<!-- 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-aochildes-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: 4.3245
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 |
|---|---|---|---|
| 6.7129 | 0.29 | 500 | 5.6313 |
| 5.3445 | 0.59 | 1000 | 5.2101 |
| 4.9992 | 0.88 | 1500 | 4.9562 |
| 4.7324 | 1.17 | 2000 | 4.8106 |
| 4.5644 | 1.47 | 2500 | 4.6898 |
| 4.463 | 1.76 | 3000 | 4.5856 |
| 4.3346 | 2.05 | 3500 | 4.5109 |
| 4.1431 | 2.34 | 4000 | 4.4614 |
| 4.1138 | 2.64 | 4500 | 4.4045 |
| 4.0727 | 2.93 | 5000 | 4.3492 |
| 3.8694 | 3.22 | 5500 | 4.3461 |
| 3.8111 | 3.52 | 6000 | 4.3130 |
| 3.7997 | 3.81 | 6500 | 4.2797 |
| 3.6813 | 4.1 | 7000 | 4.2807 |
| 3.5265 | 4.4 | 7500 | 4.2735 |
| 3.5218 | 4.69 | 8000 | 4.2609 |
| 3.506 | 4.98 | 8500 | 4.2485 |
| 3.3449 | 5.28 | 9000 | 4.2617 |
| 3.3306 | 5.57 | 9500 | 4.2607 |
| 3.3255 | 5.86 | 10000 | 4.2604 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
