_cleaned_bbc_news_summary_model

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

• Loss: 0.6223
• Rouge1: 0.2173
• Rouge2: 0.17
• Rougel: 0.2036
• Rougelsum: 0.2035
• Gen Len: 18.9708

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: 0.002
• 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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	223	0.7067	0.2044	0.1531	0.1906	0.1905	18.982
No log	2.0	446	0.6486	0.2144	0.1622	0.1984	0.1987	18.9775
0.7499	3.0	669	0.6229	0.2183	0.1684	0.2038	0.2038	18.9955
0.7499	4.0	892	0.6226	0.2174	0.1672	0.2023	0.2023	18.9528
0.476	5.0	1115	0.6223	0.2173	0.17	0.2036	0.2035	18.9708

Framework versions

• Transformers 4.27.4
• Pytorch 2.0.0+cu118
• Datasets 2.11.0
• Tokenizers 0.13.3