tawfikgh/T5-CNN-Daily-Mail-30000

This model is a fine-tuned version of tawfikgh/T5-CNN-Daily-Mail on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 1.9838
• Train Accuracy: 0.4388
• Validation Loss: 1.7669
• Validation Accuracy: 0.4634
• Train Rouge1: 23.0643
• Train Rouge2: 9.2989
• Train Rougel: 18.6586
• Train Rougelsum: 21.4398
• Train F1: 0.9629
• Train Gen Len: 19.0
• Epoch: 0

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': 5e-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	Train Accuracy	Validation Loss	Validation Accuracy	Train Rouge1	Train Rouge2	Train Rougel	Train Rougelsum	Train F1	Train Gen Len	Epoch
1.9838	0.4388	1.7669	0.4634	23.0643	9.2989	18.6586	21.4398	0.9629	19.0	0

Framework versions

• Transformers 4.35.2
• TensorFlow 2.15.0
• Datasets 2.16.1
• Tokenizers 0.15.0