mt5-small-finetuned-mlsum

This model is a fine-tuned version of google/mt5-small on the mlsum dataset. It achieves the following results on the evaluation set:

• Loss: 2.1938
• Rouge1: 23.8523
• Rouge2: 11.7959
• Rougel: 21.1838
• Rougelsum: 21.2463

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: 5.6e-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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
5.6087	1.0	1005	2.4269	29.6042	15.5378	25.5964	25.6503
3.4099	2.0	2010	2.2734	23.8963	12.2351	21.4806	21.4861
3.169	3.0	3015	2.2310	26.7408	13.7129	23.7543	23.8443
3.0327	4.0	4020	2.2084	23.2971	11.5675	20.911	21.0564
2.9777	5.0	5025	2.1938	23.8523	11.7959	21.1838	21.2463

Framework versions

• Transformers 4.34.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1