t5-small-finetuned-xsum_epoch4

This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.4245
• Rouge1: 29.5204
• Rouge2: 8.4931
• Rougel: 22.9705
• Rougelsum: 23.0872
• Gen Len: 18.8221

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:

• learning_rate: 2e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
2.7175	1.0	7620	2.4899	28.585	7.7626	22.1314	22.2424	18.8174
2.6605	2.0	15240	2.4486	29.2362	8.2481	22.7049	22.8227	18.8273
2.6368	3.0	22860	2.4303	29.4228	8.4312	22.8991	23.0192	18.8262
2.6284	4.0	30480	2.4245	29.5204	8.4931	22.9705	23.0872	18.8221

Framework versions

• Transformers 4.20.1
• Pytorch 1.11.0
• Datasets 2.1.0
• Tokenizers 0.12.1