Add evaluation results on the sst2 config and validation split of glue
#75
by
lewtun
HF staff
- opened
README.md
CHANGED
@@ -10,52 +10,75 @@ 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 |
-
|
26 |
-
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
-
|
31 |
-
|
32 |
-
-
|
33 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
34 |
value: 0.8967889908256881
|
|
|
35 |
verified: true
|
36 |
-
|
37 |
-
|
38 |
value: 0.8898678414096917
|
|
|
39 |
verified: true
|
40 |
-
|
41 |
-
|
42 |
value: 0.9099099099099099
|
|
|
43 |
verified: true
|
44 |
-
|
45 |
-
|
46 |
value: 0.967247621453229
|
|
|
47 |
verified: true
|
48 |
-
-
|
49 |
-
type: f1
|
50 |
value: 0.8997772828507795
|
|
|
51 |
verified: true
|
52 |
-
|
53 |
-
|
54 |
value: 0.30091655254364014
|
|
|
55 |
verified: true
|
56 |
-
-
|
57 |
-
type: matthews_correlation
|
58 |
value: 0.793630584795814
|
|
|
59 |
verified: true
|
60 |
---
|
61 |
|
|
|
10 |
- name: autoevaluate-binary-classification
|
11 |
results:
|
12 |
- task:
|
|
|
13 |
type: text-classification
|
14 |
+
name: Text Classification
|
15 |
dataset:
|
16 |
name: glue
|
17 |
type: glue
|
18 |
args: sst2
|
19 |
metrics:
|
20 |
+
- type: accuracy
|
|
|
21 |
value: 0.8967889908256881
|
22 |
+
name: Accuracy
|
23 |
+
- type: accuracy
|
24 |
+
value: 0.8967889908256881
|
25 |
+
name: Accuracy
|
26 |
+
verified: true
|
27 |
+
- type: precision
|
28 |
+
value: 0.8898678414096917
|
29 |
+
name: Precision
|
30 |
+
verified: true
|
31 |
+
- type: recall
|
32 |
+
value: 0.9099099099099099
|
33 |
+
name: Recall
|
34 |
+
verified: true
|
35 |
+
- type: auc
|
36 |
+
value: 0.967247621453229
|
37 |
+
name: AUC
|
38 |
+
verified: true
|
39 |
+
- type: f1
|
40 |
+
value: 0.8997772828507795
|
41 |
+
name: F1
|
42 |
+
verified: true
|
43 |
+
- type: loss
|
44 |
+
value: 0.30091655254364014
|
45 |
+
name: loss
|
46 |
+
verified: true
|
47 |
+
- type: matthews_correlation
|
48 |
+
value: 0.793630584795814
|
49 |
+
name: matthews_correlation
|
50 |
+
verified: true
|
51 |
+
- type: accuracy
|
52 |
value: 0.8967889908256881
|
53 |
+
name: Accuracy
|
54 |
verified: true
|
55 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOWY0OWI1MDEwOGU0OGU1MDkwN2RhZDIxYWUzNjc0ZTdhYzBlZjZlODY4NjdhYTAzZWQ5YjM5OGE2ZmIzMWQzOSIsInZlcnNpb24iOjF9.hcAWhrsrj1jbkjutDTvsIbfTMW3LCQ5ASMdPRme84tnPETSxMvyD3Jdap24XySAEdglhI-8e7Bzxhriur7CQAQ
|
56 |
+
- type: precision
|
57 |
value: 0.8898678414096917
|
58 |
+
name: Precision
|
59 |
verified: true
|
60 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTZkNTY0N2IyODEwN2Q2YjY5NDk5NTlmNTBhMTIyOGYyNzUzZmE1NjEwNmEzODhkZmZhZmU3OGZmNTdiMDk4OCIsInZlcnNpb24iOjF9.1rIs3ZnUAUjXnd6rAihsUDDtmG8uBNPDdV429_-8RoBijGm9EZoWTg3-naCFAVJC3IMfSrdTKt1PHChcd5aiAw
|
61 |
+
- type: recall
|
62 |
value: 0.9099099099099099
|
63 |
+
name: Recall
|
64 |
verified: true
|
65 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOWFlNmEwNDVkY2JlNDgxOTYwZThhZDc4NTMwOGQ1ZDc5YjM4OTllMTRiMDk3ZTJlZGExNjg0NWYwN2VkZWYyOCIsInZlcnNpb24iOjF9.4L8Wzz4m7InEScIVH7Xv2M0Dvf9ej7K_xzpfV67ckE7Bho4snFQ9NrDihpxloErMuqNgYa16X8b3yRcDtNI-Cw
|
66 |
+
- type: auc
|
67 |
value: 0.967247621453229
|
68 |
+
name: AUC
|
69 |
verified: true
|
70 |
+
- type: f1
|
|
|
71 |
value: 0.8997772828507795
|
72 |
+
name: F1
|
73 |
verified: true
|
74 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiM2ZlMzlmYjI0NjMzNDM5MGY0YzBhMWY3YjNkMGI4MTgzNDBjYzcxMzhiZWIxOWI3MjJiYzkwOTc3YmY1ZGViZCIsInZlcnNpb24iOjF9.ZlLSiUiws0lzlnYzntz8xLcNigC80b9ABzZy53hpxJss1aS-o_Kjv-UZvQCD6Wy9cDNwpuTjCvX8Ouqq9kyBBA
|
75 |
+
- type: loss
|
76 |
value: 0.30091655254364014
|
77 |
+
name: loss
|
78 |
verified: true
|
79 |
+
- type: matthews_correlation
|
|
|
80 |
value: 0.793630584795814
|
81 |
+
name: matthews_correlation
|
82 |
verified: true
|
83 |
---
|
84 |
|