leonardo-simao/t5-small-finetuned-samsum

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: 1.7827
• Validation Loss: 1.6911
• Train Rouge1: 45.5008
• Train Rouge2: 21.8513
• Train Rougel: 37.7516
• Train Rougelsum: 41.9987
• Train Gen Len: 22.7335
• Epoch: 9

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	Train Rouge1	Train Rouge2	Train Rougel	Train Rougelsum	Train Gen Len	Epoch
2.2008	1.8738	40.8957	17.7161	33.7622	37.8215	21.6076	0
2.0354	1.8199	42.3240	18.8923	35.2173	39.3636	22.6430	1
1.9740	1.7798	43.1803	19.4935	35.5992	39.8421	22.0257	2
1.9317	1.7616	43.6967	19.8639	36.3157	40.3523	22.8240	3
1.8972	1.7465	43.7177	20.1991	36.5373	40.6343	23.4181	4
1.8683	1.7279	44.5495	20.8857	37.0714	41.2688	23.1027	5
1.8467	1.7176	44.6826	20.8768	37.1247	41.2629	23.0770	6
1.8239	1.7093	44.8019	20.9512	37.2078	41.3814	23.4193	7
1.8021	1.7030	45.4762	21.8055	37.9099	41.9938	23.1064	8
1.7827	1.6911	45.5008	21.8513	37.7516	41.9987	22.7335	9

Framework versions

• Transformers 4.27.4
• TensorFlow 2.11.0
• Datasets 2.11.0
• Tokenizers 0.13.3