Test
Browse files
README.md
CHANGED
@@ -6,56 +6,63 @@ datasets:
|
|
6 |
- glue
|
7 |
metrics:
|
8 |
- accuracy
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
model-index:
|
10 |
- name: autoevaluate-binary-classification
|
11 |
results:
|
12 |
- task:
|
13 |
-
name: Text Classification
|
14 |
type: text-classification
|
|
|
15 |
dataset:
|
16 |
name: glue
|
17 |
type: glue
|
18 |
args: sst2
|
19 |
metrics:
|
20 |
-
-
|
21 |
-
type: accuracy
|
22 |
value: 0.8967889908256881
|
23 |
-
|
24 |
-
|
25 |
-
name: Text Classification
|
26 |
-
dataset:
|
27 |
-
name: glue
|
28 |
-
type: glue
|
29 |
-
config: sst2
|
30 |
-
split: validation
|
31 |
-
metrics:
|
32 |
-
- name: Accuracy
|
33 |
-
type: accuracy
|
34 |
value: 0.8967889908256881
|
|
|
35 |
verified: true
|
36 |
-
-
|
37 |
-
type: precision
|
38 |
value: 0.8898678414096917
|
|
|
39 |
verified: true
|
40 |
-
-
|
41 |
-
type: recall
|
42 |
value: 0.9099099099099099
|
|
|
43 |
verified: true
|
44 |
-
-
|
45 |
-
type: auc
|
46 |
value: 0.967247621453229
|
|
|
47 |
verified: true
|
48 |
-
-
|
49 |
-
type: f1
|
50 |
value: 0.8997772828507795
|
|
|
51 |
verified: true
|
52 |
-
-
|
53 |
-
type: loss
|
54 |
value: 0.30091655254364014
|
|
|
55 |
verified: true
|
56 |
-
-
|
57 |
-
type: matthews_correlation
|
58 |
value: 0.793630584795814
|
|
|
59 |
verified: true
|
60 |
---
|
61 |
|
|
|
6 |
- glue
|
7 |
metrics:
|
8 |
- accuracy
|
9 |
+
name: autoevaluate-binary-classification
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
type: text-classification
|
13 |
+
name: Text Classification
|
14 |
+
dataset:
|
15 |
+
name: glue
|
16 |
+
type: glue
|
17 |
+
config: sst2
|
18 |
+
split: validation
|
19 |
+
metrics:
|
20 |
+
- name: Accuracy
|
21 |
+
type: accuracy
|
22 |
+
value: 0.8967889908256881
|
23 |
+
verified: true
|
24 |
+
foo: 1234
|
25 |
model-index:
|
26 |
- name: autoevaluate-binary-classification
|
27 |
results:
|
28 |
- task:
|
|
|
29 |
type: text-classification
|
30 |
+
name: Text Classification
|
31 |
dataset:
|
32 |
name: glue
|
33 |
type: glue
|
34 |
args: sst2
|
35 |
metrics:
|
36 |
+
- type: accuracy
|
|
|
37 |
value: 0.8967889908256881
|
38 |
+
name: Accuracy
|
39 |
+
- type: accuracy
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
40 |
value: 0.8967889908256881
|
41 |
+
name: Accuracy
|
42 |
verified: true
|
43 |
+
- type: precision
|
|
|
44 |
value: 0.8898678414096917
|
45 |
+
name: Precision
|
46 |
verified: true
|
47 |
+
- type: recall
|
|
|
48 |
value: 0.9099099099099099
|
49 |
+
name: Recall
|
50 |
verified: true
|
51 |
+
- type: auc
|
|
|
52 |
value: 0.967247621453229
|
53 |
+
name: AUC
|
54 |
verified: true
|
55 |
+
- type: f1
|
|
|
56 |
value: 0.8997772828507795
|
57 |
+
name: F1
|
58 |
verified: true
|
59 |
+
- type: loss
|
|
|
60 |
value: 0.30091655254364014
|
61 |
+
name: loss
|
62 |
verified: true
|
63 |
+
- type: matthews_correlation
|
|
|
64 |
value: 0.793630584795814
|
65 |
+
name: matthews_correlation
|
66 |
verified: true
|
67 |
---
|
68 |
|