t5-cnn-sum

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

• Loss: 1.7032
• Rouge1: 0.2468
• Rouge2: 0.1177
• Rougel: 0.2041
• Rougelsum: 0.2041
• Gen Len: 18.9985

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.8511	1.0	17945	1.7032	0.2468	0.1177	0.2041	0.2041	18.9985

Framework versions

• Transformers 4.36.2
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.15.0