metadata

license: apache-2.0
base_model: distilbert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: food_type_classification_model
    results: []

food_type_classification_model

This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0335
Accuracy: 0.9946

Model description

This model can categorize a given food product title into Plant-based ("PLANT_BASED") or Animal-based("ANIMAL_BASED").

Intended uses & limitations

"whey" is an "ANIMAL_BASED" product derived from Cow's milk. Therefore it must be categorized as as an ANIMAL_BASED food product.

Example usage:

from transformers import pipeline

text = "whey"
classifier = pipeline("text-classification", model="nish-j/food_type_classification_model")
classifier(text)

>>> [{'label': 'ANIMAL_BASED', 'score': 0.9941352605819702}]

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	325	0.0324	0.9938
0.0347	2.0	650	0.0335	0.9946

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu121
Datasets 2.15.0
Tokenizers 0.15.0