t5-base-finetuned-es-to-pbb

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

• Loss: 1.5858
• Bleu: 0.0069
• Gen Len: 19.0

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: 2e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
No log	1.0	199	2.2691	0.0035	19.0
No log	2.0	398	1.9369	0.0051	19.0
2.5691	3.0	597	1.7988	0.0056	19.0
2.5691	4.0	796	1.7213	0.0051	19.0
2.5691	5.0	995	1.6731	0.0061	19.0
1.9438	6.0	1194	1.6376	0.0063	19.0
1.9438	7.0	1393	1.6128	0.0067	19.0
1.8122	8.0	1592	1.5972	0.0063	19.0
1.8122	9.0	1791	1.5888	0.0064	19.0
1.8122	10.0	1990	1.5858	0.0069	19.0

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.0+cu118
• Datasets 2.11.0
• Tokenizers 0.13.3