metadata
license: mit
tags:
- generated_from_trainer
model-index:
- name: ds9_all
results: []
ds9_all
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.4600
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: 1.372e-07
- train_batch_size: 1
- eval_batch_size: 1
- seed: 1523398255
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1261 | 13.0 | 8619 | 3.4600 |
| 1.141 | 14.0 | 9282 | 3.4634 |
| 1.1278 | 15.0 | 9945 | 3.4665 |
| 1.1183 | 16.0 | 10608 | 3.4697 |
| 1.1048 | 17.0 | 11271 | 3.4714 |
| 1.1061 | 18.0 | 11934 | 3.4752 |
| 1.1471 | 19.0 | 12597 | 3.4773 |
| 1.1402 | 20.0 | 13260 | 3.4798 |
| 1.0847 | 21.0 | 13923 | 3.4811 |
| 1.1462 | 22.0 | 14586 | 3.4841 |
| 1.1107 | 23.0 | 15249 | 3.4852 |
| 1.1192 | 24.0 | 15912 | 3.4873 |
| 1.0868 | 25.0 | 16575 | 3.4879 |
| 1.1313 | 26.0 | 17238 | 3.4898 |
| 1.1033 | 27.0 | 17901 | 3.4915 |
| 1.1578 | 28.0 | 18564 | 3.4939 |
| 1.0987 | 29.0 | 19227 | 3.4947 |
| 1.0779 | 30.0 | 19890 | 3.4972 |
Framework versions
- Transformers 4.13.0.dev0
- Pytorch 1.10.0+cu113
- Datasets 1.15.1
- Tokenizers 0.10.3