mt5-small-finetuned-amazon-en-es

This model is a fine-tuned version of google/mt5-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 3.0296
• Rouge1: 18.0335
• Rouge2: 8.816
• Rougel: 17.5279
• Rougelsum: 17.6189

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
6.9312	1.0	1209	3.2984	14.4268	6.4451	14.0547	14.1363
3.8882	2.0	2418	3.1272	17.1618	8.7776	16.4569	16.5079
3.578	3.0	3627	3.0798	17.9251	9.2806	17.4056	17.3871
3.4191	4.0	4836	3.0671	17.6256	8.8731	16.975	17.0113
3.3193	5.0	6045	3.0605	17.9539	8.7188	17.4034	17.4726
3.2434	6.0	7254	3.0387	17.0668	8.2769	16.5612	16.6636
3.208	7.0	8463	3.0338	17.2954	8.4547	16.7602	16.8175
3.1812	8.0	9672	3.0296	18.0335	8.816	17.5279	17.6189

Framework versions

• Transformers 4.25.1
• Pytorch 1.13.0+cu116
• Datasets 2.7.1
• Tokenizers 0.13.2