<!-- 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-all-beg-2k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.1102
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 |
|---|---|---|---|
| 6.3426 | 0.29 | 500 | 5.3274 |
| 5.0324 | 0.58 | 1000 | 4.9260 |
| 4.6993 | 0.87 | 1500 | 4.6864 |
| 4.4502 | 1.16 | 2000 | 4.5472 |
| 4.2923 | 1.46 | 2500 | 4.4266 |
| 4.1942 | 1.75 | 3000 | 4.3316 |
| 4.0805 | 2.04 | 3500 | 4.2580 |
| 3.8935 | 2.33 | 4000 | 4.2106 |
| 3.8692 | 2.62 | 4500 | 4.1596 |
| 3.8293 | 2.91 | 5000 | 4.1045 |
| 3.6476 | 3.2 | 5500 | 4.1007 |
| 3.5807 | 3.49 | 6000 | 4.0724 |
| 3.5708 | 3.79 | 6500 | 4.0417 |
| 3.4841 | 4.08 | 7000 | 4.0366 |
| 3.3149 | 4.37 | 7500 | 4.0339 |
| 3.3066 | 4.66 | 8000 | 4.0201 |
| 3.2999 | 4.95 | 8500 | 4.0077 |
| 3.1606 | 5.24 | 9000 | 4.0194 |
| 3.1239 | 5.53 | 9500 | 4.0194 |
| 3.1318 | 5.82 | 10000 | 4.0182 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
