SouthMemphis/t5-tiny_for_summarization

This model is a fine-tuned version of google/t5-efficient-tiny on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 4.4877
• Validation Loss: 3.4974
• Train Rouge1: 21.2490
• Train Rouge2: 4.2075
• Train Rougel: 16.9993
• Train Rougelsum: 16.9842
• Train Gen Len: 16.678
• Epoch: 4

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
6.2678	3.9891	17.7562	3.0062	14.6825	14.7004	14.717	0
5.1618	3.7340	19.5200	3.7088	16.1766	16.1763	15.528	1
4.8511	3.6247	20.1377	3.7645	16.1460	16.1223	15.966	2
4.6068	3.5431	20.4053	3.9626	16.3460	16.3444	15.884	3
4.4877	3.4974	21.2490	4.2075	16.9993	16.9842	16.678	4

Framework versions

• Transformers 4.33.1
• TensorFlow 2.15.0-dev20230905
• Datasets 2.14.4
• Tokenizers 0.13.3