<!-- 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-open-rarity-all-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: 4.3821
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 |
|---|---|---|---|
| 6.7448 | 0.3 | 500 | 5.6602 |
| 5.394 | 0.61 | 1000 | 5.2370 |
| 5.0391 | 0.91 | 1500 | 4.9974 |
| 4.77 | 1.22 | 2000 | 4.8671 |
| 4.6175 | 1.52 | 2500 | 4.7345 |
| 4.5073 | 1.83 | 3000 | 4.6299 |
| 4.3477 | 2.13 | 3500 | 4.5740 |
| 4.2108 | 2.44 | 4000 | 4.5190 |
| 4.1708 | 2.74 | 4500 | 4.4512 |
| 4.0895 | 3.05 | 5000 | 4.4226 |
| 3.883 | 3.35 | 5500 | 4.4025 |
| 3.873 | 3.66 | 6000 | 4.3664 |
| 3.8532 | 3.96 | 6500 | 4.3286 |
| 3.6257 | 4.27 | 7000 | 4.3401 |
| 3.5945 | 4.57 | 7500 | 4.3264 |
| 3.5796 | 4.88 | 8000 | 4.3114 |
| 3.4673 | 5.18 | 8500 | 4.3227 |
| 3.4 | 5.48 | 9000 | 4.3223 |
| 3.3995 | 5.79 | 9500 | 4.3209 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
