<!-- 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-rarity-seed
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.1015
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 |
---|---|---|---|
6.3444 | 0.29 | 500 | 5.3437 |
5.0325 | 0.58 | 1000 | 4.9351 |
4.7076 | 0.87 | 1500 | 4.6882 |
4.4438 | 1.17 | 2000 | 4.5477 |
4.2923 | 1.46 | 2500 | 4.4284 |
4.1863 | 1.75 | 3000 | 4.3230 |
4.0772 | 2.04 | 3500 | 4.2506 |
3.8897 | 2.33 | 4000 | 4.2060 |
3.8637 | 2.62 | 4500 | 4.1512 |
3.8278 | 2.91 | 5000 | 4.1009 |
3.6372 | 3.21 | 5500 | 4.0951 |
3.5835 | 3.5 | 6000 | 4.0674 |
3.5688 | 3.79 | 6500 | 4.0332 |
3.4818 | 4.08 | 7000 | 4.0308 |
3.3077 | 4.37 | 7500 | 4.0275 |
3.3134 | 4.66 | 8000 | 4.0145 |
3.2991 | 4.95 | 8500 | 4.0005 |
3.1588 | 5.24 | 9000 | 4.0125 |
3.1309 | 5.54 | 9500 | 4.0123 |
3.1268 | 5.83 | 10000 | 4.0113 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3