<!-- 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. -->
aochildes-norm-rarity-log-rarity-no-cut
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.1177
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 |
|---|---|---|---|
| 6.3587 | 0.29 | 500 | 5.3374 |
| 5.0473 | 0.59 | 1000 | 4.9329 |
| 4.7166 | 0.88 | 1500 | 4.6905 |
| 4.4468 | 1.17 | 2000 | 4.5469 |
| 4.2996 | 1.47 | 2500 | 4.4324 |
| 4.2018 | 1.76 | 3000 | 4.3343 |
| 4.0845 | 2.05 | 3500 | 4.2599 |
| 3.9014 | 2.34 | 4000 | 4.2138 |
| 3.8737 | 2.64 | 4500 | 4.1624 |
| 3.8298 | 2.93 | 5000 | 4.1071 |
| 3.6371 | 3.22 | 5500 | 4.1078 |
| 3.5947 | 3.52 | 6000 | 4.0806 |
| 3.5728 | 3.81 | 6500 | 4.0497 |
| 3.467 | 4.1 | 7000 | 4.0487 |
| 3.3191 | 4.4 | 7500 | 4.0431 |
| 3.318 | 4.69 | 8000 | 4.0308 |
| 3.3039 | 4.98 | 8500 | 4.0207 |
| 3.1482 | 5.28 | 9000 | 4.0361 |
| 3.1394 | 5.57 | 9500 | 4.0345 |
| 3.1279 | 5.86 | 10000 | 4.0337 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
