<!-- 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-guten-no-merge
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.0377
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 |
---|---|---|---|
6.3393 | 0.29 | 500 | 5.3133 |
5.0332 | 0.58 | 1000 | 4.8944 |
4.7062 | 0.87 | 1500 | 4.6552 |
4.4455 | 1.16 | 2000 | 4.5068 |
4.2946 | 1.45 | 2500 | 4.3846 |
4.1846 | 1.74 | 3000 | 4.2814 |
4.0809 | 2.03 | 3500 | 4.2011 |
3.8863 | 2.32 | 4000 | 4.1666 |
3.8588 | 2.61 | 4500 | 4.1094 |
3.814 | 2.9 | 5000 | 4.0582 |
3.6453 | 3.18 | 5500 | 4.0528 |
3.575 | 3.47 | 6000 | 4.0214 |
3.5609 | 3.76 | 6500 | 3.9924 |
3.4948 | 4.05 | 7000 | 3.9823 |
3.3077 | 4.34 | 7500 | 3.9803 |
3.2997 | 4.63 | 8000 | 3.9663 |
3.2906 | 4.92 | 8500 | 3.9538 |
3.1681 | 5.21 | 9000 | 3.9641 |
3.1219 | 5.5 | 9500 | 3.9635 |
3.1184 | 5.79 | 10000 | 3.9628 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3