---
library_name: transformers
language:
- en
license: apache-2.0
base_model: gokulsrinivasagan/tinybert_base_train_book_ent_15p_s_init
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: tinybert_base_train_book_ent_15p_s_init_mnli
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: GLUE MNLI
      type: glue
      args: mnli
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.725386493083808
---

<!-- 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. -->

# tinybert_base_train_book_ent_15p_s_init_mnli

This model is a fine-tuned version of [gokulsrinivasagan/tinybert_base_train_book_ent_15p_s_init](https://huggingface.co/gokulsrinivasagan/tinybert_base_train_book_ent_15p_s_init) on the GLUE MNLI dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6549
- Accuracy: 0.7254

## 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 |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 0.8785        | 1.0   | 1534  | 0.7729          | 0.6660   |
| 0.7353        | 2.0   | 3068  | 0.7123          | 0.6915   |
| 0.6658        | 3.0   | 4602  | 0.6983          | 0.7073   |
| 0.6113        | 4.0   | 6136  | 0.7001          | 0.7169   |
| 0.5654        | 5.0   | 7670  | 0.6811          | 0.7245   |
| 0.5207        | 6.0   | 9204  | 0.7057          | 0.7257   |
| 0.4798        | 7.0   | 10738 | 0.7188          | 0.7291   |
| 0.4403        | 8.0   | 12272 | 0.7684          | 0.7231   |
| 0.4036        | 9.0   | 13806 | 0.8034          | 0.7165   |
| 0.3685        | 10.0  | 15340 | 0.8376          | 0.7220   |


### Framework versions

- Transformers 4.51.2
- Pytorch 2.6.0+cu126
- Datasets 3.5.0
- Tokenizers 0.21.1