---
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_qnli
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: GLUE QNLI
      type: glue
      args: qnli
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.7882116053450485
---

<!-- 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_qnli

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 QNLI dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4444
- Accuracy: 0.7882

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.6384        | 1.0   | 410  | 0.5732          | 0.6985   |
| 0.5415        | 2.0   | 820  | 0.4735          | 0.7642   |
| 0.4624        | 3.0   | 1230 | 0.4444          | 0.7882   |
| 0.4039        | 4.0   | 1640 | 0.4634          | 0.7964   |
| 0.3496        | 5.0   | 2050 | 0.4948          | 0.7952   |
| 0.2985        | 6.0   | 2460 | 0.5068          | 0.7946   |
| 0.2571        | 7.0   | 2870 | 0.5432          | 0.7838   |
| 0.2182        | 8.0   | 3280 | 0.6079          | 0.7873   |


### Framework versions

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