mt5-small-sum-de-en-v1-finetuned-amazon-en-de

This model is a fine-tuned version of deutsche-telekom/mt5-small-sum-de-en-v1 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.5661
• Rouge1: 20.9307
• Rouge2: 12.3388
• Rougel: 20.4694
• Rougelsum: 20.6594

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: 10
• eval_batch_size: 10
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
2.3857	1.0	1041	2.5918	19.0955	10.5762	18.6534	18.707
2.3597	2.0	2082	2.5887	20.2078	11.1543	19.5663	19.7039
2.3623	3.0	3123	2.5802	20.1696	12.0499	19.7038	19.89
2.3815	4.0	4164	2.5498	19.9131	11.5376	19.4158	19.5746
2.3735	5.0	5205	2.5559	20.5713	11.8808	19.9335	20.1211
2.3269	6.0	6246	2.5574	19.8362	11.033	19.3193	19.5623
2.2956	7.0	7287	2.5479	19.8859	11.5389	19.4015	19.7004
2.2646	8.0	8328	2.5669	20.4666	12.2804	20.0291	20.1897
2.2618	9.0	9369	2.5703	20.9783	12.3152	20.445	20.6735
2.236	10.0	10410	2.5661	20.9307	12.3388	20.4694	20.6594

Framework versions

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