metadata
base_model: DeepESP/gpt2-spanish
library_name: transformers
license: mit
tags:
- generated_from_trainer
model-index:
- name: flisol-cba-martin-fierro
results: []
flisol-cba-martin-fierro
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: 3.9095
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.1028 | 1.0 | 9 | 4.3257 |
| 4.2296 | 2.0 | 18 | 4.1607 |
| 3.983 | 3.0 | 27 | 4.0513 |
| 3.838 | 4.0 | 36 | 3.9989 |
| 3.6462 | 5.0 | 45 | 3.9705 |
| 3.5612 | 6.0 | 54 | 3.9456 |
| 3.432 | 7.0 | 63 | 3.9310 |
| 3.3604 | 8.0 | 72 | 3.9196 |
| 3.2739 | 9.0 | 81 | 3.9135 |
| 3.2296 | 10.0 | 90 | 3.9082 |
| 3.1513 | 11.0 | 99 | 3.9078 |
| 3.0913 | 12.0 | 108 | 3.9057 |
| 3.054 | 13.0 | 117 | 3.9072 |
| 2.9832 | 14.0 | 126 | 3.9052 |
| 2.9653 | 15.0 | 135 | 3.9060 |
| 2.9376 | 16.0 | 144 | 3.9050 |
| 2.9133 | 17.0 | 153 | 3.9070 |
| 2.917 | 18.0 | 162 | 3.9082 |
| 2.8816 | 19.0 | 171 | 3.9093 |
| 2.8821 | 20.0 | 180 | 3.9095 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.3.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.1