---
license: apache-2.0
base_model: distilbert/distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: API_Detector_3_Distilbert
  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. -->

# my_awesome_model

This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on Custom dataset (3 classes).
It achieves the following results on the evaluation set:
- Loss: 0.6536
- Accuracy: 0.9437

## Model description

Due to lack of training data, this model is not recognizing difference between "order" and "orderline" in sentences. So classify "ORDERLINE" to "MAOORDER" when word "orderline" is in sentence.
This can be solved by one more 'if' condition in further script and this is more efficient way than more training data and its train.

## 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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log        | 1.0   | 15   | 0.8108          | 0.8187   |
| No log        | 2.0   | 30   | 0.6536          | 0.9437   |


### Framework versions

- Transformers 4.40.1
- Pytorch 2.1.0
- Datasets 2.19.0
- Tokenizers 0.19.1