<!-- 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_AA-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: 0.2073
- Accuracy: 0.9351
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: 10
- total_train_batch_size: 40
- 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 |
|---|---|---|---|---|
| 0.3965 | 1.0 | 651 | 0.3023 | 0.8898 |
| 0.3024 | 2.0 | 1303 | 0.2633 | 0.9132 |
| 0.2785 | 3.0 | 1954 | 0.2429 | 0.9213 |
| 0.241 | 4.0 | 2606 | 0.2293 | 0.9264 |
| 0.2346 | 5.0 | 3257 | 0.2213 | 0.9299 |
| 0.2309 | 6.0 | 3909 | 0.2153 | 0.9309 |
| 0.2226 | 7.0 | 4560 | 0.2117 | 0.9319 |
| 0.2132 | 8.0 | 5212 | 0.2091 | 0.9325 |
| 0.2154 | 9.0 | 5863 | 0.2076 | 0.9330 |
| 0.2106 | 9.99 | 6510 | 0.2069 | 0.9335 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
