ksabeh's picture
Training in progress epoch 1
9f70951
---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: ksabeh/bert-base-uncased-attribute-correction-mlm-titles
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. -->
# ksabeh/bert-base-uncased-attribute-correction-mlm-titles
This model is a fine-tuned version of [ksabeh/bert-base-uncased-attribute-correction-mlm](https://huggingface.co/ksabeh/bert-base-uncased-attribute-correction-mlm) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.0430
- Validation Loss: 0.0625
- Epoch: 1
## 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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 23878, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Epoch |
|:----------:|:---------------:|:-----:|
| 0.1429 | 0.0743 | 0 |
| 0.0430 | 0.0625 | 1 |
### Framework versions
- Transformers 4.18.0
- TensorFlow 2.6.4
- Datasets 2.1.0
- Tokenizers 0.12.1