---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- matched_accuracy
- missmatched_accuracy
model-index:
- name: bert-base-uncased-finetuned-LoRA-MNLI
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: glue
      type: glue
      args: mnli
    metrics:
    - name: Matched Accuracy
      type: matched_accuracy
      value: 0.8357615894039735
    - name: Missmatched Accuracy
      type: missmatched_accuracy
      value: 0.842046379170057
---

<!-- 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. -->

# bert-base-uncased-finetuned-lora-mnli

This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the glue dataset.
It achieves the following results on the evaluation set:
- Matched Accuracy: 0.8358
- Missmatched Accuracy: 0.8420
- trainable model parameters: 1181955
- all model parameters: 110666502
- percentage of trainable model parameters: 1.07%

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 5e-04
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- weight_decay: 0.01
- rank: 32
- lora_alpha: 16
- lora_dropout: 0.05
- num_epochs: 5