---
library_name: transformers
tags:
- generated_from_trainer
datasets:
- gokulsrinivasagan/processed_book_corpus-ld
metrics:
- accuracy
model-index:
- name: bert_tiny_lda_book
  results:
  - task:
      name: Masked Language Modeling
      type: fill-mask
    dataset:
      name: gokulsrinivasagan/processed_book_corpus-ld
      type: gokulsrinivasagan/processed_book_corpus-ld
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.6827213137673483
---

<!-- 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_tiny_lda_book

This model is a fine-tuned version of [](https://huggingface.co/) on the gokulsrinivasagan/processed_book_corpus-ld dataset.
It achieves the following results on the evaluation set:
- Loss: 3.3915
- Accuracy: 0.6827

## 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: 0.0001
- train_batch_size: 160
- eval_batch_size: 160
- seed: 10
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10000
- num_epochs: 25

### Training results

| Training Loss | Epoch   | Step   | Validation Loss | Accuracy |
|:-------------:|:-------:|:------:|:---------------:|:--------:|
| 7.9444        | 0.7025  | 10000  | 7.7823          | 0.1644   |
| 5.4537        | 1.4051  | 20000  | 5.0087          | 0.4658   |
| 4.6397        | 2.1076  | 30000  | 4.2650          | 0.5607   |
| 4.3898        | 2.8102  | 40000  | 4.0379          | 0.5916   |
| 4.2383        | 3.5127  | 50000  | 3.8978          | 0.6113   |
| 4.1379        | 4.2153  | 60000  | 3.8117          | 0.6234   |
| 4.0736        | 4.9178  | 70000  | 3.7462          | 0.6324   |
| 4.0187        | 5.6203  | 80000  | 3.6985          | 0.6391   |
| 3.9803        | 6.3229  | 90000  | 3.6644          | 0.6444   |
| 3.9462        | 7.0254  | 100000 | 3.6333          | 0.6485   |
| 3.9217        | 7.7280  | 110000 | 3.6064          | 0.6526   |
| 3.8974        | 8.4305  | 120000 | 3.5810          | 0.6558   |
| 3.8714        | 9.1331  | 130000 | 3.5696          | 0.6581   |
| 3.8565        | 9.8356  | 140000 | 3.5454          | 0.6613   |
| 3.8382        | 10.5381 | 150000 | 3.5310          | 0.6632   |
| 3.8272        | 11.2407 | 160000 | 3.5181          | 0.6647   |
| 3.8059        | 11.9432 | 170000 | 3.5012          | 0.6666   |
| 3.7935        | 12.6458 | 180000 | 3.4849          | 0.6683   |
| 3.7815        | 13.3483 | 190000 | 3.4784          | 0.6695   |
| 3.7719        | 14.0509 | 200000 | 3.4671          | 0.6710   |
| 3.7614        | 14.7534 | 210000 | 3.4574          | 0.6724   |
| 3.7509        | 15.4560 | 220000 | 3.4488          | 0.6740   |
| 3.7456        | 16.1585 | 230000 | 3.4445          | 0.6745   |
| 3.736         | 16.8610 | 240000 | 3.4378          | 0.6753   |
| 3.728         | 17.5636 | 250000 | 3.4330          | 0.6763   |
| 3.7223        | 18.2661 | 260000 | 3.4270          | 0.6772   |
| 3.7195        | 18.9687 | 270000 | 3.4210          | 0.6780   |
| 3.7104        | 19.6712 | 280000 | 3.4156          | 0.6790   |
| 3.7086        | 20.3738 | 290000 | 3.4105          | 0.6797   |
| 3.7002        | 21.0763 | 300000 | 3.4070          | 0.6803   |
| 3.698         | 21.7788 | 310000 | 3.4013          | 0.6812   |
| 3.6915        | 22.4814 | 320000 | 3.3987          | 0.6814   |
| 3.6909        | 23.1839 | 330000 | 3.3962          | 0.6818   |
| 3.6883        | 23.8865 | 340000 | 3.3933          | 0.6825   |
| 3.6867        | 24.5890 | 350000 | 3.3903          | 0.6829   |


### Framework versions

- Transformers 4.46.1
- Pytorch 2.2.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.1