metadata
license: mit
tags:
- generated_from_trainer
model-index:
- name: poem-gen-spanish-t5-small
results: []
poem-gen-spanish-t5-small
This model is a fine-tuned version of flax-community/spanish-t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.1909
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: 12
- eval_batch_size: 12
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.5448 | 1.0 | 3347 | 3.4082 |
| 3.4232 | 2.0 | 6694 | 3.3411 |
| 3.3338 | 3.0 | 10041 | 3.2953 |
| 3.2769 | 4.0 | 13388 | 3.2608 |
| 3.2347 | 5.0 | 16735 | 3.2417 |
| 3.1921 | 6.0 | 20082 | 3.2319 |
| 3.1512 | 7.0 | 23429 | 3.2162 |
| 3.1188 | 8.0 | 26776 | 3.2117 |
| 3.1045 | 9.0 | 30123 | 3.2022 |
| 3.0718 | 10.0 | 33470 | 3.1961 |
| 3.0644 | 11.0 | 36817 | 3.1928 |
| 3.0403 | 12.0 | 40164 | 3.1922 |
| 3.0332 | 13.0 | 43511 | 3.1915 |
| 3.0225 | 14.0 | 46858 | 3.1899 |
| 3.0066 | 15.0 | 50205 | 3.1909 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0+cu111
- Datasets 2.0.0
- Tokenizers 0.11.6