mt5-small-finetuned-long-sumeczech

This model is a fine-tuned version of google/mt5-small on an unknown dataset. It achieves the following results on the evaluation set: 'eval_loss': 2.8214199542999268, 'eval_rouge1': 12.8674, 'eval_rouge2': 2.6891, 'eval_rougeL': 10.0662, 'eval_rougeLsum': 11.2368

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: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
3.5441	1.0	15064	3.0664	11.0135	1.7163	8.2892	9.7803
3.4047	2.0	30128	2.9725	10.5507	1.8535	8.0843	9.3876
3.2782	3.0	45192	2.9240	10.5563	1.9566	8.1144	9.4192
3.2035	4.0	60256	2.8895	10.5418	2.0105	8.132	9.3701
3.1538	5.0	75320	2.8712	10.6085	1.9954	8.1587	9.4499
3.1197	6.0	90384	2.8562	10.6394	2.0582	8.1855	9.4841
3.0976	7.0	105448	2.8439	10.7537	2.0754	8.2822	9.5754
3.0849	8.0	120512	2.8402	10.751	2.1081	8.2982	9.5911

Framework versions

• Transformers 4.34.1
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1