m-newhauser commited on
Commit
95a34f4
1 Parent(s): 9f3a1d8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +19 -25
README.md CHANGED
@@ -1,51 +1,45 @@
1
  ---
2
  language:
3
  - en
4
- license: apache-2.0
 
5
  tags:
6
  - text-classification
7
  - transformers
8
  - pytorch
9
  - generated_from_keras_callback
 
 
 
10
  datasets:
11
  - m-newhauser/senator-tweets
12
- model-index:
13
- - name: distilbert-political-tweets
14
- results: []
 
 
15
  ---
16
 
17
- <!-- This model card has been generated automatically according to the information Keras had access to. You should
18
- probably proofread and complete it, then remove this comment. -->
19
 
20
- # distilbert-political-tweets
21
-
22
- This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the m-newhauser/senator-tweets dataset.
23
  It achieves the following results on the evaluation set:
24
-
 
25
 
26
  ## Model description
27
 
28
- More information needed
29
-
30
- ## Intended uses & limitations
31
-
32
- More information needed
33
-
34
- ## Training and evaluation data
35
 
36
- More information needed
37
-
38
- ## Training procedure
39
 
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
- - optimizer: None
44
  - training_precision: float32
45
-
46
- ### Training results
47
-
48
-
49
 
50
  ### Framework versions
51
 
 
1
  ---
2
  language:
3
  - en
4
+ license: lgpl-3.0
5
+ library_name: pytorch
6
  tags:
7
  - text-classification
8
  - transformers
9
  - pytorch
10
  - generated_from_keras_callback
11
+ metrics:
12
+ - accuracy
13
+ - f1
14
  datasets:
15
  - m-newhauser/senator-tweets
16
+ widget:
17
+ - text: "This pandemic has shown us clearly the vulgarity of our healthcare system. Highest costs in the world, yet not enough nurses or doctors. Many millions uninsured, while insurance company profits soar. The struggle continues. Healthcare is a human right. Medicare for all."
18
+ example_title: "Bernie Sanders (D)"
19
+ - text: "Team Biden would rather fund the Ayatollah's Death to America regime than allow Americans to produce energy for our own domestic consumption."
20
+ example_title: "Ted Cruz (R)"
21
  ---
22
 
23
+ # distilbert-political-tweets 🗣 🇺🇸
 
24
 
25
+ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the [m-newhauser/senator-tweets](https://huggingface.co/datasets/m-newhauser/senator-tweets) dataset, which contains all tweets made by United States senators during the first year of the Biden Administration.
 
 
26
  It achieves the following results on the evaluation set:
27
+ * Accuracy: 0.9076
28
+ * F1: 0.9117
29
 
30
  ## Model description
31
 
32
+ The goal of this model is to classify short pieces of text as having either Democratic or Republican sentiment. The model was fine-tuned on 99,693 tweets (51.6% Democrat, 48.4% Republican) made by US senators in 2021.
 
 
 
 
 
 
33
 
34
+ Model accuracy may not hold up on pieces of text longer than a tweet.
 
 
35
 
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
+ - optimizer: Adam
40
  - training_precision: float32
41
+ - learning_rate = 5e-5
42
+ - num_epochs = 5
 
 
43
 
44
  ### Framework versions
45