<!-- 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. -->
distilgpt2-finetuned-brookstraining
This model is a fine-tuned version of distilgpt2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.6363
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
No log | 1.0 | 201 | 4.1881 |
No log | 2.0 | 402 | 4.0630 |
4.3174 | 3.0 | 603 | 3.9803 |
4.3174 | 4.0 | 804 | 3.9193 |
4.0754 | 5.0 | 1005 | 3.8654 |
4.0754 | 6.0 | 1206 | 3.8216 |
4.0754 | 7.0 | 1407 | 3.7805 |
3.9638 | 8.0 | 1608 | 3.7475 |
3.9638 | 9.0 | 1809 | 3.7168 |
3.8825 | 10.0 | 2010 | 3.6928 |
3.8825 | 11.0 | 2211 | 3.6715 |
3.8825 | 12.0 | 2412 | 3.6567 |
3.8238 | 13.0 | 2613 | 3.6455 |
3.8238 | 14.0 | 2814 | 3.6389 |
3.7844 | 15.0 | 3015 | 3.6363 |
Framework versions
- Transformers 4.27.4
- Pytorch 1.13.1
- Datasets 2.11.0
- Tokenizers 0.11.0