<!-- 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-norm-rarity-neg-log-rarity-end-19p5k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.1127
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 |
|---|---|---|---|
| 6.337 | 0.29 | 500 | 5.3391 |
| 5.0313 | 0.58 | 1000 | 4.9321 |
| 4.7099 | 0.88 | 1500 | 4.6910 |
| 4.4438 | 1.17 | 2000 | 4.5565 |
| 4.3034 | 1.46 | 2500 | 4.4402 |
| 4.1985 | 1.75 | 3000 | 4.3359 |
| 4.0854 | 2.05 | 3500 | 4.2658 |
| 3.899 | 2.34 | 4000 | 4.2197 |
| 3.8754 | 2.63 | 4500 | 4.1634 |
| 3.8316 | 2.92 | 5000 | 4.1128 |
| 3.6489 | 3.21 | 5500 | 4.1043 |
| 3.5936 | 3.51 | 6000 | 4.0788 |
| 3.5707 | 3.8 | 6500 | 4.0499 |
| 3.4804 | 4.09 | 7000 | 4.0419 |
| 3.3223 | 4.38 | 7500 | 4.0333 |
| 3.3179 | 4.68 | 8000 | 4.0236 |
| 3.308 | 4.97 | 8500 | 4.0107 |
| 3.157 | 5.26 | 9000 | 4.0223 |
| 3.1406 | 5.55 | 9500 | 4.0212 |
| 3.1361 | 5.84 | 10000 | 4.0201 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
