cbt-rarity
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.0375
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 |
|---|---|---|---|
| 6.3439 | 0.29 | 500 | 5.3171 |
| 5.0356 | 0.58 | 1000 | 4.8973 |
| 4.7113 | 0.87 | 1500 | 4.6631 |
| 4.4527 | 1.16 | 2000 | 4.5185 |
| 4.3042 | 1.45 | 2500 | 4.3965 |
| 4.1936 | 1.74 | 3000 | 4.2874 |
| 4.0885 | 2.03 | 3500 | 4.2062 |
| 3.8938 | 2.32 | 4000 | 4.1672 |
| 3.865 | 2.61 | 4500 | 4.1098 |
| 3.8203 | 2.9 | 5000 | 4.0591 |
| 3.6517 | 3.18 | 5500 | 4.0511 |
| 3.5823 | 3.47 | 6000 | 4.0221 |
| 3.5678 | 3.76 | 6500 | 3.9929 |
| 3.5014 | 4.05 | 7000 | 3.9837 |
| 3.3153 | 4.34 | 7500 | 3.9803 |
| 3.3079 | 4.63 | 8000 | 3.9677 |
| 3.2975 | 4.92 | 8500 | 3.9545 |
| 3.1763 | 5.21 | 9000 | 3.9634 |
| 3.1301 | 5.5 | 9500 | 3.9632 |
| 3.1272 | 5.79 | 10000 | 3.9618 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
- Downloads last month
- 5