<!-- 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. -->
cbt-guten-rarity-all-est-2p5k-guten
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.1100
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 |
|---|---|---|---|
| 6.3376 | 0.29 | 500 | 5.3378 |
| 5.0347 | 0.59 | 1000 | 4.9236 |
| 4.7052 | 0.88 | 1500 | 4.6938 |
| 4.4506 | 1.17 | 2000 | 4.5584 |
| 4.2967 | 1.47 | 2500 | 4.4305 |
| 4.1938 | 1.76 | 3000 | 4.3307 |
| 4.079 | 2.05 | 3500 | 4.2585 |
| 3.895 | 2.35 | 4000 | 4.2084 |
| 3.8722 | 2.64 | 4500 | 4.1495 |
| 3.8245 | 2.93 | 5000 | 4.1026 |
| 3.6339 | 3.23 | 5500 | 4.0968 |
| 3.5909 | 3.52 | 6000 | 4.0698 |
| 3.5755 | 3.81 | 6500 | 4.0402 |
| 3.4668 | 4.11 | 7000 | 4.0409 |
| 3.3194 | 4.4 | 7500 | 4.0353 |
| 3.3196 | 4.69 | 8000 | 4.0179 |
| 3.3088 | 4.99 | 8500 | 4.0070 |
| 3.1488 | 5.28 | 9000 | 4.0193 |
| 3.1429 | 5.58 | 9500 | 4.0183 |
| 3.1402 | 5.87 | 10000 | 4.0178 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
