Add evaluation results on the samsum config and validation split of samsum
#6
by
autoevaluator
HF Staff
- opened
README.md
CHANGED
|
@@ -104,6 +104,39 @@ model-index:
|
|
| 104 |
type: gen_len
|
| 105 |
value: 25.0234
|
| 106 |
verified: true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 107 |
---
|
| 108 |
|
| 109 |
### Pegasus Models
|
|
|
|
| 104 |
type: gen_len
|
| 105 |
value: 25.0234
|
| 106 |
verified: true
|
| 107 |
+
- task:
|
| 108 |
+
type: summarization
|
| 109 |
+
name: Summarization
|
| 110 |
+
dataset:
|
| 111 |
+
name: samsum
|
| 112 |
+
type: samsum
|
| 113 |
+
config: samsum
|
| 114 |
+
split: validation
|
| 115 |
+
metrics:
|
| 116 |
+
- name: ROUGE-1
|
| 117 |
+
type: rouge
|
| 118 |
+
value: 21.9676
|
| 119 |
+
verified: true
|
| 120 |
+
- name: ROUGE-2
|
| 121 |
+
type: rouge
|
| 122 |
+
value: 4.2575
|
| 123 |
+
verified: true
|
| 124 |
+
- name: ROUGE-L
|
| 125 |
+
type: rouge
|
| 126 |
+
value: 17.3584
|
| 127 |
+
verified: true
|
| 128 |
+
- name: ROUGE-LSUM
|
| 129 |
+
type: rouge
|
| 130 |
+
value: 19.0
|
| 131 |
+
verified: true
|
| 132 |
+
- name: loss
|
| 133 |
+
type: loss
|
| 134 |
+
value: 3.033092975616455
|
| 135 |
+
verified: true
|
| 136 |
+
- name: gen_len
|
| 137 |
+
type: gen_len
|
| 138 |
+
value: 19.6956
|
| 139 |
+
verified: true
|
| 140 |
---
|
| 141 |
|
| 142 |
### Pegasus Models
|