Add evaluation results on the default config and test split of billsum
#1
by
autoevaluator
HF Staff
- opened
README.md
CHANGED
|
@@ -113,6 +113,42 @@ widget:
|
|
| 113 |
medical parole hearing or medical parole release is scheduled for an inmate receiving
|
| 114 |
medical parole consideration, regardless of whether the inmate is sentenced either
|
| 115 |
determinately or indeterminately.'
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 116 |
---
|
| 117 |
|
| 118 |
# Longformer Encoder-Decoder (LED) fine-tuned on Billsum
|
|
|
|
| 113 |
medical parole hearing or medical parole release is scheduled for an inmate receiving
|
| 114 |
medical parole consideration, regardless of whether the inmate is sentenced either
|
| 115 |
determinately or indeterminately.'
|
| 116 |
+
model-index:
|
| 117 |
+
- name: Artifact-AI/led_base_16384_billsum_summarization
|
| 118 |
+
results:
|
| 119 |
+
- task:
|
| 120 |
+
type: summarization
|
| 121 |
+
name: Summarization
|
| 122 |
+
dataset:
|
| 123 |
+
name: billsum
|
| 124 |
+
type: billsum
|
| 125 |
+
config: default
|
| 126 |
+
split: test
|
| 127 |
+
metrics:
|
| 128 |
+
- name: ROUGE-1
|
| 129 |
+
type: rouge
|
| 130 |
+
value: 47.6721
|
| 131 |
+
verified: true
|
| 132 |
+
- name: ROUGE-2
|
| 133 |
+
type: rouge
|
| 134 |
+
value: 26.7372
|
| 135 |
+
verified: true
|
| 136 |
+
- name: ROUGE-L
|
| 137 |
+
type: rouge
|
| 138 |
+
value: 34.5681
|
| 139 |
+
verified: true
|
| 140 |
+
- name: ROUGE-LSUM
|
| 141 |
+
type: rouge
|
| 142 |
+
value: 41.5295
|
| 143 |
+
verified: true
|
| 144 |
+
- name: loss
|
| 145 |
+
type: loss
|
| 146 |
+
value: 2.079916000366211
|
| 147 |
+
verified: true
|
| 148 |
+
- name: gen_len
|
| 149 |
+
type: gen_len
|
| 150 |
+
value: 128.8152
|
| 151 |
+
verified: true
|
| 152 |
---
|
| 153 |
|
| 154 |
# Longformer Encoder-Decoder (LED) fine-tuned on Billsum
|