<!-- 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. -->
ratish/DBERT_ZS_CleanCollision_v1
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.0014
- Validation Loss: 0.0010
- Train Accuracy: 1.0
- Epoch: 27
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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 9960, '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 |
---|---|---|---|
0.7535 | 0.3396 | 1.0 | 0 |
0.2209 | 0.0995 | 1.0 | 1 |
0.0806 | 0.0471 | 1.0 | 2 |
0.0450 | 0.0296 | 1.0 | 3 |
0.0305 | 0.0210 | 1.0 | 4 |
0.0222 | 0.0157 | 1.0 | 5 |
0.0175 | 0.0122 | 1.0 | 6 |
0.0139 | 0.0098 | 1.0 | 7 |
0.0111 | 0.0080 | 1.0 | 8 |
0.0094 | 0.0066 | 1.0 | 9 |
0.0077 | 0.0056 | 1.0 | 10 |
0.0067 | 0.0048 | 1.0 | 11 |
0.0059 | 0.0042 | 1.0 | 12 |
0.0053 | 0.0037 | 1.0 | 13 |
0.0044 | 0.0032 | 1.0 | 14 |
0.0041 | 0.0029 | 1.0 | 15 |
0.0036 | 0.0026 | 1.0 | 16 |
0.0032 | 0.0023 | 1.0 | 17 |
0.0029 | 0.0021 | 1.0 | 18 |
0.0027 | 0.0019 | 1.0 | 19 |
0.0024 | 0.0017 | 1.0 | 20 |
0.0022 | 0.0016 | 1.0 | 21 |
0.0020 | 0.0015 | 1.0 | 22 |
0.0018 | 0.0013 | 1.0 | 23 |
0.0017 | 0.0012 | 1.0 | 24 |
0.0016 | 0.0011 | 1.0 | 25 |
0.0015 | 0.0011 | 1.0 | 26 |
0.0014 | 0.0010 | 1.0 | 27 |
Framework versions
- Transformers 4.28.1
- TensorFlow 2.12.0
- Datasets 2.11.0
- Tokenizers 0.13.3