|
--- |
|
license: mit |
|
base_model: gpt2 |
|
tags: |
|
- generated_from_keras_callback |
|
model-index: |
|
- name: vedantjumle/indo-ml-final-test-gpt2 |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# vedantjumle/indo-ml-final-test-gpt2 |
|
|
|
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Train Loss: 0.0791 |
|
- Validation Loss: 0.5970 |
|
- Train Accuracy: 0.86 |
|
- Epoch: 48 |
|
|
|
## 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': 'Adam', 'weight_decay': None, '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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 3000, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} |
|
- training_precision: float32 |
|
|
|
### Training results |
|
|
|
| Train Loss | Validation Loss | Train Accuracy | Epoch | |
|
|:----------:|:---------------:|:--------------:|:-----:| |
|
| 6.1590 | 5.0940 | 0.01 | 0 | |
|
| 5.0418 | 4.9883 | 0.0133 | 1 | |
|
| 4.9133 | 4.8504 | 0.0333 | 2 | |
|
| 4.7401 | 4.6073 | 0.07 | 3 | |
|
| 4.3767 | 3.9978 | 0.1767 | 4 | |
|
| 3.6892 | 3.2744 | 0.35 | 5 | |
|
| 2.9908 | 2.6567 | 0.4933 | 6 | |
|
| 2.3695 | 2.2079 | 0.6033 | 7 | |
|
| 1.9372 | 1.8126 | 0.66 | 8 | |
|
| 1.5314 | 1.5588 | 0.7133 | 9 | |
|
| 1.2590 | 1.3589 | 0.7333 | 10 | |
|
| 1.0342 | 1.2366 | 0.7433 | 11 | |
|
| 0.8585 | 1.1181 | 0.77 | 12 | |
|
| 0.7366 | 1.0283 | 0.78 | 13 | |
|
| 0.6208 | 0.9584 | 0.7933 | 14 | |
|
| 0.5448 | 0.9084 | 0.8133 | 15 | |
|
| 0.4745 | 0.8591 | 0.8033 | 16 | |
|
| 0.4187 | 0.8293 | 0.83 | 17 | |
|
| 0.3628 | 0.7953 | 0.84 | 18 | |
|
| 0.3299 | 0.7676 | 0.8467 | 19 | |
|
| 0.3072 | 0.7536 | 0.8267 | 20 | |
|
| 0.2794 | 0.7395 | 0.8367 | 21 | |
|
| 0.2370 | 0.7114 | 0.8567 | 22 | |
|
| 0.2203 | 0.6990 | 0.8467 | 23 | |
|
| 0.2104 | 0.6906 | 0.8433 | 24 | |
|
| 0.1838 | 0.6815 | 0.86 | 25 | |
|
| 0.1680 | 0.6633 | 0.8533 | 26 | |
|
| 0.1650 | 0.6629 | 0.8533 | 27 | |
|
| 0.1558 | 0.6536 | 0.8567 | 28 | |
|
| 0.1482 | 0.6499 | 0.86 | 29 | |
|
| 0.1404 | 0.6465 | 0.86 | 30 | |
|
| 0.1340 | 0.6385 | 0.8567 | 31 | |
|
| 0.1226 | 0.6313 | 0.8533 | 32 | |
|
| 0.1212 | 0.6257 | 0.86 | 33 | |
|
| 0.1120 | 0.6220 | 0.86 | 34 | |
|
| 0.1084 | 0.6271 | 0.86 | 35 | |
|
| 0.1043 | 0.6172 | 0.86 | 36 | |
|
| 0.1046 | 0.6173 | 0.86 | 37 | |
|
| 0.0989 | 0.6127 | 0.86 | 38 | |
|
| 0.0969 | 0.6106 | 0.86 | 39 | |
|
| 0.0918 | 0.6161 | 0.8633 | 40 | |
|
| 0.0916 | 0.6062 | 0.86 | 41 | |
|
| 0.0892 | 0.6037 | 0.86 | 42 | |
|
| 0.0822 | 0.6037 | 0.86 | 43 | |
|
| 0.0865 | 0.5968 | 0.86 | 44 | |
|
| 0.0819 | 0.5992 | 0.86 | 45 | |
|
| 0.0847 | 0.5988 | 0.86 | 46 | |
|
| 0.0805 | 0.5971 | 0.86 | 47 | |
|
| 0.0791 | 0.5970 | 0.86 | 48 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.2 |
|
- TensorFlow 2.13.0 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.13.3 |
|
|
