<!-- 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-end-cut-19k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.3128
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 |
|---|---|---|---|
| 6.69 | 0.29 | 500 | 5.6412 |
| 5.3327 | 0.59 | 1000 | 5.2058 |
| 4.9884 | 0.88 | 1500 | 4.9570 |
| 4.7105 | 1.18 | 2000 | 4.8008 |
| 4.5563 | 1.47 | 2500 | 4.6777 |
| 4.4438 | 1.77 | 3000 | 4.5652 |
| 4.3057 | 2.06 | 3500 | 4.4916 |
| 4.1258 | 2.36 | 4000 | 4.4456 |
| 4.1001 | 2.65 | 4500 | 4.3854 |
| 4.0586 | 2.94 | 5000 | 4.3319 |
| 3.8297 | 3.24 | 5500 | 4.3249 |
| 3.8029 | 3.53 | 6000 | 4.2962 |
| 3.7812 | 3.83 | 6500 | 4.2655 |
| 3.6544 | 4.12 | 7000 | 4.2687 |
| 3.5166 | 4.42 | 7500 | 4.2598 |
| 3.4969 | 4.71 | 8000 | 4.2438 |
| 3.4978 | 5.01 | 8500 | 4.2328 |
| 3.3159 | 5.3 | 9000 | 4.2445 |
| 3.3203 | 5.59 | 9500 | 4.2434 |
| 3.3104 | 5.89 | 10000 | 4.2422 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
