asahi417 commited on
Commit
cb77705
1 Parent(s): b55d407

model update

Browse files
Files changed (2) hide show
  1. README.md +73 -0
  2. metric_summary.json +1 -0
README.md ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ datasets:
3
+ - cardiffnlp/tweet_topic_single
4
+ metrics:
5
+ - f1
6
+ - accuracy
7
+ model-index:
8
+ - name: cardiffnlp/twitter-roberta-base-dec2021-tweet-topic-single-2020
9
+ results:
10
+ - task:
11
+ type: text-classification
12
+ name: Text Classification
13
+ dataset:
14
+ name: cardiffnlp/tweet_topic_single
15
+ type: cardiffnlp/tweet_topic_single
16
+ args: cardiffnlp/tweet_topic_single
17
+ split: test_2021
18
+ metrics:
19
+ - name: F1
20
+ type: f1
21
+ value: 0.10513880685174248
22
+ - name: F1 (macro)
23
+ type: f1_macro
24
+ value: 0.035785101822079314
25
+ - name: Accuracy
26
+ type: accuracy
27
+ value: 0.10513880685174247
28
+ pipeline_tag: text-classification
29
+ widget:
30
+ - text: "I'm sure the {@Tampa Bay Lightning@} would’ve rather faced the Flyers but man does their experience versus the Blue Jackets this year and last help them a lot versus this Islanders team. Another meat grinder upcoming for the good guys"
31
+ example_title: "Example 1"
32
+ - text: "Love to take night time bike rides at the jersey shore. Seaside Heights boardwalk. Beautiful weather. Wishing everyone a safe Labor Day weekend in the US."
33
+ example_title: "Example 2"
34
+ ---
35
+ # cardiffnlp/twitter-roberta-base-dec2021-tweet-topic-single-2020
36
+
37
+ This model is a fine-tuned version of [cardiffnlp/twitter-roberta-base-dec2021](https://huggingface.co/cardiffnlp/twitter-roberta-base-dec2021) on the [tweet_topic_single](https://huggingface.co/datasets/cardiffnlp/tweet_topic_single). This model is fine-tuned on `train_2020` split and validated on `test_2021` split of tweet_topic.
38
+ Fine-tuning script can be found [here](https://huggingface.co/datasets/cardiffnlp/tweet_topic_single/blob/main/lm_finetuning.py). It achieves the following results on the test_2021 set:
39
+
40
+ - F1 (micro): 0.10513880685174248
41
+ - F1 (macro): 0.035785101822079314
42
+ - Accuracy: 0.10513880685174247
43
+
44
+
45
+ ### Usage
46
+
47
+ ```python
48
+ from transformers import pipeline
49
+
50
+ pipe = pipeline("text-classification", "cardiffnlp/twitter-roberta-base-dec2021-tweet-topic-single-2020")
51
+ topic = pipe("Love to take night time bike rides at the jersey shore. Seaside Heights boardwalk. Beautiful weather. Wishing everyone a safe Labor Day weekend in the US.")
52
+ print(topic)
53
+ ```
54
+
55
+ ### Reference
56
+ ```
57
+
58
+ @inproceedings{dimosthenis-etal-2022-twitter,
59
+ title = "{T}witter {T}opic {C}lassification",
60
+ author = "Antypas, Dimosthenis and
61
+ Ushio, Asahi and
62
+ Camacho-Collados, Jose and
63
+ Neves, Leonardo and
64
+ Silva, Vitor and
65
+ Barbieri, Francesco",
66
+ booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
67
+ month = oct,
68
+ year = "2022",
69
+ address = "Gyeongju, Republic of Korea",
70
+ publisher = "International Committee on Computational Linguistics"
71
+ }
72
+
73
+ ```
metric_summary.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"test/eval_loss": 2.080143928527832, "test/eval_f1": 0.10513880685174248, "test/eval_f1_macro": 0.035785101822079314, "test/eval_accuracy": 0.10513880685174247, "test/eval_runtime": 17.589, "test/eval_samples_per_second": 96.253, "test/eval_steps_per_second": 12.053}