t5-small-finetuned-cnn-news

This model is a fine-tuned version of t5-small on the cnn_dailymail dataset. It achieves the following results on the evaluation set:

• Loss: 1.8412
• Rouge1: 24.7231
• Rouge2: 12.292
• Rougel: 20.5347
• Rougelsum: 23.4668

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: 0.00056
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
2.0318	1.0	718	1.8028	24.5415	12.0907	20.5343	23.3386
1.8307	2.0	1436	1.8028	24.0965	11.6367	20.2078	22.8138
1.6881	3.0	2154	1.8136	25.0822	12.6509	20.9523	23.8303
1.5778	4.0	2872	1.8269	24.4271	11.8443	20.2281	23.0941
1.501	5.0	3590	1.8412	24.7231	12.292	20.5347	23.4668

Framework versions

• Transformers 4.20.1
• Pytorch 1.12.0+cu113
• Datasets 2.3.2
• Tokenizers 0.12.1