metadata
license: mit
tags:
- generated_from_keras_callback
model-index:
- name: soumya13/GPT2_CleanDesc_MAKE_v1.3
results: []
soumya13/GPT2_CleanDesc_MAKE_v1.3
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.0174
- Validation Loss: 0.0005
- Train Accuracy: 1.0
- Epoch: 17
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': False, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 6180, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, '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 |
---|---|---|---|
2.3151 | 0.8093 | 0.775 | 0 |
0.6489 | 0.5116 | 0.825 | 1 |
0.2988 | 0.2341 | 0.85 | 2 |
0.1152 | 0.0806 | 1.0 | 3 |
0.0876 | 0.0790 | 1.0 | 4 |
0.0523 | 0.0376 | 1.0 | 5 |
0.0522 | 0.0212 | 1.0 | 6 |
0.0222 | 0.0104 | 1.0 | 7 |
0.0271 | 0.0044 | 1.0 | 8 |
0.0430 | 0.0024 | 1.0 | 9 |
0.0101 | 0.0015 | 1.0 | 10 |
0.0280 | 0.0011 | 1.0 | 11 |
0.0346 | 0.0009 | 1.0 | 12 |
0.0275 | 0.0010 | 1.0 | 13 |
0.0329 | 0.0007 | 1.0 | 14 |
0.0140 | 0.0008 | 1.0 | 15 |
0.0121 | 0.0008 | 1.0 | 16 |
0.0174 | 0.0005 | 1.0 | 17 |
Framework versions
- Transformers 4.28.1
- TensorFlow 2.12.0
- Datasets 2.11.0
- Tokenizers 0.13.3