metadata
license: mit
base_model: astrosbd/fake-reviews-distilbert
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: fake-reviews-distilbert-v3
results: []
fake-reviews-distilbert-v3
This model is a fine-tuned version of astrosbd/fake-reviews-distilbert on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6513
- Accuracy: 0.6304
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: 32
- eval_batch_size: 32
- seed: 42
- 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 |
|---|---|---|---|---|
| No log | 1.0 | 420 | 0.6513 | 0.6304 |
| 0.7036 | 2.0 | 840 | 0.7393 | 0.5944 |
| 0.5522 | 3.0 | 1260 | 0.9045 | 0.5452 |
| 0.4173 | 4.0 | 1680 | 1.2752 | 0.5060 |
| 0.3116 | 5.0 | 2100 | 1.3108 | 0.5445 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.13.2