mt5-small-finetuned-amazon-en-de

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: 2.6824
• Rouge1: 16.5188
• Rouge2: 9.9087
• Rougel: 16.3497
• Rougelsum: 16.3207

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: 16
• eval_batch_size: 16
• 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
8.4221	1.0	651	3.1302	13.8418	6.2062	13.6147	13.7041
4.1085	2.0	1302	2.8969	13.842	7.0502	13.6309	13.7681
3.7329	3.0	1953	2.8285	13.4412	6.5045	13.2123	13.1854
3.5489	4.0	2604	2.7547	16.8572	9.781	16.8349	16.8095
3.4223	5.0	3255	2.7334	16.7217	9.9946	16.5297	16.5576
3.3509	6.0	3906	2.6994	16.8925	10.2889	16.7603	16.7358
3.2895	7.0	4557	2.6871	16.4238	9.974	16.3198	16.2857
3.281	8.0	5208	2.6824	16.5188	9.9087	16.3497	16.3207

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0