Update README.md
Browse files
README.md
CHANGED
|
@@ -1,4 +1,3 @@
|
|
| 1 |
-
|
| 2 |
---
|
| 3 |
library_name: transformers
|
| 4 |
tags:
|
|
@@ -6,32 +5,61 @@ tags:
|
|
| 6 |
- text-classification
|
| 7 |
base_model: google-bert/bert-base-multilingual-uncased
|
| 8 |
widget:
|
| 9 |
-
- text:
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
-
#
|
| 13 |
-
|
| 14 |
-
- Problem type: Text Classification
|
| 15 |
-
|
| 16 |
-
## Validation Metrics
|
| 17 |
-
loss: 0.157407745718956
|
| 18 |
-
|
| 19 |
-
f1_macro: 0.9613886456444749
|
| 20 |
|
| 21 |
-
|
| 22 |
|
| 23 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
|
| 25 |
-
|
| 26 |
|
| 27 |
-
|
|
|
|
| 28 |
|
| 29 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
tags:
|
|
|
|
| 5 |
- text-classification
|
| 6 |
base_model: google-bert/bert-base-multilingual-uncased
|
| 7 |
widget:
|
| 8 |
+
- text: I love AutoTrain
|
| 9 |
+
license: apache-2.0
|
| 10 |
---
|
| 11 |
|
| 12 |
+
# 📚 Institutional Books Pipeline
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
|
| 14 |
+
## Training data
|
| 15 |
|
| 16 |
+
## Input format
|
| 17 |
+
Text, formatted as follows:
|
| 18 |
+
```
|
| 19 |
+
Title: Full title of the book
|
| 20 |
+
Author: Lorem Ipsum
|
| 21 |
+
Year: 1852
|
| 22 |
+
Language: English
|
| 23 |
+
General Note: A great book
|
| 24 |
+
```
|
| 25 |
|
| 26 |
+
All of the fields listed in this example are optional.
|
| 27 |
|
| 28 |
+
## Categories
|
| 29 |
+
First level of the [Library of Congress Classification Outline](https://www.loc.gov/catdir/cpso/lcco/)
|
| 30 |
|
| 31 |
+
- GENERAL WORKS
|
| 32 |
+
- PHILOSOPHY. PSYCHOLOGY. RELIGION
|
| 33 |
+
- AUXILIARY SCIENCES OF HISTORY
|
| 34 |
+
- WORLD HISTORY AND HISTORY OF EUROPE, ASIA, AFRICA, AUSTRALIA, NEW ZEALAND, ETC.
|
| 35 |
+
- HISTORY OF THE AMERICAS
|
| 36 |
+
- GEOGRAPHY. ANTHROPOLOGY. RECREATION
|
| 37 |
+
- SOCIAL SCIENCES
|
| 38 |
+
- POLITICAL SCIENCE
|
| 39 |
+
- LAW
|
| 40 |
+
- EDUCATION
|
| 41 |
+
- MUSIC AND BOOKS ON MUSIC
|
| 42 |
+
- FINE ARTS
|
| 43 |
+
- LANGUAGE AND LITERATURE
|
| 44 |
+
- SCIENCE
|
| 45 |
+
- MEDICINE
|
| 46 |
+
- AGRICULTURE
|
| 47 |
+
- TECHNOLOGY
|
| 48 |
+
- MILITARY SCIENCE
|
| 49 |
+
- NAVAL SCIENCE
|
| 50 |
+
- BIBLIOGRAPHY. LIBRARY SCIENCE. INFORMATION RESOURCES (GENERAL)
|
| 51 |
|
| 52 |
+
## Validation Metrics
|
| 53 |
+
| Metric | Value |
|
| 54 |
+
| --- | --- |
|
| 55 |
+
| loss | 0.157407745718956 |
|
| 56 |
+
| f1_macro | 0.9613886456444749 |
|
| 57 |
+
| f1_micro | 0.9694 |
|
| 58 |
+
| f1_weighted | 0.9693030681223207 |
|
| 59 |
+
| precision_macro | 0.9679892485977634 |
|
| 60 |
+
| precision_micro | 0.9694 |
|
| 61 |
+
| precision_weighted | 0.9695713537396466 |
|
| 62 |
+
| recall_macro | 0.9560667596679707 |
|
| 63 |
+
| recall_micro | 0.9694 |
|
| 64 |
+
| recall_weighted | 0.9694 |
|
| 65 |
+
| accuracy | 0.9694 |
|