<!-- 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-log-rarity
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.1304
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 |
|---|---|---|---|
| 6.3458 | 0.29 | 500 | 5.3403 |
| 5.0473 | 0.58 | 1000 | 4.9210 |
| 4.7056 | 0.88 | 1500 | 4.6976 |
| 4.4581 | 1.17 | 2000 | 4.5505 |
| 4.3012 | 1.46 | 2500 | 4.4357 |
| 4.2018 | 1.75 | 3000 | 4.3315 |
| 4.0811 | 2.05 | 3500 | 4.2660 |
| 3.8943 | 2.34 | 4000 | 4.2167 |
| 3.8774 | 2.63 | 4500 | 4.1659 |
| 3.8319 | 2.92 | 5000 | 4.1187 |
| 3.6414 | 3.22 | 5500 | 4.1128 |
| 3.5868 | 3.51 | 6000 | 4.0844 |
| 3.5807 | 3.8 | 6500 | 4.0513 |
| 3.4751 | 4.09 | 7000 | 4.0524 |
| 3.3231 | 4.39 | 7500 | 4.0478 |
| 3.312 | 4.68 | 8000 | 4.0353 |
| 3.3046 | 4.97 | 8500 | 4.0234 |
| 3.1605 | 5.26 | 9000 | 4.0388 |
| 3.1352 | 5.56 | 9500 | 4.0392 |
| 3.1314 | 5.85 | 10000 | 4.0378 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
