t5-small-finetuned-cnn-news

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

• Loss: 1.8421
• Rouge1: 24.3896
• Rouge2: 12.1278
• Rougel: 20.4284
• Rougelsum: 23.1568

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
2.0267	1.0	718	1.8134	24.5126	12.0487	20.3865	23.2129
1.8289	2.0	1436	1.8150	24.4837	12.142	20.5671	23.3283
1.6833	3.0	2154	1.8148	23.9291	11.7959	20.0136	22.7257
1.576	4.0	2872	1.8271	24.2228	11.8815	20.2007	22.9745
1.4965	5.0	3590	1.8421	24.3896	12.1278	20.4284	23.1568

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1