t5-base-spanish-yoremnokki-nlpaug-augmented-data

This model is a fine-tuned version of google-t5/t5-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.7798
• Bleu: 7.9993
• Gen Len: 14.7173

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: 1e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
2.7502	0.9996	1231	2.2298	0.2939	14.9914
2.3463	2.0	2463	1.9711	1.8741	14.8172
2.1123	2.9996	3694	1.8500	5.618	14.7577
2.045	4.0	4926	1.7951	7.6976	14.7248
2.0031	4.9980	6155	1.7798	7.9993	14.7173

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.0+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3