Chima207 commited on
Commit
be8d123
·
verified ·
1 Parent(s): 600f8c2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +20 -5
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 the None dataset.
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
- More information needed
 
 
32
 
33
  ## Intended uses & limitations
34
 
35
- More information needed
 
 
 
 
 
 
 
36
 
37
  ## Training and evaluation data
38
 
39
- More information needed
 
 
 
 
 
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