<!-- 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. -->
gmra_model_gpt2-medium_15082023T162956
This model is a fine-tuned version of gpt2-medium on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6457
- Accuracy: 0.9429
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
- 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 |
|---|---|---|---|---|
| 0.5737 | 1.0 | 1137 | 0.3965 | 0.9007 |
| 0.3096 | 2.0 | 2274 | 0.5199 | 0.9192 |
| 0.183 | 3.0 | 3411 | 0.4597 | 0.9367 |
| 0.068 | 4.0 | 4548 | 0.5839 | 0.9332 |
| 0.0344 | 5.0 | 5685 | 0.5424 | 0.9402 |
| 0.021 | 6.0 | 6822 | 0.6616 | 0.9394 |
| 0.0177 | 7.0 | 7959 | 0.6239 | 0.9385 |
| 0.0075 | 8.0 | 9096 | 0.6500 | 0.9411 |
| 0.0035 | 9.0 | 10233 | 0.6396 | 0.9429 |
| 0.0185 | 10.0 | 11370 | 0.6457 | 0.9429 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1
- Datasets 2.14.4
- Tokenizers 0.13.2
