metadata
license: apache-2.0
base_model: google-bert/bert-base-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: test_trainer
results: []
test_trainer
This model is a fine-tuned version of google-bert/bert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5712
- Precision: 0.8669
- Recall: 0.8669
- F1: 0.8669
- Accuracy: 0.8669
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.7396 | 1.0 | 7500 | 0.6680 | 0.8223 | 0.8223 | 0.8223 | 0.8223 |
| 0.4939 | 2.0 | 15000 | 0.5864 | 0.8515 | 0.8515 | 0.8515 | 0.8515 |
| 0.3209 | 3.0 | 22500 | 0.5712 | 0.8669 | 0.8669 | 0.8669 | 0.8669 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1