arthd24/ext_abs_t5small

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: 3.1939
• Validation Loss: 3.0679
• Train Rouge1: 0.4006
• Train Rouge2: 0.1457
• Train Rougel: 0.2419
• Train Rougelsum: 0.242
• Train Bertscore F1: 0.6168
• Train Gen Len: 240.9263
• 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 Bertscore F1	Train Gen Len	Epoch
3.3096	3.1447	0.3986	0.1493	0.2359	0.2366	0.6148	238.5368	0
3.2719	3.1231	0.3898	0.1414	0.2306	0.231	0.6069	239.7053	1
3.2477	3.0994	0.3885	0.1403	0.2293	0.2293	0.6094	241.9368	2
3.2166	3.0848	0.3972	0.1458	0.234	0.2339	0.6136	239.5474	3
3.1939	3.0679	0.4006	0.1457	0.2419	0.242	0.6168	240.9263	4

Framework versions

• Transformers 4.46.3
• TensorFlow 2.16.1
• Datasets 3.1.0
• Tokenizers 0.20.0