mt5-small-test-amazon-v2

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: 2.0555
• Rouge1: 27.8124
• Rouge2: 15.3682
• Rougel: 27.8646
• Rougelsum: 27.9044

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
6.2982	1.0	1935	2.7890	23.293	12.7229	23.3183	23.3368
2.9801	2.0	3870	2.4341	25.9888	14.0833	26.07	26.0897
2.5025	3.0	5805	2.2611	26.5127	14.5775	26.5105	26.5442
2.2681	4.0	7740	2.1966	27.7476	14.9971	27.835	27.8186
2.1198	5.0	9675	2.1209	27.3796	15.1938	27.4549	27.4759
2.0089	6.0	11610	2.0856	27.6637	15.2345	27.7419	27.7608
1.9416	7.0	13545	2.0637	27.9013	15.3682	27.9621	27.9833
1.9034	8.0	15480	2.0555	27.8124	15.3682	27.8646	27.9044

Framework versions

• Transformers 4.20.0
• Pytorch 1.11.0+cu113
• Datasets 2.3.2
• Tokenizers 0.12.1