mt5-small-finetuned-amazon-en-es

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: 2.5792
• Rouge1: 19.178
• Rouge2: 11.1294
• Rougel: 18.8056
• Rougelsum: 18.8857

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
3.1482	1.0	1301	2.6708	17.2978	11.0922	17.1791	17.1414
2.867	2.0	2602	2.6532	17.7932	10.2988	17.6139	17.6418
2.74	3.0	3903	2.6575	19.2584	11.6796	18.98	19.0057
3.0353	4.0	5204	2.5845	19.1599	11.2723	18.8132	18.8559
2.9691	5.0	6505	2.5820	18.2435	9.5271	17.904	17.9735
2.9221	6.0	7806	2.5784	18.5969	10.5778	18.2837	18.2395
2.8944	7.0	9107	2.5738	18.6871	10.6402	18.4386	18.4199
2.8636	8.0	10408	2.5792	19.178	11.1294	18.8056	18.8857

Framework versions

• Transformers 4.34.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1