<!-- 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-TxtToJson-v0.2.0
This model is a fine-tuned version of EleutherAI/gpt-neo-125m on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1651
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: 0.0002
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9487 | 1.0 | 219 | 0.9445 |
| 0.6889 | 2.0 | 438 | 0.6272 |
| 0.3906 | 3.0 | 657 | 0.4168 |
| 0.2992 | 4.0 | 876 | 0.2859 |
| 0.2253 | 5.0 | 1095 | 0.2373 |
| 0.1777 | 6.0 | 1314 | 0.2094 |
| 0.1537 | 7.0 | 1533 | 0.2002 |
| 0.1029 | 8.0 | 1752 | 0.1847 |
| 0.1162 | 9.0 | 1971 | 0.1751 |
| 0.0681 | 10.0 | 2190 | 0.1725 |
| 0.0626 | 11.0 | 2409 | 0.1696 |
| 0.0569 | 12.0 | 2628 | 0.1691 |
| 0.0455 | 13.0 | 2847 | 0.1673 |
| 0.0339 | 14.0 | 3066 | 0.1655 |
| 0.0338 | 15.0 | 3285 | 0.1651 |
Framework versions
- Transformers 4.27.4
- Pytorch 1.13.0
- Datasets 2.1.0
- Tokenizers 0.13.2
