tawfikgh/t5-small-finetuned-xsum

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: 2.6007
• Train Accuracy: 0.3468
• Validation Loss: 2.4078
• Validation Accuracy: 0.3649
• Train Rouge1: 28.6978
• Train Rouge2: 8.2259
• Train Rougel: 22.5783
• Train Rougelsum: 22.5893
• Train Gen Len: 18.8233
• Epoch: 3

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	Train Accuracy	Validation Loss	Validation Accuracy	Train Rouge1	Train Rouge2	Train Rougel	Train Rougelsum	Train Gen Len	Epoch
2.7567	0.3320	2.5031	0.3547	27.5049	7.3784	21.4250	21.4420	18.8232	0
2.6906	0.3388	2.4626	0.3594	28.0606	7.6834	21.9653	21.9739	18.8168	1
2.6419	0.3436	2.4321	0.3624	28.5598	8.0688	22.3498	22.3559	18.8152	2
2.6007	0.3468	2.4078	0.3649	28.6978	8.2259	22.5783	22.5893	18.8233	3

Framework versions

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