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: 3.6642
• Rouge1: 12.9097
• Rouge2: 3.2756
• Rougel: 12.2885
• Rougelsum: 12.3186

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
No log	1.0	300	5.0305	4.4679	0.4134	4.3487	4.2807
9.3723	2.0	600	3.8535	10.6408	2.6198	10.5538	10.5819
9.3723	3.0	900	3.7590	12.1502	3.3079	12.013	12.1208
4.3429	4.0	1200	3.7019	13.0029	3.7708	12.9759	12.876
4.3429	5.0	1500	3.6782	13.1362	3.0904	12.561	12.5702
4.0043	6.0	1800	3.6698	12.8674	3.8026	12.3664	12.4216
4.0043	7.0	2100	3.6644	12.9581	3.3843	12.407	12.3956
3.872	8.0	2400	3.6642	12.9097	3.2756	12.2885	12.3186

Framework versions

• Transformers 4.21.1
• Pytorch 1.12.0+cu116
• Datasets 2.4.0
• Tokenizers 0.12.1