---
tags:
- generated_from_trainer
datasets:
- gokuls/wiki_book_corpus_complete_processed_bert_dataset
metrics:
- accuracy
model-index:
- name: bert_12_layer_model_v4_complete_training_48
  results:
  - task:
      name: Masked Language Modeling
      type: fill-mask
    dataset:
      name: gokuls/wiki_book_corpus_complete_processed_bert_dataset
      type: gokuls/wiki_book_corpus_complete_processed_bert_dataset
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.2879346070609049
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# bert_12_layer_model_v4_complete_training_48

This model is a fine-tuned version of [](https://huggingface.co/) on the gokuls/wiki_book_corpus_complete_processed_bert_dataset dataset.
It achieves the following results on the evaluation set:
- Loss: 4.7042
- Accuracy: 0.2879

## 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:
- learning_rate: 1e-05
- train_batch_size: 48
- eval_batch_size: 48
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10000
- num_epochs: 5

### Training results

| Training Loss | Epoch | Step   | Validation Loss | Accuracy |
|:-------------:|:-----:|:------:|:---------------:|:--------:|
| 6.5774        | 0.08  | 10000  | 6.5399          | 0.1253   |
| 6.3254        | 0.16  | 20000  | 6.3103          | 0.1388   |
| 6.2278        | 0.25  | 30000  | 6.2114          | 0.1443   |
| 6.1712        | 0.33  | 40000  | 6.1491          | 0.1475   |
| 6.12          | 0.41  | 50000  | 6.1086          | 0.1492   |
| 6.0914        | 0.49  | 60000  | 6.0781          | 0.1500   |
| 6.0676        | 0.57  | 70000  | 6.0540          | 0.1505   |
| 6.0492        | 0.66  | 80000  | 6.0345          | 0.1512   |
| 6.028         | 0.74  | 90000  | 6.0157          | 0.1516   |
| 5.9337        | 0.82  | 100000 | 5.8988          | 0.1533   |
| 5.7697        | 0.9   | 110000 | 5.7402          | 0.1654   |
| 5.6918        | 0.98  | 120000 | 5.6387          | 0.1777   |
| 5.6026        | 1.07  | 130000 | 5.5348          | 0.1910   |
| 5.5066        | 1.15  | 140000 | 5.4329          | 0.2035   |
| 5.4294        | 1.23  | 150000 | 5.3326          | 0.2144   |
| 5.3402        | 1.31  | 160000 | 5.2304          | 0.2270   |
| 5.2397        | 1.39  | 170000 | 5.1170          | 0.2406   |
| 5.1356        | 1.47  | 180000 | 4.9793          | 0.2564   |
| 5.0099        | 1.56  | 190000 | 4.8372          | 0.2730   |
| 4.885         | 1.64  | 200000 | 4.7058          | 0.2878   |


### Framework versions

- Transformers 4.33.3
- Pytorch 1.14.0a0+410ce96
- Datasets 2.14.5
- Tokenizers 0.13.3