---
language:
- en
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: distilbert_sa_GLUE_Experiment_logit_kd_qnli_192
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: GLUE QNLI
      type: glue
      config: qnli
      split: validation
      args: qnli
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.5870400878638111
---

<!-- 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. -->

# distilbert_sa_GLUE_Experiment_logit_kd_qnli_192

This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the GLUE QNLI dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3931
- Accuracy: 0.5870

## 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
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.4083        | 1.0   | 410  | 0.3946          | 0.5735   |
| 0.3936        | 2.0   | 820  | 0.3931          | 0.5870   |
| 0.3843        | 3.0   | 1230 | 0.3935          | 0.5863   |
| 0.3766        | 4.0   | 1640 | 0.3980          | 0.5858   |
| 0.3699        | 5.0   | 2050 | 0.3996          | 0.5781   |
| 0.3636        | 6.0   | 2460 | 0.4112          | 0.5795   |
| 0.3572        | 7.0   | 2870 | 0.4269          | 0.5667   |


### Framework versions

- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2