<!-- 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. -->
gpt2-concat-guten-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: 4.3296
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 |
|---|---|---|---|
| 6.6869 | 0.29 | 500 | 5.6385 |
| 5.3235 | 0.59 | 1000 | 5.2015 |
| 4.9865 | 0.88 | 1500 | 4.9498 |
| 4.7068 | 1.18 | 2000 | 4.8080 |
| 4.5674 | 1.47 | 2500 | 4.6941 |
| 4.4601 | 1.76 | 3000 | 4.5872 |
| 4.3293 | 2.06 | 3500 | 4.5155 |
| 4.1497 | 2.35 | 4000 | 4.4676 |
| 4.1182 | 2.64 | 4500 | 4.4072 |
| 4.0826 | 2.94 | 5000 | 4.3514 |
| 3.8664 | 3.23 | 5500 | 4.3488 |
| 3.8272 | 3.53 | 6000 | 4.3168 |
| 3.8034 | 3.82 | 6500 | 4.2843 |
| 3.6795 | 4.11 | 7000 | 4.2836 |
| 3.5333 | 4.41 | 7500 | 4.2764 |
| 3.534 | 4.7 | 8000 | 4.2603 |
| 3.5182 | 4.99 | 8500 | 4.2478 |
| 3.3437 | 5.29 | 9000 | 4.2620 |
| 3.3384 | 5.58 | 9500 | 4.2601 |
| 3.3385 | 5.88 | 10000 | 4.2595 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
