<!-- 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-rarity-no-cut-new-loop
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.1202
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 |
|---|---|---|---|
| 6.3521 | 0.29 | 500 | 5.3425 |
| 5.0432 | 0.58 | 1000 | 4.9203 |
| 4.7164 | 0.88 | 1500 | 4.6916 |
| 4.4472 | 1.17 | 2000 | 4.5559 |
| 4.3067 | 1.46 | 2500 | 4.4347 |
| 4.2037 | 1.75 | 3000 | 4.3339 |
| 4.0939 | 2.05 | 3500 | 4.2637 |
| 3.9028 | 2.34 | 4000 | 4.2175 |
| 3.8804 | 2.63 | 4500 | 4.1665 |
| 3.8379 | 2.92 | 5000 | 4.1136 |
| 3.6542 | 3.22 | 5500 | 4.1123 |
| 3.6025 | 3.51 | 6000 | 4.0822 |
| 3.5762 | 3.8 | 6500 | 4.0522 |
| 3.4854 | 4.09 | 7000 | 4.0517 |
| 3.3327 | 4.39 | 7500 | 4.0452 |
| 3.3175 | 4.68 | 8000 | 4.0294 |
| 3.3131 | 4.97 | 8500 | 4.0172 |
| 3.1598 | 5.26 | 9000 | 4.0329 |
| 3.1481 | 5.56 | 9500 | 4.0308 |
| 3.1467 | 5.85 | 10000 | 4.0303 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
