<!-- 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-no-cut-mixed
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.3145
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 |
|---|---|---|---|
| 6.6998 | 0.29 | 500 | 5.6349 |
| 5.3359 | 0.58 | 1000 | 5.2045 |
| 5.0022 | 0.87 | 1500 | 4.9528 |
| 4.7241 | 1.17 | 2000 | 4.8077 |
| 4.569 | 1.46 | 2500 | 4.6840 |
| 4.4553 | 1.75 | 3000 | 4.5780 |
| 4.3352 | 2.04 | 3500 | 4.4962 |
| 4.1392 | 2.33 | 4000 | 4.4494 |
| 4.1038 | 2.62 | 4500 | 4.3886 |
| 4.0691 | 2.91 | 5000 | 4.3376 |
| 3.8726 | 3.21 | 5500 | 4.3303 |
| 3.8038 | 3.5 | 6000 | 4.3011 |
| 3.7898 | 3.79 | 6500 | 4.2699 |
| 3.7078 | 4.08 | 7000 | 4.2647 |
| 3.5226 | 4.37 | 7500 | 4.2585 |
| 3.5168 | 4.66 | 8000 | 4.2445 |
| 3.5054 | 4.95 | 8500 | 4.2338 |
| 3.3562 | 5.24 | 9000 | 4.2460 |
| 3.3295 | 5.54 | 9500 | 4.2429 |
| 3.3233 | 5.83 | 10000 | 4.2431 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
