<!-- 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-mixed-cut-1p6k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.3198
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 |
|---|---|---|---|
| 6.7132 | 0.29 | 500 | 5.6388 |
| 5.3379 | 0.58 | 1000 | 5.2003 |
| 4.9911 | 0.88 | 1500 | 4.9501 |
| 4.7234 | 1.17 | 2000 | 4.7998 |
| 4.56 | 1.46 | 2500 | 4.6792 |
| 4.4531 | 1.75 | 3000 | 4.5736 |
| 4.3338 | 2.04 | 3500 | 4.4956 |
| 4.1301 | 2.34 | 4000 | 4.4492 |
| 4.1048 | 2.63 | 4500 | 4.3884 |
| 4.0747 | 2.92 | 5000 | 4.3417 |
| 3.8686 | 3.21 | 5500 | 4.3330 |
| 3.8073 | 3.5 | 6000 | 4.3052 |
| 3.7976 | 3.79 | 6500 | 4.2688 |
| 3.6924 | 4.09 | 7000 | 4.2710 |
| 3.5274 | 4.38 | 7500 | 4.2596 |
| 3.5143 | 4.67 | 8000 | 4.2507 |
| 3.5116 | 4.96 | 8500 | 4.2372 |
| 3.3548 | 5.25 | 9000 | 4.2518 |
| 3.3311 | 5.55 | 9500 | 4.2495 |
| 3.3309 | 5.84 | 10000 | 4.2485 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
