---
tags:
- generated_from_keras_callback
- NLP
- wikitext-2-raw-v1
model-index:
- name: pretrained-bertbase-wikitext
  results: []
pipeline_tag: fill-mask
datasets:
- wikitext
language:
- en
metrics:
- accuracy
---

<!-- 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. -->

# pretrained-bertbase-wikitext

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: 7.5881
- Validation Loss: 8.5897
- Epoch: 4

## 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': 1e-04, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32

### Training results

| Train Loss | Validation Loss | Epoch |
|:----------:|:---------------:|:-----:|
| 8.2205     | 8.4585          | 0     |
| 7.7729     | 8.5769          | 1     |
| 7.6960     | 8.4921          | 2     |
| 7.6486     | 8.5941          | 3     |
| 7.5881     | 8.5897          | 4     |


### Framework versions

- Transformers 4.35.2
- TensorFlow 2.14.0
- Tokenizers 0.15.0