metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: results
results: []
results
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8920
- Accuracy: 0.9210
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: 128
- eval_batch_size: 128
- 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 |
|---|---|---|---|---|
| 5.8623 | 1.0 | 2371 | 5.5613 | 0.5716 |
| 3.9844 | 2.0 | 4742 | 3.8082 | 0.8562 |
| 2.7326 | 3.0 | 7113 | 2.4057 | 0.9110 |
| 1.6646 | 4.0 | 9484 | 1.4718 | 0.9200 |
| 1.0158 | 5.0 | 11855 | 0.8920 | 0.9210 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.3.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2