metadata
license: apache-2.0
base_model: distilgpt2
tags:
- generated_from_keras_callback
model-index:
- name: pippinnie/distilgpt2-finetuned-cyber-readme-v3
results: []
pippinnie/distilgpt2-finetuned-cyber-readme-v3
This model is a fine-tuned version of distilgpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 3.8927
- Validation Loss: 3.9904
- 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': 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 |
|---|---|---|
| 4.6828 | 4.4721 | 0 |
| 4.3595 | 4.2948 | 1 |
| 4.1610 | 4.1656 | 2 |
| 4.0115 | 4.0678 | 3 |
| 3.8927 | 3.9904 | 4 |
Framework versions
- Transformers 4.38.2
- TensorFlow 2.16.1
- Datasets 2.18.0
- Tokenizers 0.15.2