---
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
base_model: duraad/nep-spell-mbart-new
model-index:
- name: nep-spell-mbart-new
  results: []
---

<!-- 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. -->

# nep-spell-mbart-new

This model is a fine-tuned version of [duraad/nep-spell-mbart-new](https://huggingface.co/duraad/nep-spell-mbart-new) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0020
- Accuracy: 0.7987
- Precision: 0.7987
- Recall: 0.7987
- F1: 0.7987
- Exact Match: 0.7987

## 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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     | Exact Match |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:-----------:|
| 0.0046        | 0.79  | 1000 | 0.0030          | 0.75     | 0.75      | 0.75   | 0.75   | 0.75        |
| 0.002         | 1.57  | 2000 | 0.0024          | 0.7799   | 0.7799    | 0.7799 | 0.7799 | 0.7799      |
| 0.0008        | 2.36  | 3000 | 0.0020          | 0.7987   | 0.7987    | 0.7987 | 0.7987 | 0.7987      |


### Framework versions

- Transformers 4.37.0
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.1