metadata
base_model: dccuchile/bert-base-spanish-wwm-uncased
tags:
- generated_from_trainer
model-index:
- name: bert_adaptation_resenas_de_vinos_2023_11_25_15_31
results: []
bert_adaptation_resenas_de_vinos_2023_11_25_15_31
This model is a fine-tuned version of dccuchile/bert-base-spanish-wwm-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.6461
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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.9807 | 1.0 | 250 | 3.0434 |
| 3.0811 | 2.0 | 500 | 3.1461 |
| 2.7704 | 3.0 | 750 | 2.9649 |
| 2.6821 | 4.0 | 1000 | 2.8179 |
| 2.556 | 5.0 | 1250 | 2.6522 |
| 2.3324 | 6.0 | 1500 | 2.7123 |
| 2.3137 | 7.0 | 1750 | 2.5994 |
| 2.2926 | 8.0 | 2000 | 2.6741 |
| 2.1216 | 9.0 | 2250 | 2.6469 |
| 2.0317 | 10.0 | 2500 | 2.6205 |
| 2.0053 | 11.0 | 2750 | 2.4237 |
| 2.0453 | 12.0 | 3000 | 2.5970 |
| 1.9702 | 13.0 | 3250 | 2.4548 |
| 1.9147 | 14.0 | 3500 | 2.4731 |
| 1.9143 | 15.0 | 3750 | 2.4431 |
| 1.7803 | 16.0 | 4000 | 2.4247 |
| 1.7726 | 17.0 | 4250 | 2.5558 |
| 1.7448 | 18.0 | 4500 | 2.5092 |
| 1.7008 | 19.0 | 4750 | 2.4883 |
| 1.769 | 20.0 | 5000 | 2.4471 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0