---
library_name: transformers
base_model: gokulsrinivasagan/bert_tiny_lda_50_v1_book
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: bert_tiny_lda_50_v1_book_mnli
  results: []
---

<!-- 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_50_v1_book_mnli

This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_50_v1_book](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_50_v1_book) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8192
- Accuracy: 0.7524

## 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: 5e-05
- train_batch_size: 256
- eval_batch_size: 256
- seed: 10
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 0.7973        | 1.0   | 1534  | 0.7054          | 0.6963   |
| 0.6499        | 2.0   | 3068  | 0.6406          | 0.7318   |
| 0.5649        | 3.0   | 4602  | 0.6320          | 0.7460   |
| 0.4962        | 4.0   | 6136  | 0.6454          | 0.7494   |
| 0.4374        | 5.0   | 7670  | 0.6634          | 0.7514   |
| 0.3831        | 6.0   | 9204  | 0.7042          | 0.7517   |
| 0.3325        | 7.0   | 10738 | 0.7310          | 0.7552   |
| 0.2885        | 8.0   | 12272 | 0.8192          | 0.7524   |


### Framework versions

- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3