metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: google-bert/bert-base-uncased
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: bert-finetuned-spam
results: []
bert-finetuned-spam
This model is a fine-tuned version of google-bert/bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1942
- Accuracy: 0.952
- F1: 0.9502
- Precision: 0.9871
- Recall: 0.916
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: 2.5719605731158755e-06
- train_batch_size: 4
- eval_batch_size: 2
- seed: 19
- 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 | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.2449 | 1.0 | 2250 | 0.2435 | 0.901 | 0.8930 | 0.9718 | 0.826 |
| 0.2545 | 2.0 | 4500 | 0.2138 | 0.937 | 0.9336 | 0.9866 | 0.886 |
| 0.1397 | 3.0 | 6750 | 0.2162 | 0.944 | 0.9413 | 0.9890 | 0.898 |
| 0.1184 | 4.0 | 9000 | 0.2134 | 0.946 | 0.9436 | 0.9869 | 0.904 |
| 0.2056 | 5.0 | 11250 | 0.1942 | 0.952 | 0.9502 | 0.9871 | 0.916 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1