metadata
license: mit
tags:
- generated_from_trainer
base_model: desarrolloasesoreslocales/bert-leg-al-corpus
model-index:
- name: bert-leg-al-corpus
results: []
bert-leg-al-corpus
This model is a fine-tuned version of desarrolloasesoreslocales/bert-leg-al-corpus on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.7132
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: 36
- eval_batch_size: 8
- 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 |
|---|---|---|---|
| No log | 1.0 | 54 | 1.7600 |
| No log | 2.0 | 108 | 1.7598 |
| No log | 3.0 | 162 | 1.7642 |
| No log | 4.0 | 216 | 1.7780 |
| No log | 5.0 | 270 | 1.7340 |
| No log | 6.0 | 324 | 1.7279 |
| No log | 7.0 | 378 | 1.7354 |
| No log | 8.0 | 432 | 1.7241 |
| No log | 9.0 | 486 | 1.7431 |
| 1.8388 | 10.0 | 540 | 1.7157 |
| 1.8388 | 11.0 | 594 | 1.7248 |
| 1.8388 | 12.0 | 648 | 1.7144 |
| 1.8388 | 13.0 | 702 | 1.6979 |
| 1.8388 | 14.0 | 756 | 1.7217 |
| 1.8388 | 15.0 | 810 | 1.7059 |
| 1.8388 | 16.0 | 864 | 1.7506 |
| 1.8388 | 17.0 | 918 | 1.7058 |
| 1.8388 | 18.0 | 972 | 1.6922 |
| 1.7728 | 19.0 | 1026 | 1.6916 |
| 1.7728 | 20.0 | 1080 | 1.7038 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2