<!-- 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. -->
botGPT2_Context_v1
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.3524
- Train Accuracy: 0.0000
- Train Perplexity: 18824.3340
- Validation Loss: 0.3106
- Validation Accuracy: 0.0
- Validation Perplexity: 39785.5430
- Epoch: 8
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': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 1e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 1e-05, 'decay_steps': 16381, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'passive_serialization': True}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: mixed_float16
Training results
Train Loss | Train Accuracy | Train Perplexity | Validation Loss | Validation Accuracy | Validation Perplexity | Epoch |
---|---|---|---|---|---|---|
0.6295 | 0.0032 | 100042.4062 | 0.3106 | 0.0 | 39785.5273 | 0 |
0.3528 | 0.0000 | 18560.1328 | 0.3106 | 0.0 | 39785.5391 | 1 |
0.3525 | 0.0000 | 18773.9668 | 0.3106 | 0.0 | 39785.5156 | 2 |
0.3525 | 0.0 | 18342.8223 | 0.3106 | 0.0 | 39785.5078 | 3 |
0.3525 | 0.0000 | 19026.9180 | 0.3106 | 0.0 | 39785.5508 | 4 |
0.3526 | 0.0 | 19108.625 | 0.3106 | 0.0 | 39785.5195 | 5 |
0.3526 | 0.0000 | 19143.7520 | 0.3106 | 0.0 | 39785.5312 | 6 |
0.3525 | 0.0000 | 18503.0938 | 0.3106 | 0.0 | 39785.5195 | 7 |
0.3524 | 0.0000 | 18824.3340 | 0.3106 | 0.0 | 39785.5430 | 8 |
Framework versions
- Transformers 4.26.0
- TensorFlow 2.11.0
- Datasets 2.9.0
- Tokenizers 0.13.2