metadata
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: Manuel-I/distilgpt2-finetuned-shakespeare
results: []
Manuel-I/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: 3.2540
- Validation Loss: 3.4994
- Epoch: 16
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 |
|---|---|---|
| 4.2103 | 3.8318 | 0 |
| 3.9016 | 3.7030 | 1 |
| 3.7804 | 3.6243 | 2 |
| 3.7072 | 3.5896 | 3 |
| 3.6501 | 3.5631 | 4 |
| 3.6008 | 3.5464 | 5 |
| 3.5605 | 3.5322 | 6 |
| 3.5229 | 3.5230 | 7 |
| 3.4857 | 3.5189 | 8 |
| 3.4517 | 3.5118 | 9 |
| 3.4204 | 3.5034 | 10 |
| 3.3916 | 3.4978 | 11 |
| 3.3621 | 3.4949 | 12 |
| 3.3332 | 3.5003 | 13 |
| 3.3063 | 3.4998 | 14 |
| 3.2773 | 3.5015 | 15 |
| 3.2540 | 3.4994 | 16 |
Framework versions
- Transformers 4.26.1
- TensorFlow 2.11.0
- Datasets 2.10.0
- Tokenizers 0.13.2