Tristan Thrush
commited on
Commit
·
c24edc7
1
Parent(s):
79771c0
Add evaluation results on emotion
Browse filesBeep boop, I am a bot from Hugging Face's automatic evaluation service! Your model has been evaluated on the [emotion](https://huggingface.co/datasets/emotion) dataset. Accept this pull request to see the results displayed on the [Hub leaderboard](https://huggingface.co/spaces/autoevaluate/leaderboards?dataset=emotion). Evaluate your model on more datasets [here](https://huggingface.co/spaces/autoevaluate/autoevaluate?dataset=emotion).
README.md
CHANGED
|
@@ -77,6 +77,63 @@ model-index:
|
|
| 77 |
type: matthews_correlation
|
| 78 |
value: 0.8920254536671932
|
| 79 |
verified: true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 80 |
---
|
| 81 |
|
| 82 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 77 |
type: matthews_correlation
|
| 78 |
value: 0.8920254536671932
|
| 79 |
verified: true
|
| 80 |
+
- task:
|
| 81 |
+
type: text-classification
|
| 82 |
+
name: Text Classification
|
| 83 |
+
dataset:
|
| 84 |
+
name: emotion
|
| 85 |
+
type: emotion
|
| 86 |
+
config: default
|
| 87 |
+
split: validation
|
| 88 |
+
metrics:
|
| 89 |
+
- name: Accuracy
|
| 90 |
+
type: accuracy
|
| 91 |
+
value: 0.928
|
| 92 |
+
verified: true
|
| 93 |
+
- name: Precision Macro
|
| 94 |
+
type: precision
|
| 95 |
+
value: 0.9021100779342405
|
| 96 |
+
verified: true
|
| 97 |
+
- name: Precision Micro
|
| 98 |
+
type: precision
|
| 99 |
+
value: 0.928
|
| 100 |
+
verified: true
|
| 101 |
+
- name: Precision Weighted
|
| 102 |
+
type: precision
|
| 103 |
+
value: 0.9280919251001837
|
| 104 |
+
verified: true
|
| 105 |
+
- name: Recall Macro
|
| 106 |
+
type: recall
|
| 107 |
+
value: 0.8968051962257172
|
| 108 |
+
verified: true
|
| 109 |
+
- name: Recall Micro
|
| 110 |
+
type: recall
|
| 111 |
+
value: 0.928
|
| 112 |
+
verified: true
|
| 113 |
+
- name: Recall Weighted
|
| 114 |
+
type: recall
|
| 115 |
+
value: 0.928
|
| 116 |
+
verified: true
|
| 117 |
+
- name: F1 Macro
|
| 118 |
+
type: f1
|
| 119 |
+
value: 0.8991718089322509
|
| 120 |
+
verified: true
|
| 121 |
+
- name: F1 Micro
|
| 122 |
+
type: f1
|
| 123 |
+
value: 0.928
|
| 124 |
+
verified: true
|
| 125 |
+
- name: F1 Weighted
|
| 126 |
+
type: f1
|
| 127 |
+
value: 0.9279314819862883
|
| 128 |
+
verified: true
|
| 129 |
+
- name: loss
|
| 130 |
+
type: loss
|
| 131 |
+
value: 0.20090055465698242
|
| 132 |
+
verified: true
|
| 133 |
+
- name: pearsonr
|
| 134 |
+
type: pearsonr
|
| 135 |
+
value: 0.9157453001659976
|
| 136 |
+
verified: true
|
| 137 |
---
|
| 138 |
|
| 139 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|