t5-small-finetuned-tf-xsum

This model was trained from scratch on xsum dataset. It achieves the following results on the evaluation set:

• Train Loss: 2.3494
• Validation Loss: 2.1933
• Train Rouge1: 32.0241
• Train Rouge2: 10.1025
• Train Rougel: 25.8834
• Train Rougelsum: 25.9662
• Train Gen Len: 18.69
• Epoch: 8

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
2.7197	2.4028	29.6376	8.8596	22.8598	22.8401	18.82	1
2.5822	2.3407	30.6849	9.3100	23.8971	23.9096	18.745	2
2.5174	2.2979	32.3706	11.5463	26.4253	26.3525	18.75	3
2.4711	2.2703	32.2768	11.0460	26.2472	26.1540	18.825	4
2.4305	2.2432	29.3935	8.3337	22.2859	22.3557	18.65	5
2.3994	2.2237	31.0993	8.7932	23.6971	23.7702	18.815	6
2.3732	2.2071	31.4819	10.0677	25.1846	25.2829	18.675	7
2.3494	2.1933	32.0241	10.1025	25.8834	25.9662	18.69	8

Framework versions

• Transformers 4.21.1
• TensorFlow 2.8.2
• Datasets 2.4.0
• Tokenizers 0.12.1