metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: BertALL
results: []
BertALL
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: 0.4052
- Accuracy: 0.8834
- Precision: 0.8107
- Recall: 0.8046
- F1: 0.8040
- Top3: 0.9820
- Top3macro: 0.9594
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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Top3 | Top3macro |
|---|---|---|---|---|---|---|---|---|---|
| 0.5593 | 1.0 | 7566 | 0.5067 | 0.8363 | 0.7252 | 0.6802 | 0.6880 | 0.9642 | 0.9173 |
| 0.3827 | 2.0 | 15132 | 0.4301 | 0.8662 | 0.7785 | 0.7760 | 0.7727 | 0.9766 | 0.9457 |
| 0.2735 | 3.0 | 22698 | 0.4170 | 0.8760 | 0.7973 | 0.7949 | 0.7920 | 0.9816 | 0.9577 |
| 0.2132 | 4.0 | 30264 | 0.4437 | 0.8846 | 0.8048 | 0.8186 | 0.8105 | 0.9828 | 0.9607 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.2.1
- Tokenizers 0.19.1