|
--- |
|
license: mit |
|
base_model: DeepESP/gpt2-spanish |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: Martin-Fierro |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# Martin-Fierro |
|
|
|
This model is a fine-tuned version of [DeepESP/gpt2-spanish](https://huggingface.co/DeepESP/gpt2-spanish) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.6687 |
|
|
|
## 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: 15 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 3.9891 | 1.0 | 40 | 3.7897 | |
|
| 3.4333 | 2.0 | 80 | 3.6631 | |
|
| 3.25 | 3.0 | 120 | 3.6085 | |
|
| 3.0732 | 4.0 | 160 | 3.5934 | |
|
| 2.7839 | 5.0 | 200 | 3.5859 | |
|
| 2.7496 | 6.0 | 240 | 3.5977 | |
|
| 2.5405 | 7.0 | 280 | 3.6088 | |
|
| 2.259 | 8.0 | 320 | 3.6209 | |
|
| 2.3266 | 9.0 | 360 | 3.6279 | |
|
| 2.1343 | 10.0 | 400 | 3.6405 | |
|
| 2.1211 | 11.0 | 440 | 3.6489 | |
|
| 1.9877 | 12.0 | 480 | 3.6576 | |
|
| 1.9446 | 13.0 | 520 | 3.6644 | |
|
| 1.9366 | 14.0 | 560 | 3.6667 | |
|
| 1.9959 | 15.0 | 600 | 3.6687 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.1 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.13.3 |
|
|
