metadata
base_model: dccuchile/distilbert-base-spanish-uncased
tags:
- generated_from_trainer
model-index:
- name: distilbert-base-spanish-uncased-2023-11-13-18-01
results: []
distilbert-base-spanish-uncased-2023-11-13-18-01
This model is a fine-tuned version of dccuchile/distilbert-base-spanish-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3884
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: 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.5316 | 0.59 | 500 | 2.2591 |
| 2.2197 | 1.19 | 1000 | 1.9800 |
| 2.0108 | 1.78 | 1500 | 1.8304 |
| 1.855 | 2.38 | 2000 | 1.7229 |
| 1.7933 | 2.97 | 2500 | 1.6561 |
| 1.7466 | 3.56 | 3000 | 1.6101 |
| 1.6906 | 4.16 | 3500 | 1.5588 |
| 1.6301 | 4.75 | 4000 | 1.5264 |
| 1.6131 | 5.34 | 4500 | 1.4893 |
| 1.5731 | 5.94 | 5000 | 1.4626 |
| 1.5248 | 6.53 | 5500 | 1.4445 |
| 1.509 | 7.13 | 6000 | 1.4274 |
| 1.5083 | 7.72 | 6500 | 1.4109 |
| 1.5277 | 8.31 | 7000 | 1.4051 |
| 1.4884 | 8.91 | 7500 | 1.3872 |
| 1.496 | 9.5 | 8000 | 1.3912 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1