metadata
library_name: transformers
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: results_bert_full
results: []
results_bert_full
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5038
- Accuracy: 0.876
- F1: 0.8654
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.4682 | 1.0 | 500 | 0.3929 | 0.838 | 0.8325 |
| 0.4017 | 2.0 | 1000 | 0.4347 | 0.833 | 0.7715 |
| 0.3825 | 3.0 | 1500 | 0.6541 | 0.779 | 0.7984 |
| 0.3609 | 4.0 | 2000 | 0.4493 | 0.851 | 0.8484 |
| 0.3404 | 5.0 | 2500 | 0.4276 | 0.843 | 0.7941 |
| 0.3184 | 6.0 | 3000 | 0.3935 | 0.864 | 0.8509 |
| 0.2792 | 7.0 | 3500 | 0.3839 | 0.867 | 0.8519 |
| 0.2919 | 8.0 | 4000 | 0.5530 | 0.855 | 0.8216 |
| 0.2404 | 9.0 | 4500 | 0.5326 | 0.865 | 0.8603 |
| 0.2139 | 10.0 | 5000 | 0.5038 | 0.876 | 0.8654 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0