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: 3.2409
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: 13
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.5247 | 1.0 | 4016 | 3.4165 |
| 3.4245 | 2.0 | 8032 | 3.3498 |
| 3.3625 | 3.0 | 12048 | 3.3182 |
| 3.3216 | 5.0 | 16735 | 3.3069 |
| 3.3008 | 6.0 | 20082 | 3.2967 |
| 3.2958 | 7.0 | 23429 | 3.2862 |
| 3.2715 | 8.0 | 26776 | 3.2755 |
| 3.2514 | 9.0 | 30123 | 3.2603 |
| 3.2269 | 10.0 | 33470 | 3.2490 |
| 3.2061 | 11.0 | 36817 | 3.2467 |
| 3.19 | 12.0 | 40164 | 3.2412 |
| 3.172 | 13.0 | 43511 | 3.2409 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0+cu111
- Datasets 2.0.0
- Tokenizers 0.11.6