Add evaluation results on the default config and test split of emotion
#1
by
autoevaluator
HF staff
- opened
README.md
CHANGED
|
@@ -2,7 +2,8 @@
|
|
| 2 |
---
|
| 3 |
language: en
|
| 4 |
widget:
|
| 5 |
-
- text:
|
|
|
|
| 6 |
tags:
|
| 7 |
- sagemaker
|
| 8 |
- roberta-base
|
|
@@ -13,20 +14,72 @@ datasets:
|
|
| 13 |
model-index:
|
| 14 |
- name: sagemaker-roberta-base-emotion
|
| 15 |
results:
|
| 16 |
-
- task:
|
| 17 |
name: Multi Class Text Classification
|
| 18 |
type: text-classification
|
| 19 |
dataset:
|
| 20 |
-
name:
|
| 21 |
type: emotion
|
| 22 |
metrics:
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
|
| 27 |
-
|
| 28 |
-
|
| 29 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
---
|
| 31 |
## roberta-base
|
| 32 |
|
|
|
|
| 2 |
---
|
| 3 |
language: en
|
| 4 |
widget:
|
| 5 |
+
- text: I am really upset that I have to call up to three times to the number on the
|
| 6 |
+
back of my insurance card for my call to be answer
|
| 7 |
tags:
|
| 8 |
- sagemaker
|
| 9 |
- roberta-base
|
|
|
|
| 14 |
model-index:
|
| 15 |
- name: sagemaker-roberta-base-emotion
|
| 16 |
results:
|
| 17 |
+
- task:
|
| 18 |
name: Multi Class Text Classification
|
| 19 |
type: text-classification
|
| 20 |
dataset:
|
| 21 |
+
name: emotion
|
| 22 |
type: emotion
|
| 23 |
metrics:
|
| 24 |
+
- name: Validation Accuracy
|
| 25 |
+
type: accuracy
|
| 26 |
+
value: 94.1
|
| 27 |
+
- name: Validation F1
|
| 28 |
+
type: f1
|
| 29 |
+
value: 94.13
|
| 30 |
+
- task:
|
| 31 |
+
type: text-classification
|
| 32 |
+
name: Text Classification
|
| 33 |
+
dataset:
|
| 34 |
+
name: emotion
|
| 35 |
+
type: emotion
|
| 36 |
+
config: default
|
| 37 |
+
split: test
|
| 38 |
+
metrics:
|
| 39 |
+
- name: Accuracy
|
| 40 |
+
type: accuracy
|
| 41 |
+
value: 0.931
|
| 42 |
+
verified: true
|
| 43 |
+
- name: Precision Macro
|
| 44 |
+
type: precision
|
| 45 |
+
value: 0.8833042147663716
|
| 46 |
+
verified: true
|
| 47 |
+
- name: Precision Micro
|
| 48 |
+
type: precision
|
| 49 |
+
value: 0.931
|
| 50 |
+
verified: true
|
| 51 |
+
- name: Precision Weighted
|
| 52 |
+
type: precision
|
| 53 |
+
value: 0.9337002742192515
|
| 54 |
+
verified: true
|
| 55 |
+
- name: Recall Macro
|
| 56 |
+
type: recall
|
| 57 |
+
value: 0.9087144572668905
|
| 58 |
+
verified: true
|
| 59 |
+
- name: Recall Micro
|
| 60 |
+
type: recall
|
| 61 |
+
value: 0.931
|
| 62 |
+
verified: true
|
| 63 |
+
- name: Recall Weighted
|
| 64 |
+
type: recall
|
| 65 |
+
value: 0.931
|
| 66 |
+
verified: true
|
| 67 |
+
- name: F1 Macro
|
| 68 |
+
type: f1
|
| 69 |
+
value: 0.8949974527433656
|
| 70 |
+
verified: true
|
| 71 |
+
- name: F1 Micro
|
| 72 |
+
type: f1
|
| 73 |
+
value: 0.931
|
| 74 |
+
verified: true
|
| 75 |
+
- name: F1 Weighted
|
| 76 |
+
type: f1
|
| 77 |
+
value: 0.9318434300647934
|
| 78 |
+
verified: true
|
| 79 |
+
- name: loss
|
| 80 |
+
type: loss
|
| 81 |
+
value: 0.17379647493362427
|
| 82 |
+
verified: true
|
| 83 |
---
|
| 84 |
## roberta-base
|
| 85 |
|