CarelvNiekerk commited on
Commit
eac02c5
1 Parent(s): 6da7c27

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +59 -0
README.md CHANGED
@@ -1,3 +1,62 @@
1
  ---
 
 
2
  license: apache-2.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ language:
3
+ - en
4
  license: apache-2.0
5
+ tags:
6
+ - roberta
7
+ - classification
8
+ - dialog state tracking
9
+ - conversational system
10
+ - task-oriented dialog
11
+ datasets:
12
+ - ConvLab/sgd
13
+ metrics:
14
+ - Joint Goal Accuracy
15
+ - Slot F1
16
+
17
+ model-index:
18
+ - name: setsumbt-dst-sgd
19
+ results:
20
+ - task:
21
+ type: classification
22
+ name: dialog state tracking
23
+ dataset:
24
+ type: ConvLab/sgd
25
+ name: SGD
26
+ split: test
27
+ metrics:
28
+ - type: Joint Goal Accuracy
29
+ value: 20.0
30
+ name: JGA
31
+ - type: Slot F1
32
+ value: 58.8
33
+ name: Slot F1
34
+
35
  ---
36
+
37
+ # SetSUMBT-dst-sgd
38
+
39
+ This model is a fine-tuned version [SetSUMBT](https://github.com/ConvLab/ConvLab-3/tree/master/convlab/dst/setsumbt) of [roberta-base](https://huggingface.co/roberta-base) on [Schema-Guided Dialog](https://huggingface.co/datasets/ConvLab/sgd).
40
+
41
+ Refer to [ConvLab-3](https://github.com/ConvLab/ConvLab-3) for model description and usage.
42
+
43
+ ## Training procedure
44
+
45
+ ### Training hyperparameters
46
+
47
+ The following hyperparameters were used during training:
48
+ - learning_rate: 0.00001
49
+ - train_batch_size: 3
50
+ - eval_batch_size: 16
51
+ - seed: 0
52
+ - gradient_accumulation_steps: 1
53
+ - optimizer: AdamW
54
+ - lr_scheduler_type: linear
55
+ - num_epochs: 50.0
56
+
57
+ ### Framework versions
58
+
59
+ - Transformers 4.17.0
60
+ - Pytorch 1.8.0+cu110
61
+ - Datasets 2.3.2
62
+ - Tokenizers 0.12.1