metadata
license: apache-2.0
base_model: bert-large-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: results_fold_4
results: []
results_fold_4
This model is a fine-tuned version of bert-large-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2926
- Accuracy: 0.879
- Precision: 0.866
- Recall: 0.899
- F1: 0.882
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.205 | 1.0 | 686 | 0.2434 | 0.9 | 0.882 | 0.913 | 0.897 |
| 0.3799 | 2.0 | 1372 | 0.2525 | 0.895 | 0.867 | 0.922 | 0.894 |
| 0.3218 | 3.0 | 2058 | 0.2512 | 0.898 | 0.912 | 0.87 | 0.891 |
| 0.2818 | 4.0 | 2744 | 0.2460 | 0.903 | 0.898 | 0.899 | 0.899 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.5.1+cu118
- Datasets 2.19.1
- Tokenizers 0.19.1