<!-- 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. -->
Imran1/distilgpt2-pashto_model
This model is a fine-tuned version of distilgpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 1.3857
- Train Accuracy: 0.0184
- Validation Loss: 1.3845
- Validation Accuracy: 0.0113
- Epoch: 4
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': 0.0003, '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 | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|---|---|---|---|---|
| 1.9135 | 0.0235 | 1.6378 | 0.0128 | 0 |
| 1.6200 | 0.0203 | 1.4978 | 0.0091 | 1 |
| 1.5127 | 0.0188 | 1.4323 | 0.0087 | 2 |
| 1.4434 | 0.0187 | 1.3812 | 0.0106 | 3 |
| 1.3857 | 0.0184 | 1.3845 | 0.0113 | 4 |
Framework versions
- Transformers 4.31.0.dev0
- TensorFlow 2.12.0
- Datasets 2.13.1
- Tokenizers 0.13.3
