<!-- 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. -->
badokorach/distilbert-base-cased-160923
This model is a fine-tuned version of badokorach/distilbert-base-cased-160923 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.0084
- Validation Loss: 0.0
- Epoch: 28
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': 'transformers.optimization_tf', 'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1946, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 4, 'power': 1.0, 'name': None}, 'registered_name': 'WarmUp'}, 'decay': 0.0, 'beta_1': 0.8999999761581421, 'beta_2': 0.9990000128746033, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.02}, 'registered_name': 'AdamWeightDecay'}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
- training_precision: mixed_float16
Training results
Train Loss | Validation Loss | Epoch |
---|---|---|
0.0655 | 0.0 | 0 |
0.1225 | 0.0 | 1 |
0.0648 | 0.0 | 2 |
0.0527 | 0.0 | 3 |
0.0653 | 0.0 | 4 |
0.0456 | 0.0 | 5 |
0.0482 | 0.0 | 6 |
0.0318 | 0.0 | 7 |
0.0183 | 0.0 | 8 |
0.0237 | 0.0 | 9 |
0.0146 | 0.0 | 10 |
0.0231 | 0.0 | 11 |
0.0115 | 0.0 | 12 |
0.0161 | 0.0 | 13 |
0.0129 | 0.0 | 14 |
0.0162 | 0.0 | 15 |
0.0118 | 0.0 | 16 |
0.0109 | 0.0 | 17 |
0.0097 | 0.0 | 18 |
0.0070 | 0.0 | 19 |
0.0073 | 0.0 | 20 |
0.0099 | 0.0 | 21 |
0.0067 | 0.0 | 22 |
0.0037 | 0.0 | 23 |
0.0041 | 0.0 | 24 |
0.0082 | 0.0 | 25 |
0.0037 | 0.0 | 26 |
0.0054 | 0.0 | 27 |
0.0084 | 0.0 | 28 |
Framework versions
- Transformers 4.33.2
- TensorFlow 2.13.0
- Datasets 2.14.5
- Tokenizers 0.13.3