bert_3 / README.md
hanci05's picture
Upload TFBertForPreTraining
9aad6c2
---
tags:
- generated_from_keras_callback
model-index:
- name: bert_3
results: []
---
<!-- 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. -->
# bert_3
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 6.0851
- 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', 'learning_rate': 1e-04, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Epoch |
|:----------:|:-----:|
| 8.8352 | 0 |
| 6.8732 | 1 |
| 6.6390 | 2 |
| 6.3008 | 3 |
| 6.5051 | 4 |
| 6.3542 | 5 |
| 6.2322 | 6 |
| 6.2831 | 7 |
| 6.3018 | 8 |
| 6.2346 | 9 |
| 6.1593 | 10 |
| 6.1451 | 11 |
| 6.1091 | 12 |
| 6.1909 | 13 |
| 6.1473 | 14 |
| 6.0694 | 15 |
| 5.9517 | 16 |
| 6.1890 | 17 |
| 6.1535 | 18 |
| 6.0851 | 19 |
### Framework versions
- Transformers 4.33.1
- TensorFlow 2.10.0
- Datasets 2.12.0
- Tokenizers 0.13.3