metadata
base_model: bert-base-chinese
tags:
- generated_from_keras_callback
model-index:
- name: node-py/my_awesome_eli5_clm-model
results: []
node-py/my_awesome_eli5_clm-model
This model is a fine-tuned version of bert-base-chinese on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 2.8978
- Epoch: 20
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': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
Training results
| Train Loss | Epoch |
|---|---|
| 6.5795 | 0 |
| 5.8251 | 1 |
| 5.3850 | 2 |
| 5.0469 | 3 |
| 4.8048 | 4 |
| 4.6144 | 5 |
| 4.4743 | 6 |
| 4.3366 | 7 |
| 4.2178 | 8 |
| 4.1022 | 9 |
| 3.9908 | 10 |
| 3.8856 | 11 |
| 3.7700 | 12 |
| 3.6673 | 13 |
| 3.5560 | 14 |
| 3.4401 | 15 |
| 3.3328 | 16 |
| 3.2248 | 17 |
| 3.1290 | 18 |
| 3.0121 | 19 |
| 2.8978 | 20 |
Framework versions
- Transformers 4.44.0
- TensorFlow 2.16.1
- Datasets 2.21.0
- Tokenizers 0.19.1