cv_summarization-t5-small

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

• Train Loss: 0.8053
• Validation Loss: 0.7027
• Train Rougel: tf.Tensor(0.3339088, shape=(), dtype=float32)
• 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': 'Adam', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Validation Loss	Train Rougel	Epoch
1.9068	1.5592	tf.Tensor(0.31806523, shape=(), dtype=float32)	0
1.6027	1.3316	tf.Tensor(0.30698553, shape=(), dtype=float32)	1
1.4177	1.1818	tf.Tensor(0.30701882, shape=(), dtype=float32)	2
1.2744	1.0718	tf.Tensor(0.30627215, shape=(), dtype=float32)	3
1.1618	0.9846	tf.Tensor(0.3005299, shape=(), dtype=float32)	4
1.0575	0.9088	tf.Tensor(0.2958022, shape=(), dtype=float32)	5
0.9764	0.8441	tf.Tensor(0.30608675, shape=(), dtype=float32)	6
0.9196	0.7895	tf.Tensor(0.31722832, shape=(), dtype=float32)	7
0.8478	0.7411	tf.Tensor(0.3254477, shape=(), dtype=float32)	8
0.8053	0.7027	tf.Tensor(0.3339088, shape=(), dtype=float32)	9

Framework versions

• Transformers 4.30.1
• TensorFlow 2.12.0
• Datasets 2.12.0
• Tokenizers 0.13.3