Update README.md
Browse files
README.md
CHANGED
|
@@ -12,9 +12,6 @@ widget:
|
|
| 12 |
example_title: "Negative"
|
| 13 |
---
|
| 14 |
|
| 15 |
-
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
| 16 |
-
probably proofread and complete it, then remove this comment. -->
|
| 17 |
-
|
| 18 |
# distilbert-base-future
|
| 19 |
## Table of Contents
|
| 20 |
|
|
@@ -23,7 +20,7 @@ probably proofread and complete it, then remove this comment. -->
|
|
| 23 |
- [Training and evaluation data](#training_and_evaluation_data)
|
| 24 |
- [Training procedure](#training_procedure)
|
| 25 |
|
| 26 |
-
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on
|
| 27 |
It achieves the following results on the evaluation set:
|
| 28 |
- Train Loss: 0.1142
|
| 29 |
- Train Sparse Categorical Accuracy: 0.9613
|
|
@@ -33,15 +30,24 @@ It achieves the following results on the evaluation set:
|
|
| 33 |
|
| 34 |
## Model description
|
| 35 |
|
| 36 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
|
| 38 |
## Intended uses & limitations
|
| 39 |
|
| 40 |
-
|
|
|
|
| 41 |
|
| 42 |
## Training and evaluation data
|
| 43 |
|
| 44 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
|
| 46 |
## Training procedure
|
| 47 |
|
|
|
|
| 12 |
example_title: "Negative"
|
| 13 |
---
|
| 14 |
|
|
|
|
|
|
|
|
|
|
| 15 |
# distilbert-base-future
|
| 16 |
## Table of Contents
|
| 17 |
|
|
|
|
| 20 |
- [Training and evaluation data](#training_and_evaluation_data)
|
| 21 |
- [Training procedure](#training_procedure)
|
| 22 |
|
| 23 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the [future-statements dataset](https://huggingface.co/datasets/fidsinn/future-statements).
|
| 24 |
It achieves the following results on the evaluation set:
|
| 25 |
- Train Loss: 0.1142
|
| 26 |
- Train Sparse Categorical Accuracy: 0.9613
|
|
|
|
| 30 |
|
| 31 |
## Model description
|
| 32 |
|
| 33 |
+
- The model was created by graduate students [D. Baradari](https://huggingface.co/Dunya), [F. Bartels](https://huggingface.co/fidsinn), A. Dewald, [J. Peters](https://huggingface.co/jpeters92) as part of a data science module of the University of Leipzig.
|
| 34 |
+
- Model was created on 11/08/22.
|
| 35 |
+
- This is version 1.0
|
| 36 |
+
- The model is a text classification model which is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased)
|
| 37 |
+
- Questions and comments can be send via the [community tab](https://huggingface.co/fidsinn/distilbert-base-future/discussions)
|
| 38 |
|
| 39 |
## Intended uses & limitations
|
| 40 |
|
| 41 |
+
- The primary intended use is the classification of input into a future or non-future sentence/statement.
|
| 42 |
+
- The model is primarily intended to be used by researchers to filter or label a large number of sentences according to the grammatical tense of the input.
|
| 43 |
|
| 44 |
## Training and evaluation data
|
| 45 |
|
| 46 |
+
- [Distilbert-base-future model](https://huggingface.co/fidsinn/distilbert-base-future) was trained and evaluated on the [future-statements dataset](https://huggingface.co/datasets/fidsinn/future-statements).
|
| 47 |
+
- [future-statements](https://huggingface.co/datasets/fidsinn/future-statements) is a dataset collected manually and automatically by graduate students [D. Baradari](https://huggingface.co/Dunya), [F. Bartels](https://huggingface.co/fidsinn), A. Dewald, [J. Peters](https://huggingface.co/jpeters92) of the University of Leipzig.
|
| 48 |
+
- We collected 2500 statements, 50% of which relate to future events and 50% of which relate to non-future events.
|
| 49 |
+
- The sole purpose of the dataset was the fine-tuning process of this model.
|
| 50 |
+
- Additional information on the dataset can be found on Huggingface: [future-statements dataset](https://huggingface.co/datasets/fidsinn/future-statements).
|
| 51 |
|
| 52 |
## Training procedure
|
| 53 |
|