GPT2_natural_function_53
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.7165
- Accuracy: 0.3685
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: 0.0001
- train_batch_size: 128
- eval_batch_size: 128
- seed: 53
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10000
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 4.9681 | 1.0 | 6422 | 4.7441 | 0.2809 |
| 4.3361 | 2.0 | 12844 | 4.1924 | 0.3208 |
| 4.0681 | 3.0 | 19266 | 4.0019 | 0.3379 |
| 3.9431 | 4.0 | 25688 | 3.9031 | 0.3468 |
| 3.8435 | 5.0 | 32110 | 3.8400 | 0.3539 |
| 3.7716 | 6.0 | 38532 | 3.7953 | 0.3586 |
| 3.7115 | 7.0 | 44954 | 3.7655 | 0.3618 |
| 3.6569 | 8.0 | 51376 | 3.7415 | 0.3647 |
| 3.6087 | 9.0 | 57798 | 3.7231 | 0.3674 |
| 3.5685 | 10.0 | 64220 | 3.7165 | 0.3685 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.9.1+cu128
- Datasets 4.1.1
- Tokenizers 0.13.3
- Downloads last month
- 22
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support