Lightscale/aap_summarization_model_3

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

• Train Loss: 3.5410
• Validation Loss: 2.6951
• Train Rouge1: 0.1943
• Train Rouge2: 0.0749
• Train Rougel: 0.1532
• Train Rougelsum: 0.1527
• Train Gen Len: 19.0
• 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
4.4213	3.7473	0.1974	0.0822	0.1557	0.1557	19.0	0
4.2189	3.4754	0.1988	0.0822	0.158	0.1579	19.0	1
3.9742	3.1733	0.1988	0.0822	0.158	0.1579	19.0	2
3.8071	2.9327	0.1916	0.0735	0.1506	0.1501	19.0	3
3.5410	2.6951	0.1943	0.0749	0.1532	0.1527	19.0	4

Framework versions

• Transformers 4.42.4
• TensorFlow 2.17.0
• Datasets 2.20.0
• Tokenizers 0.19.1