metadata
license: apache-2.0
base_model: distilgpt2
tags:
- generated_from_keras_callback
model-index:
- name: node-py/my_awesome_eli5_clm-model
results: []
node-py/my_awesome_eli5_clm-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: 1.5653
- Validation Loss: 1.6131
- Epoch: 37
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 |
|---|---|---|
| 2.5315 | 2.2372 | 0 |
| 2.2709 | 2.1303 | 1 |
| 2.1837 | 2.0685 | 2 |
| 2.1268 | 2.0216 | 3 |
| 2.0821 | 1.9830 | 4 |
| 2.0436 | 1.9497 | 5 |
| 2.0105 | 1.9194 | 6 |
| 1.9810 | 1.8955 | 7 |
| 1.9552 | 1.8767 | 8 |
| 1.9311 | 1.8544 | 9 |
| 1.9080 | 1.8386 | 10 |
| 1.8864 | 1.8183 | 11 |
| 1.8676 | 1.7983 | 12 |
| 1.8487 | 1.7856 | 13 |
| 1.8304 | 1.7766 | 14 |
| 1.8150 | 1.7672 | 15 |
| 1.7992 | 1.7472 | 16 |
| 1.7841 | 1.7402 | 17 |
| 1.7687 | 1.7266 | 18 |
| 1.7554 | 1.7215 | 19 |
| 1.7422 | 1.7091 | 20 |
| 1.7279 | 1.7099 | 21 |
| 1.7163 | 1.6969 | 22 |
| 1.7051 | 1.6856 | 23 |
| 1.6925 | 1.6795 | 24 |
| 1.6819 | 1.6712 | 25 |
| 1.6709 | 1.6665 | 26 |
| 1.6593 | 1.6606 | 27 |
| 1.6504 | 1.6572 | 28 |
| 1.6402 | 1.6542 | 29 |
| 1.6308 | 1.6493 | 30 |
| 1.6205 | 1.6393 | 31 |
| 1.6104 | 1.6329 | 32 |
| 1.5999 | 1.6361 | 33 |
| 1.5915 | 1.6329 | 34 |
| 1.5832 | 1.6229 | 35 |
| 1.5746 | 1.6142 | 36 |
| 1.5653 | 1.6131 | 37 |
Framework versions
- Transformers 4.44.0
- TensorFlow 2.16.1
- Datasets 2.21.0
- Tokenizers 0.19.1