Text Classification
Transformers
TensorBoard
Safetensors
English
distilbert
Generated from Trainer
text-embeddings-inference
Instructions to use Chima207/distilbert_amazon_book_classification with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Chima207/distilbert_amazon_book_classification with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Chima207/distilbert_amazon_book_classification")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("Chima207/distilbert_amazon_book_classification") model = AutoModelForSequenceClassification.from_pretrained("Chima207/distilbert_amazon_book_classification", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -8,6 +8,7 @@ metrics:
|
|
| 8 |
- accuracy
|
| 9 |
- precision
|
| 10 |
- recall
|
|
|
|
| 11 |
model-index:
|
| 12 |
- name: distilbert_amazon_book_classification
|
| 13 |
results: []
|
|
@@ -18,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
# distilbert_amazon_book_classification
|
| 20 |
|
| 21 |
-
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
- Loss: 1.4475
|
| 24 |
- Accuracy: 0.5871
|
|
@@ -28,15 +29,29 @@ It achieves the following results on the evaluation set:
|
|
| 28 |
|
| 29 |
## Model description
|
| 30 |
|
| 31 |
-
|
|
|
|
|
|
|
| 32 |
|
| 33 |
## Intended uses & limitations
|
| 34 |
|
| 35 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
|
| 37 |
## Training and evaluation data
|
| 38 |
|
| 39 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
|
| 41 |
## Training procedure
|
| 42 |
|
|
@@ -67,4 +82,4 @@ The following hyperparameters were used during training:
|
|
| 67 |
- Transformers 4.45.2
|
| 68 |
- Pytorch 2.5.1
|
| 69 |
- Datasets 4.1.1
|
| 70 |
-
- Tokenizers 0.20.1
|
|
|
|
| 8 |
- accuracy
|
| 9 |
- precision
|
| 10 |
- recall
|
| 11 |
+
- f1
|
| 12 |
model-index:
|
| 13 |
- name: distilbert_amazon_book_classification
|
| 14 |
results: []
|
|
|
|
| 19 |
|
| 20 |
# distilbert_amazon_book_classification
|
| 21 |
|
| 22 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an [Kaggle Amazon Kindle Books}(https://www.kaggle.com/datasets/asaniczka/amazon-kindle-books-dataset-2023-130k-books) dataset.
|
| 23 |
It achieves the following results on the evaluation set:
|
| 24 |
- Loss: 1.4475
|
| 25 |
- Accuracy: 0.5871
|
|
|
|
| 29 |
|
| 30 |
## Model description
|
| 31 |
|
| 32 |
+
This model is a fine-tuned version of distilbert-base-uncased trained directly on structured Amazon book metadata across 31 standardized Kindle categories.
|
| 33 |
+
|
| 34 |
+
Serving as a clean-data benchmark in comparative analysis, this model evaluates genre classification performance under structured, editorial metadata conditions. It achieves an Accuracy of 58.71% and a Macro F1-Score of 58.65%, demonstrating that high inherent data quality and structured category labels significantly improve the upper-bound performance of transformer architectures.
|
| 35 |
|
| 36 |
## Intended uses & limitations
|
| 37 |
|
| 38 |
+
* Direct classification of structured book descriptions into standard Amazon Kindle categories.
|
| 39 |
+
|
| 40 |
+
* Comparative benchmarking for domain adaptation and cross-domain transfer learning experiments.
|
| 41 |
+
|
| 42 |
+
* May underperform or show sensitivity when applied to highly informal, uncurated, or user-generated text inputs without prior domain adaptation.
|
| 43 |
+
|
| 44 |
+
## Datasets
|
| 45 |
+
* **Amazon-Dataset:** *[Kaggle Amazon Kindle Books Dataset](https://www.kaggle.com/datasets/asaniczka/amazon-kindle-books-dataset-2023-130k-books))*
|
| 46 |
|
| 47 |
## Training and evaluation data
|
| 48 |
|
| 49 |
+
* **Source:** Official Amazon Kindle book product listings and metadata.
|
| 50 |
+
* **Target Taxonomy:** 31 standardized Amazon Kindle categories (e.g., Literature & Fiction, Sci-Fi & Fantasy, Romance, Business & Money).
|
| 51 |
+
* **Input Features:** Concatenated book title and author.
|
| 52 |
+
|
| 53 |
+
* **Metadata Quality:** High quality, structured, and editorially curated product descriptions with minimal noise compared to community-driven tags.
|
| 54 |
+
* **Splits:** Partitioned into stratified (80/20) train and test sets across all 31 target classes.
|
| 55 |
|
| 56 |
## Training procedure
|
| 57 |
|
|
|
|
| 82 |
- Transformers 4.45.2
|
| 83 |
- Pytorch 2.5.1
|
| 84 |
- Datasets 4.1.1
|
| 85 |
+
- Tokenizers 0.20.1
|