t5-small-finetuned-cnn-2

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: 1.6620
• Rouge1: 24.5085
• Rouge2: 11.7925
• Rougel: 20.2631
• Rougelsum: 23.1253
• Gen Len: 18.9996

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: 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: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.8435	1.0	35890	1.6753	24.5387	11.7851	20.2792	23.1595	18.999
1.8143	2.0	71780	1.6660	24.5268	11.7976	20.2699	23.1384	18.9996
1.816	3.0	107670	1.6620	24.5085	11.7925	20.2631	23.1253	18.9996

Framework versions

• Transformers 4.16.2
• Pytorch 1.10.2+cu102
• Datasets 1.18.3
• Tokenizers 0.11.0