fine_tuned_gpt2_clm-model
This model is a fine-tuned version of gpt2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.6233
- Perplexity: 37.46
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: 4
- eval_batch_size: 4
- 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 |
|---|---|---|---|
| 3.5982 | 1.0 | 555 | 3.6067 |
| 3.5546 | 2.0 | 1110 | 3.6103 |
| 3.5102 | 3.0 | 1665 | 3.6054 |
| 3.4797 | 4.0 | 2220 | 3.6033 |
| 3.4634 | 5.0 | 2775 | 3.6053 |
| 3.4315 | 6.0 | 3330 | 3.6046 |
| 3.4116 | 7.0 | 3885 | 3.6077 |
| 3.3934 | 8.0 | 4440 | 3.6121 |
| 3.3741 | 9.0 | 4995 | 3.6158 |
| 3.3443 | 10.0 | 5550 | 3.6175 |
| 3.335 | 11.0 | 6105 | 3.6219 |
| 3.3203 | 12.0 | 6660 | 3.6227 |
| 3.3123 | 13.0 | 7215 | 3.6206 |
| 3.3154 | 14.0 | 7770 | 3.6220 |
| 3.3057 | 15.0 | 8325 | 3.6233 |
Framework versions
- Transformers 4.32.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
- Downloads last month
- 2