---
library_name: transformers
language:
- en
base_model: gokulsrinivasagan/bert_base_lda_100_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: bert_base_lda_100_v1_mnli
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: GLUE MNLI
      type: glue
      args: mnli
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.7162327095199349
---

<!-- 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_base_lda_100_v1_mnli

This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_100_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_100_v1) on the GLUE MNLI dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6799
- Accuracy: 0.7162

## 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 |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 0.9588        | 1.0   | 1534  | 0.8420          | 0.6249   |
| 0.7857        | 2.0   | 3068  | 0.7451          | 0.6808   |
| 0.6825        | 3.0   | 4602  | 0.7162          | 0.6976   |
| 0.5973        | 4.0   | 6136  | 0.7056          | 0.7113   |
| 0.5208        | 5.0   | 7670  | 0.7460          | 0.7144   |
| 0.4464        | 6.0   | 9204  | 0.7907          | 0.7078   |
| 0.3775        | 7.0   | 10738 | 0.8362          | 0.7172   |
| 0.316         | 8.0   | 12272 | 0.9463          | 0.7101   |
| 0.2617        | 9.0   | 13806 | 1.0094          | 0.7111   |


### Framework versions

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