GPTNEO_BGL-Anomaly_Baseline
This model is a fine-tuned version of EleutherAI/gpt-neo-1.3B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1131
- Accuracy: 0.9685
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2112 | 1.0 | 2187 | 0.1709 | 0.9428 |
| 0.1562 | 2.0 | 4375 | 0.1386 | 0.9550 |
| 0.1374 | 3.0 | 6562 | 0.1349 | 0.9570 |
| 0.1282 | 4.0 | 8750 | 0.1400 | 0.9582 |
| 0.1262 | 5.0 | 10937 | 0.1283 | 0.9610 |
| 0.1231 | 6.0 | 13125 | 0.1267 | 0.9622 |
| 0.1178 | 7.0 | 15312 | 0.1203 | 0.9634 |
| 0.1203 | 8.0 | 17500 | 0.1193 | 0.9646 |
| 0.1219 | 9.0 | 19687 | 0.1155 | 0.9662 |
| 0.1189 | 10.0 | 21870 | 0.1158 | 0.9662 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3