<!-- 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. -->
guten-no-merge-rarity
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.0918
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: 0.0005
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.3568 | 0.29 | 500 | 5.3301 |
| 5.0466 | 0.58 | 1000 | 4.9080 |
| 4.73 | 0.87 | 1500 | 4.6682 |
| 4.4679 | 1.16 | 2000 | 4.5283 |
| 4.3158 | 1.45 | 2500 | 4.4125 |
| 4.2188 | 1.74 | 3000 | 4.3088 |
| 4.1156 | 2.03 | 3500 | 4.2357 |
| 3.9133 | 2.31 | 4000 | 4.1932 |
| 3.8904 | 2.6 | 4500 | 4.1438 |
| 3.8544 | 2.89 | 5000 | 4.0942 |
| 3.6874 | 3.18 | 5500 | 4.0860 |
| 3.6165 | 3.47 | 6000 | 4.0586 |
| 3.5896 | 3.76 | 6500 | 4.0289 |
| 3.5354 | 4.05 | 7000 | 4.0195 |
| 3.3403 | 4.34 | 7500 | 4.0222 |
| 3.3454 | 4.63 | 8000 | 4.0074 |
| 3.3303 | 4.92 | 8500 | 3.9963 |
| 3.2093 | 5.21 | 9000 | 4.0075 |
| 3.1655 | 5.5 | 9500 | 4.0067 |
| 3.1652 | 5.79 | 10000 | 4.0057 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
