<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
GPTNEO_Spirit-Anomaly_Baseline
This model is a fine-tuned version of EleutherAI/gpt-neo-1.3B on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0466
- Accuracy: 0.986
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 |
|---|---|---|---|---|
| 0.1261 | 1.0 | 2187 | 0.0865 | 0.9790 |
| 0.0721 | 2.0 | 4375 | 0.0715 | 0.9806 |
| 0.0628 | 3.0 | 6562 | 0.0612 | 0.9810 |
| 0.0539 | 4.0 | 8750 | 0.0577 | 0.9826 |
| 0.0515 | 5.0 | 10937 | 0.0547 | 0.9828 |
| 0.0516 | 6.0 | 13125 | 0.0515 | 0.9832 |
| 0.0471 | 7.0 | 15312 | 0.0493 | 0.9838 |
| 0.0481 | 8.0 | 17500 | 0.0486 | 0.9836 |
| 0.0463 | 9.0 | 19687 | 0.0481 | 0.9838 |
| 0.0441 | 10.0 | 21870 | 0.0483 | 0.9838 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
