mt5-small-finetuned-tr-news

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

• Loss: 2.3748
• Rouge1: 25.2124
• Rouge2: 13.3894
• Rougel: 22.4063
• Rougelsum: 22.9668

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
5.5375	1.0	875	2.5866	22.5826	11.7162	19.8221	20.1884
3.3129	2.0	1750	2.5237	23.8445	12.7539	21.3485	21.7204
3.0876	3.0	2625	2.4728	24.1288	12.5373	21.4068	21.8723
2.9685	4.0	3500	2.4348	25.3884	13.3569	22.5336	23.0989
2.8886	5.0	4375	2.4043	25.5798	13.7628	22.7085	23.2025
2.836	6.0	5250	2.3813	24.93	13.2058	22.2455	22.6959
2.8069	7.0	6125	2.3800	24.8104	12.9556	22.1114	22.6108
2.7813	8.0	7000	2.3748	25.2124	13.3894	22.4063	22.9668

Framework versions

• Transformers 4.34.0
• Pytorch 2.1.0+cu121
• Datasets 2.14.5
• Tokenizers 0.14.1