|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: ds9_all |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# ds9_all |
|
|
|
This model is a fine-tuned version of [gpt2](https://huggingface.co/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 |
|
|
