Elron commited on
Commit
9a2f6f0
1 Parent(s): 27e031e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +17 -12
README.md CHANGED
@@ -5,34 +5,39 @@ tags:
5
  metrics:
6
  - accuracy
7
  model-index:
8
- - name: deberta-v3-large-irony-lr8e-6-gas2-ls0.1
9
  results: []
10
  ---
11
 
12
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
- should probably proofread and complete it, then remove this comment. -->
14
 
15
- # deberta-v3-large-irony-lr8e-6-gas2-ls0.1
16
-
17
- This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on an unknown dataset.
18
- It achieves the following results on the evaluation set:
19
- - Loss: 0.7673
20
- - Accuracy: 0.7675
21
 
22
  ## Model description
23
 
24
- More information needed
 
 
 
 
 
 
 
 
 
25
 
26
  ## Intended uses & limitations
27
 
28
- More information needed
29
 
30
  ## Training and evaluation data
31
 
32
- More information needed
33
 
34
  ## Training procedure
35
 
 
 
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
 
5
  metrics:
6
  - accuracy
7
  model-index:
8
+ - name: deberta-v3-large
9
  results: []
10
  ---
11
 
12
+ # deberta-v3-large-irony
 
13
 
14
+ This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on an [tweet_eval](https://huggingface.co/datasets/tweet_eval) dataset.
 
 
 
 
 
15
 
16
  ## Model description
17
 
18
+ Test set results:
19
+
20
+ | Model | Emotion | Hate | Irony | Offensive | Sentiment |
21
+ | ------------- | ------------- | ------------- | ------------- | ------------- | ------------- |
22
+ | deberta-v3-large | **86.3** | **61.3** | **87.1** | **86.4** | **73.9** |
23
+ | BERTweet | 79.3 | - | 82.1 | 79.5 | 73.4 |
24
+ | RoB-RT | 79.5 | 52.3 | 61.7 | 80.5 | 69.3 |
25
+
26
+ [source:papers_with_code](https://paperswithcode.com/sota/sentiment-analysis-on-tweeteval)
27
+
28
 
29
  ## Intended uses & limitations
30
 
31
+ Classifying attributes of interest on tweeter like data.
32
 
33
  ## Training and evaluation data
34
 
35
+ [tweet_eval](https://huggingface.co/datasets/tweet_eval) dataset.
36
 
37
  ## Training procedure
38
 
39
+ Fine tuned and evaluated with [run_glue.py]()
40
+
41
  ### Training hyperparameters
42
 
43
  The following hyperparameters were used during training: