<!-- 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_PKDD-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: 0.5452
- Accuracy: 0.7331
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 |
|---|---|---|---|---|
| 0.6396 | 1.0 | 2187 | 0.5922 | 0.7048 |
| 0.5857 | 2.0 | 4375 | 0.5698 | 0.7138 |
| 0.5682 | 3.0 | 6562 | 0.5585 | 0.7252 |
| 0.5592 | 4.0 | 8750 | 0.5500 | 0.7274 |
| 0.5527 | 5.0 | 10937 | 0.5463 | 0.734 |
| 0.5467 | 6.0 | 13125 | 0.5403 | 0.7342 |
| 0.542 | 7.0 | 15312 | 0.5374 | 0.739 |
| 0.5415 | 8.0 | 17500 | 0.5361 | 0.7382 |
| 0.5388 | 9.0 | 19687 | 0.5342 | 0.7396 |
| 0.5361 | 10.0 | 21870 | 0.5340 | 0.7404 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
