|
--- |
|
base_model: dccuchile/albert-base-spanish |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: albert-model-mesa-ayuda |
|
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. --> |
|
|
|
# albert-model-mesa-ayuda |
|
|
|
This model is a fine-tuned version of [dccuchile/albert-base-spanish](https://huggingface.co/dccuchile/albert-base-spanish) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3099 |
|
- Accuracy: 0.9162 |
|
- F1: 0.9148 |
|
- Precision: 0.9156 |
|
- Recall: 0.9162 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 28 |
|
- eval_batch_size: 28 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 0.8309 | 1.0 | 3419 | 0.8166 | 0.7809 | 0.7698 | 0.7813 | 0.7809 | |
|
| 0.4419 | 2.0 | 6838 | 0.4836 | 0.8622 | 0.8571 | 0.8616 | 0.8622 | |
|
| 0.2584 | 3.0 | 10257 | 0.3691 | 0.8913 | 0.8881 | 0.8913 | 0.8913 | |
|
| 0.137 | 4.0 | 13676 | 0.3205 | 0.9093 | 0.9076 | 0.9078 | 0.9093 | |
|
| 0.0609 | 5.0 | 17095 | 0.3099 | 0.9162 | 0.9148 | 0.9156 | 0.9162 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
