---
language:
- en
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: distilbert_add_GLUE_Experiment_logit_kd_qnli
  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: 0.5883214351089145
---

<!-- 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_add_GLUE_Experiment_logit_kd_qnli

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: 0.3978
- Accuracy: 0.5883

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.4154        | 1.0   | 410  | 0.3986          | 0.5779   |
| 0.3986        | 2.0   | 820  | 0.3978          | 0.5883   |
| 0.3909        | 3.0   | 1230 | 0.3990          | 0.5887   |
| 0.384         | 4.0   | 1640 | 0.3988          | 0.5913   |
| 0.3761        | 5.0   | 2050 | 0.4001          | 0.5900   |
| 0.3634        | 6.0   | 2460 | 0.4026          | 0.6121   |
| 0.3413        | 7.0   | 2870 | 0.4068          | 0.6174   |


### Framework versions

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