metadata
license: mit
base_model: DeepESP/gpt2-spanish
tags:
- generated_from_trainer
model-index:
- name: peppa_pig
results: []
peppa_pig
This model is a fine-tuned version of DeepESP/gpt2-spanish on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.3870
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.6125 | 1.0 | 28 | 2.6842 |
| 2.3335 | 2.0 | 56 | 2.5216 |
| 2.1436 | 3.0 | 84 | 2.4615 |
| 1.9946 | 4.0 | 112 | 2.4247 |
| 1.9846 | 5.0 | 140 | 2.4094 |
| 1.8404 | 6.0 | 168 | 2.3987 |
| 1.7489 | 7.0 | 196 | 2.3924 |
| 1.7656 | 8.0 | 224 | 2.3894 |
| 1.744 | 9.0 | 252 | 2.3880 |
| 1.6455 | 10.0 | 280 | 2.3870 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Tokenizers 0.13.3