<!-- 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-log-rarity-end-20k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.1150
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 |
|---|---|---|---|
| 6.3356 | 0.3 | 500 | 5.3433 |
| 5.0136 | 0.59 | 1000 | 4.9319 |
| 4.6901 | 0.89 | 1500 | 4.6908 |
| 4.4248 | 1.19 | 2000 | 4.5507 |
| 4.2814 | 1.48 | 2500 | 4.4273 |
| 4.1763 | 1.78 | 3000 | 4.3220 |
| 4.051 | 2.08 | 3500 | 4.2604 |
| 3.8807 | 2.37 | 4000 | 4.2115 |
| 3.8476 | 2.67 | 4500 | 4.1556 |
| 3.8146 | 2.97 | 5000 | 4.1014 |
| 3.5937 | 3.26 | 5500 | 4.1008 |
| 3.5681 | 3.56 | 6000 | 4.0690 |
| 3.5565 | 3.86 | 6500 | 4.0366 |
| 3.416 | 4.15 | 7000 | 4.0413 |
| 3.308 | 4.45 | 7500 | 4.0335 |
| 3.2985 | 4.74 | 8000 | 4.0194 |
| 3.2598 | 5.04 | 8500 | 4.0185 |
| 3.1205 | 5.34 | 9000 | 4.0235 |
| 3.1206 | 5.63 | 9500 | 4.0218 |
| 3.1213 | 5.93 | 10000 | 4.0214 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
