<!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. -->
Joeni/distilgpt2-finetuned-shakespeare
This model is a fine-tuned version of distilgpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 3.1768
- Validation Loss: 3.5077
- Epoch: 19
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:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 4.2091 | 3.8246 | 0 |
| 3.9001 | 3.6943 | 1 |
| 3.7802 | 3.6283 | 2 |
| 3.7044 | 3.5885 | 3 |
| 3.6483 | 3.5617 | 4 |
| 3.5981 | 3.5464 | 5 |
| 3.5571 | 3.5362 | 6 |
| 3.5193 | 3.5247 | 7 |
| 3.4848 | 3.5205 | 8 |
| 3.4528 | 3.5129 | 9 |
| 3.4202 | 3.5090 | 10 |
| 3.3915 | 3.5002 | 11 |
| 3.3608 | 3.5041 | 12 |
| 3.3321 | 3.4999 | 13 |
| 3.3039 | 3.4969 | 14 |
| 3.2783 | 3.4997 | 15 |
| 3.2511 | 3.5030 | 16 |
| 3.2269 | 3.5071 | 17 |
| 3.2013 | 3.5086 | 18 |
| 3.1768 | 3.5077 | 19 |
Framework versions
- Transformers 4.26.1
- TensorFlow 2.11.0
- Datasets 2.10.1
- Tokenizers 0.13.2
