metadata
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: dhanunjaya/distilgpt2-finetuned-pragmatic-1
results: []
dhanunjaya/distilgpt2-finetuned-pragmatic-1
This model is a fine-tuned version of distilgpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 3.2545
- Validation Loss: 3.2669
- Epoch: 9
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 |
|---|---|---|
| 3.9823 | 3.3961 | 0 |
| 3.7835 | 3.3474 | 1 |
| 3.6659 | 3.3297 | 2 |
| 3.5855 | 3.3068 | 3 |
| 3.5032 | 3.2984 | 4 |
| 3.4418 | 3.2964 | 5 |
| 3.3827 | 3.2846 | 6 |
| 3.3475 | 3.2771 | 7 |
| 3.2982 | 3.2761 | 8 |
| 3.2545 | 3.2669 | 9 |
Framework versions
- Transformers 4.26.1
- TensorFlow 2.11.0
- Datasets 2.10.1
- Tokenizers 0.13.2