<!-- 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. -->
GPT2_AA-Anomaly_Baseline
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3265
- Accuracy: 0.8856
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 |
---|---|---|---|---|
0.6664 | 1.0 | 651 | 0.4061 | 0.8513 |
0.4037 | 2.0 | 1303 | 0.3675 | 0.8651 |
0.3746 | 3.0 | 1954 | 0.3521 | 0.8706 |
0.3513 | 4.0 | 2606 | 0.3437 | 0.8758 |
0.3477 | 5.0 | 3257 | 0.3371 | 0.8797 |
0.344 | 6.0 | 3909 | 0.3334 | 0.8809 |
0.3322 | 7.0 | 4560 | 0.3302 | 0.8842 |
0.3347 | 8.0 | 5212 | 0.3291 | 0.8842 |
0.3329 | 9.0 | 5863 | 0.3277 | 0.8837 |
0.335 | 9.99 | 6510 | 0.3272 | 0.8840 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3