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: 2.4213
• Rouge1: 31.833
• Rouge2: 11.5704
• Rougel: 28.3537
• Rougelsum: 29.7517

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
12.421	1.0	185	4.1761	8.5214	1.3412	8.1063	8.2251
4.6683	2.0	370	2.8343	20.6485	7.1917	18.6741	19.4706
3.6666	3.0	555	2.5616	20.3673	6.1998	18.2531	19.0305
3.3157	4.0	740	2.5002	28.4326	11.0801	25.391	26.4882
3.1834	5.0	925	2.4586	29.0975	11.3058	26.0004	27.5342
3.0983	6.0	1110	2.4191	31.5865	11.3633	27.6063	29.6726
3.0338	7.0	1295	2.4258	31.845	11.9743	28.3534	29.8196
2.9805	8.0	1480	2.4213	31.833	11.5704	28.3537	29.7517

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.0
• Tokenizers 0.15.0