<!-- 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. -->
cbt-rarity-all-p8k-new-loop-2-pad
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.1006
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 |
|---|---|---|---|
| 6.3461 | 0.29 | 500 | 5.3438 |
| 5.0317 | 0.58 | 1000 | 4.9286 |
| 4.7079 | 0.88 | 1500 | 4.6894 |
| 4.4388 | 1.17 | 2000 | 4.5454 |
| 4.2948 | 1.46 | 2500 | 4.4210 |
| 4.1904 | 1.75 | 3000 | 4.3216 |
| 4.073 | 2.04 | 3500 | 4.2445 |
| 3.8868 | 2.33 | 4000 | 4.2018 |
| 3.8634 | 2.63 | 4500 | 4.1489 |
| 3.8217 | 2.92 | 5000 | 4.0997 |
| 3.6311 | 3.21 | 5500 | 4.0929 |
| 3.5766 | 3.5 | 6000 | 4.0624 |
| 3.5658 | 3.79 | 6500 | 4.0332 |
| 3.483 | 4.08 | 7000 | 4.0303 |
| 3.3086 | 4.38 | 7500 | 4.0283 |
| 3.312 | 4.67 | 8000 | 4.0121 |
| 3.2964 | 4.96 | 8500 | 3.9992 |
| 3.1533 | 5.25 | 9000 | 4.0123 |
| 3.1289 | 5.54 | 9500 | 4.0107 |
| 3.1299 | 5.83 | 10000 | 4.0098 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
