rougelsum: 18.4246
• Train Gen Len: 18.5
• 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': 'Adam', '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.98, 'epsilon': 1e-06, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Validation Loss	Train Rouge1	Train Rouge2	Train Rougel	Train Rougelsum	Train Gen Len	Epoch
3.8670	3.3126	18.0994	2.9443	14.8574	14.8089	18.69	0
3.5043	3.1732	20.2677	3.9191	15.8137	15.8748	18.53	1
3.4010	3.1149	21.9985	4.4897	16.7720	16.8119	18.36	2
3.3235	3.0830	20.6948	3.9055	15.9707	15.9961	18.49	3
3.2700	3.0611	21.2726	3.8497	16.5193	16.5449	18.64	4
3.2309	3.0456	22.2643	4.5285	17.6124	17.6095	18.53	5
3.1842	3.0302	22.3951	4.7814	18.0792	18.0771	18.4	6
3.1399	3.0183	23.2180	5.1740	18.3975	18.4246	18.5	7

Framework versions

• Transformers 4.26.1
• TensorFlow 2.11.0
• Datasets 2.9.0
• Tokenizers 0.13.2