<!-- 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-all-base-rarity-all-iorder-8k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.3668
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: 7
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.7674 | 0.31 | 500 | 5.6574 |
| 5.4175 | 0.63 | 1000 | 5.2219 |
| 5.0586 | 0.94 | 1500 | 4.9730 |
| 4.769 | 1.25 | 2000 | 4.8188 |
| 4.6293 | 1.57 | 2500 | 4.6974 |
| 4.5229 | 1.88 | 3000 | 4.5900 |
| 4.32 | 2.19 | 3500 | 4.5361 |
| 4.2339 | 2.51 | 4000 | 4.4732 |
| 4.1839 | 2.82 | 4500 | 4.4075 |
| 4.048 | 3.13 | 5000 | 4.3910 |
| 3.9138 | 3.45 | 5500 | 4.3635 |
| 3.913 | 3.76 | 6000 | 4.3244 |
| 3.8274 | 4.07 | 6500 | 4.3225 |
| 3.6274 | 4.39 | 7000 | 4.3147 |
| 3.6392 | 4.7 | 7500 | 4.2932 |
| 3.6153 | 5.01 | 8000 | 4.2830 |
| 3.3708 | 5.33 | 8500 | 4.2999 |
| 3.3807 | 5.64 | 9000 | 4.2967 |
| 3.3739 | 5.95 | 9500 | 4.2874 |
| 3.2452 | 6.27 | 10000 | 4.3030 |
| 3.2215 | 6.58 | 10500 | 4.3028 |
| 3.2157 | 6.89 | 11000 | 4.3022 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
