pokemon_team_BERT
ポケモンのパーティの並びで学習した BERT(Masked Language Model) です。 学習に使ったデータは、自分自身で収集したパーティの並びをシャッフルなどして増やしたものを使用しています。
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4446
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.786 | 1.0 | 1995 | 3.7066 |
| 3.5106 | 2.0 | 3990 | 3.5062 |
| 3.3389 | 3.0 | 5985 | 3.2973 |
| 3.2422 | 4.0 | 7980 | 3.3000 |
| 3.173 | 5.0 | 9975 | nan |
| 3.0516 | 6.0 | 11970 | 3.0902 |
| 2.9928 | 7.0 | 13965 | 3.1138 |
| 2.9509 | 8.0 | 15960 | 3.0007 |
| 2.8988 | 9.0 | 17955 | 3.0047 |
| 2.8105 | 10.0 | 19950 | 2.9341 |
| 2.8212 | 11.0 | 21945 | 2.8955 |
| 2.6472 | 12.0 | 23940 | 2.7615 |
| 2.6196 | 13.0 | 25935 | 2.7013 |
| 2.6267 | 14.0 | 27930 | 2.7081 |
| 2.5083 | 15.0 | 29925 | 2.4976 |
| 2.447 | 16.0 | 31920 | 2.5197 |
| 2.3858 | 17.0 | 33915 | 2.4245 |
| 2.3841 | 18.0 | 35910 | 2.3988 |
| 2.3517 | 19.0 | 37905 | 2.3718 |
| 2.2163 | 20.0 | 39900 | 2.3823 |
| 2.1698 | 21.0 | 41895 | 2.2830 |
| 2.1829 | 22.0 | 43890 | 2.1554 |
| 2.0978 | 23.0 | 45885 | 2.2174 |
| 2.0231 | 24.0 | 47880 | 2.2168 |
| 1.9973 | 25.0 | 49875 | 2.2039 |
| 1.9273 | 26.0 | 51870 | 2.1422 |
| 1.9079 | 27.0 | 53865 | 2.0993 |
| 1.8985 | 28.0 | 55860 | 1.9250 |
| 1.8285 | 29.0 | 57855 | 1.9467 |
| 1.8864 | 30.0 | 59850 | nan |
| 1.7704 | 31.0 | 61845 | 1.8719 |
| 1.7629 | 32.0 | 63840 | 1.8193 |
| 1.6854 | 33.0 | 65835 | 1.8562 |
| 1.6579 | 34.0 | 67830 | 1.7616 |
| 1.5921 | 35.0 | 69825 | 1.7197 |
| 1.637 | 36.0 | 71820 | nan |
| 1.6207 | 37.0 | 73815 | nan |
| 1.6019 | 38.0 | 75810 | 1.6114 |
| 1.5648 | 39.0 | 77805 | nan |
| 1.5385 | 40.0 | 79800 | nan |
| 1.5333 | 41.0 | 81795 | nan |
| 1.5206 | 42.0 | 83790 | 1.6189 |
| 1.4768 | 43.0 | 85785 | 1.5352 |
| 1.4768 | 44.0 | 87780 | 1.5310 |
| 1.5099 | 45.0 | 89775 | 1.5464 |
| 1.455 | 46.0 | 91770 | 1.5714 |
| 1.4361 | 47.0 | 93765 | nan |
| 1.4291 | 48.0 | 95760 | 1.5281 |
| 1.443 | 49.0 | 97755 | 1.5089 |
| 1.4544 | 50.0 | 99750 | nan |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
- Downloads last month
- 0