<!-- 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-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: 4.1410
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 |
|---|---|---|---|
| 6.351 | 0.29 | 500 | 5.3291 |
| 5.0493 | 0.59 | 1000 | 4.9419 |
| 4.7234 | 0.88 | 1500 | 4.7048 |
| 4.4524 | 1.17 | 2000 | 4.5595 |
| 4.3123 | 1.46 | 2500 | 4.4472 |
| 4.2134 | 1.76 | 3000 | 4.3517 |
| 4.0971 | 2.05 | 3500 | 4.2754 |
| 3.9151 | 2.34 | 4000 | 4.2320 |
| 3.8812 | 2.63 | 4500 | 4.1763 |
| 3.8438 | 2.93 | 5000 | 4.1267 |
| 3.6488 | 3.22 | 5500 | 4.1269 |
| 3.6024 | 3.51 | 6000 | 4.0958 |
| 3.5864 | 3.81 | 6500 | 4.0625 |
| 3.4842 | 4.1 | 7000 | 4.0646 |
| 3.3367 | 4.39 | 7500 | 4.0563 |
| 3.3316 | 4.68 | 8000 | 4.0432 |
| 3.3157 | 4.98 | 8500 | 4.0354 |
| 3.1598 | 5.27 | 9000 | 4.0473 |
| 3.1514 | 5.56 | 9500 | 4.0472 |
| 3.1497 | 5.85 | 10000 | 4.0465 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
