---
library_name: transformers
language:
- en
license: apache-2.0
base_model: gokulsrinivasagan/tinybert_base_train_kd
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- spearmanr
model-index:
- name: tinybert_base_train_kd_stsb
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: GLUE STSB
      type: glue
      args: stsb
    metrics:
    - name: Spearmanr
      type: spearmanr
      value: 0.8229059501737404
---

<!-- 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_kd_stsb

This model is a fine-tuned version of [gokulsrinivasagan/tinybert_base_train_kd](https://huggingface.co/gokulsrinivasagan/tinybert_base_train_kd) on the GLUE STSB dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7127
- Pearson: 0.8275
- Spearmanr: 0.8229
- Combined Score: 0.8252

## 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 | Pearson | Spearmanr | Combined Score |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|:--------------:|
| 2.613         | 1.0   | 23   | 2.5624          | 0.1145  | 0.1287    | 0.1216         |
| 1.8186        | 2.0   | 46   | 1.1171          | 0.7169  | 0.7142    | 0.7155         |
| 1.1222        | 3.0   | 69   | 1.0925          | 0.7803  | 0.7822    | 0.7813         |
| 0.8374        | 4.0   | 92   | 0.7486          | 0.8170  | 0.8122    | 0.8146         |
| 0.7145        | 5.0   | 115  | 0.7349          | 0.8232  | 0.8204    | 0.8218         |
| 0.5299        | 6.0   | 138  | 0.7158          | 0.8318  | 0.8265    | 0.8292         |
| 0.4359        | 7.0   | 161  | 0.7249          | 0.8288  | 0.8267    | 0.8278         |
| 0.3798        | 8.0   | 184  | 0.7129          | 0.8281  | 0.8235    | 0.8258         |
| 0.3253        | 9.0   | 207  | 0.7902          | 0.8171  | 0.8150    | 0.8161         |
| 0.277         | 10.0  | 230  | 0.7336          | 0.8229  | 0.8195    | 0.8212         |
| 0.255         | 11.0  | 253  | 0.7127          | 0.8275  | 0.8229    | 0.8252         |
| 0.2257        | 12.0  | 276  | 0.7646          | 0.8233  | 0.8216    | 0.8225         |
| 0.204         | 13.0  | 299  | 0.8714          | 0.8245  | 0.8235    | 0.8240         |
| 0.1957        | 14.0  | 322  | 0.7891          | 0.8213  | 0.8179    | 0.8196         |
| 0.1725        | 15.0  | 345  | 0.7348          | 0.8230  | 0.8193    | 0.8212         |
| 0.1621        | 16.0  | 368  | 0.7909          | 0.8179  | 0.8149    | 0.8164         |


### Framework versions

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