<!-- 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_Desc_MAKE_v1.3.1
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: 0.0102
- Validation Loss: 0.0046
- Train Accuracy: 1.0
- Epoch: 19
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': 5840, '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 |
---|---|---|---|
1.2904 | 0.6970 | 1.0 | 0 |
0.6383 | 0.2616 | 1.0 | 1 |
0.3360 | 0.1262 | 1.0 | 2 |
0.1989 | 0.0738 | 1.0 | 3 |
0.1280 | 0.0499 | 1.0 | 4 |
0.0833 | 0.0364 | 1.0 | 5 |
0.0638 | 0.0281 | 1.0 | 6 |
0.0508 | 0.0224 | 1.0 | 7 |
0.0408 | 0.0185 | 1.0 | 8 |
0.0335 | 0.0155 | 1.0 | 9 |
0.0299 | 0.0131 | 1.0 | 10 |
0.0244 | 0.0112 | 1.0 | 11 |
0.0222 | 0.0098 | 1.0 | 12 |
0.0189 | 0.0085 | 1.0 | 13 |
0.0171 | 0.0076 | 1.0 | 14 |
0.0153 | 0.0068 | 1.0 | 15 |
0.0138 | 0.0061 | 1.0 | 16 |
0.0119 | 0.0055 | 1.0 | 17 |
0.0114 | 0.0050 | 1.0 | 18 |
0.0102 | 0.0046 | 1.0 | 19 |
Framework versions
- Transformers 4.28.1
- TensorFlow 2.12.0
- Datasets 2.11.0
- Tokenizers 0.13.3