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: 2.5259
• Rouge1: 36.6783
• Rouge2: 8.5304
• Rougel: 26.4419
• Rougelsum: 26.6455

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
3.833	1.0	250	2.6792	31.8471	7.6517	22.5413	22.6222
3.5861	2.0	500	2.6408	36.8204	8.641	26.7687	26.9114
3.411	3.0	750	2.6037	36.2502	7.9975	26.3962	26.502
3.29	4.0	1000	2.5673	36.7784	8.4415	26.7726	26.9248
3.2199	5.0	1250	2.5568	36.8812	8.7419	26.7704	26.8682
3.1628	6.0	1500	2.5280	37.1871	8.8604	26.9372	27.0992
3.1292	7.0	1750	2.5265	36.6801	8.5876	26.4392	26.5908
3.1129	8.0	2000	2.5259	36.6783	8.5304	26.4419	26.6455

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.2
• Tokenizers 0.19.1