<!-- 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-rarity-log-rarity-mod-2p3k-cut-20k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.1101
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 |
|---|---|---|---|
| 6.355 | 0.29 | 500 | 5.3357 |
| 5.0281 | 0.58 | 1000 | 4.9180 |
| 4.6986 | 0.88 | 1500 | 4.6875 |
| 4.4342 | 1.17 | 2000 | 4.5418 |
| 4.2929 | 1.46 | 2500 | 4.4259 |
| 4.1877 | 1.75 | 3000 | 4.3251 |
| 4.0785 | 2.04 | 3500 | 4.2559 |
| 3.8951 | 2.34 | 4000 | 4.2073 |
| 3.8585 | 2.63 | 4500 | 4.1500 |
| 3.8273 | 2.92 | 5000 | 4.1021 |
| 3.6371 | 3.21 | 5500 | 4.1007 |
| 3.588 | 3.5 | 6000 | 4.0699 |
| 3.5635 | 3.79 | 6500 | 4.0420 |
| 3.4785 | 4.09 | 7000 | 4.0381 |
| 3.3125 | 4.38 | 7500 | 4.0363 |
| 3.3124 | 4.67 | 8000 | 4.0171 |
| 3.2951 | 4.96 | 8500 | 4.0059 |
| 3.1536 | 5.25 | 9000 | 4.0198 |
| 3.137 | 5.55 | 9500 | 4.0185 |
| 3.1266 | 5.84 | 10000 | 4.0176 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
