<!-- 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. -->
dialogpt
This model is a fine-tuned version of microsoft/DialoGPT-medium on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 6.1947
- Epoch: 29
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: {'inner_optimizer': {'module': 'keras.optimizers', 'class_name': 'AdamW', 'config': {'name': 'AdamW', 'weight_decay': 0.004, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 0.0010000000474974513, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}, 'registered_name': None}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
- training_precision: mixed_float16
Training results
Train Loss | Epoch |
---|---|
6.2302 | 0 |
6.2428 | 1 |
6.2165 | 2 |
6.1857 | 3 |
6.1930 | 4 |
6.2082 | 5 |
6.2222 | 6 |
6.1664 | 7 |
6.2068 | 8 |
6.1659 | 9 |
6.2533 | 10 |
6.2140 | 11 |
6.2313 | 12 |
6.1959 | 13 |
6.1944 | 14 |
6.2060 | 15 |
6.2331 | 16 |
6.2295 | 17 |
6.2094 | 18 |
6.2031 | 19 |
6.1904 | 20 |
6.1994 | 21 |
6.1597 | 22 |
6.2218 | 23 |
6.2402 | 24 |
6.1590 | 25 |
6.1848 | 26 |
6.1851 | 27 |
6.1585 | 28 |
6.1947 | 29 |
Framework versions
- Transformers 4.33.1
- TensorFlow 2.13.0
- Tokenizers 0.13.3