<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
t5-base-finetuned-es-to-cbv
This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3257
- Bleu: 0.1018
- 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 | 193 | 1.9564 | 0.0086 | 19.0 |
No log | 2.0 | 386 | 1.6338 | 0.0061 | 19.0 |
2.2915 | 3.0 | 579 | 1.5132 | 0.0644 | 19.0 |
2.2915 | 4.0 | 772 | 1.4475 | 0.0934 | 19.0 |
2.2915 | 5.0 | 965 | 1.4026 | 0.0837 | 19.0 |
1.6353 | 6.0 | 1158 | 1.3695 | 0.0936 | 19.0 |
1.6353 | 7.0 | 1351 | 1.3498 | 0.097 | 19.0 |
1.5205 | 8.0 | 1544 | 1.3354 | 0.1012 | 19.0 |
1.5205 | 9.0 | 1737 | 1.3288 | 0.0998 | 19.0 |
1.5205 | 10.0 | 1930 | 1.3257 | 0.1018 | 19.0 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3