<!-- 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. -->
gpt-2-spiritualtest-1
This model is a fine-tuned version of Aharneish/gpt2-spiritual on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4340
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: 0.001
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.9989 | 0.26 | 500 | 1.5329 |
1.6426 | 0.53 | 1000 | 1.1962 |
1.4637 | 0.79 | 1500 | 0.9494 |
1.2908 | 1.06 | 2000 | 0.7930 |
1.0382 | 1.32 | 2500 | 0.6957 |
0.9785 | 1.59 | 3000 | 0.6044 |
0.9246 | 1.85 | 3500 | 0.5384 |
0.7572 | 2.12 | 4000 | 0.5502 |
0.7632 | 2.38 | 4500 | 0.5121 |
0.7364 | 2.65 | 5000 | 0.4723 |
0.7012 | 2.91 | 5500 | 0.4340 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3