<!-- 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_CSIC-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: 0.6128
- Accuracy: 0.6647
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 10
- total_train_batch_size: 80
- 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 |
---|---|---|---|---|
0.7143 | 1.0 | 437 | 0.7182 | 0.4122 |
0.6603 | 2.0 | 875 | 0.6668 | 0.6196 |
0.6439 | 3.0 | 1312 | 0.6421 | 0.6738 |
0.6327 | 4.0 | 1750 | 0.6301 | 0.6722 |
0.6279 | 5.0 | 2187 | 0.6215 | 0.6672 |
0.6231 | 6.0 | 2625 | 0.6159 | 0.6658 |
0.6203 | 7.0 | 3062 | 0.6137 | 0.6652 |
0.6166 | 8.0 | 3500 | 0.6105 | 0.6634 |
0.6183 | 9.0 | 3937 | 0.6102 | 0.6642 |
0.615 | 9.99 | 4370 | 0.6096 | 0.6634 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3