<!-- 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. -->
bnc-cbt-rarity-mixed
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.0594
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 |
|---|---|---|---|
| 6.3665 | 0.29 | 500 | 5.3115 |
| 5.0498 | 0.58 | 1000 | 4.9024 |
| 4.7317 | 0.87 | 1500 | 4.6646 |
| 4.4609 | 1.16 | 2000 | 4.5206 |
| 4.3169 | 1.45 | 2500 | 4.4078 |
| 4.2185 | 1.75 | 3000 | 4.3041 |
| 4.0998 | 2.04 | 3500 | 4.2236 |
| 3.9145 | 2.33 | 4000 | 4.1835 |
| 3.8745 | 2.62 | 4500 | 4.1284 |
| 3.8531 | 2.91 | 5000 | 4.0763 |
| 3.6685 | 3.2 | 5500 | 4.0703 |
| 3.598 | 3.49 | 6000 | 4.0412 |
| 3.5813 | 3.78 | 6500 | 4.0117 |
| 3.5089 | 4.07 | 7000 | 4.0030 |
| 3.3334 | 4.36 | 7500 | 3.9999 |
| 3.3274 | 4.65 | 8000 | 3.9871 |
| 3.317 | 4.94 | 8500 | 3.9757 |
| 3.1751 | 5.24 | 9000 | 3.9865 |
| 3.1414 | 5.53 | 9500 | 3.9854 |
| 3.1567 | 5.82 | 10000 | 3.9837 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
