metadata

license: apache-2.0
base_model: distilbert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: amazon_review_classification
    results: []
widget:
  - text: |-
      Title: These earrings are much smaller than pictured. They are so tiny 
       Text: The online picture is deceiving. They are shown much larger than their actual size. Was very disappointed
    output:
      - label: Not Recommended
        score: 0.783
      - label: Negative Experience
        score: 0.087
      - label: Low Quality
        score: 0.04
      - label: Poor Service
        score: 0.026
      - label: Overpriced
        score: 0.021
      - label: Positive Experience
        score: 0.015
      - label: Excellent Service
        score: 0.009
      - label: Great Value
        score: 0.007
      - label: Highly Recommended
        score: 0.006
      - label: High Quality
        score: 0.005

amazon_review_classification

This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.3976
Accuracy: 0.6732

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: 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	115	1.0703	0.6732
No log	2.0	230	1.2393	0.6341
No log	3.0	345	1.1084	0.6683
No log	4.0	460	1.1262	0.6829
0.3201	5.0	575	1.3179	0.6732
0.3201	6.0	690	1.3832	0.6585
0.3201	7.0	805	1.2997	0.6683
0.3201	8.0	920	1.3872	0.6634
0.0863	9.0	1035	1.3832	0.6634
0.0863	10.0	1150	1.3976	0.6732

Framework versions

Transformers 4.38.2
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2

Usage

from transformers import pipeline

classifier = pipeline("sentiment-analysis", model="eren23/amazon_review_classification")
classifier(text)