Add evaluation results on the samsum config and test split of samsum
#1
by
autoevaluator
HF staff
- opened
README.md
CHANGED
|
@@ -5,9 +5,45 @@ tags:
|
|
| 5 |
language:
|
| 6 |
- en
|
| 7 |
widget:
|
| 8 |
-
- text: "I love AutoTrain
|
| 9 |
co2_eq_emissions:
|
| 10 |
emissions: 4.325625308048844
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
# Model Trained Using AutoTrain
|
|
|
|
| 5 |
language:
|
| 6 |
- en
|
| 7 |
widget:
|
| 8 |
+
- text: "I love AutoTrain \U0001F917"
|
| 9 |
co2_eq_emissions:
|
| 10 |
emissions: 4.325625308048844
|
| 11 |
+
model-index:
|
| 12 |
+
- name: YtBig/subtitle-v2
|
| 13 |
+
results:
|
| 14 |
+
- task:
|
| 15 |
+
type: summarization
|
| 16 |
+
name: Summarization
|
| 17 |
+
dataset:
|
| 18 |
+
name: samsum
|
| 19 |
+
type: samsum
|
| 20 |
+
config: samsum
|
| 21 |
+
split: test
|
| 22 |
+
metrics:
|
| 23 |
+
- name: ROUGE-1
|
| 24 |
+
type: rouge
|
| 25 |
+
value: 20.8518
|
| 26 |
+
verified: true
|
| 27 |
+
- name: ROUGE-2
|
| 28 |
+
type: rouge
|
| 29 |
+
value: 6.2893
|
| 30 |
+
verified: true
|
| 31 |
+
- name: ROUGE-L
|
| 32 |
+
type: rouge
|
| 33 |
+
value: 18.6895
|
| 34 |
+
verified: true
|
| 35 |
+
- name: ROUGE-LSUM
|
| 36 |
+
type: rouge
|
| 37 |
+
value: 19.3197
|
| 38 |
+
verified: true
|
| 39 |
+
- name: loss
|
| 40 |
+
type: loss
|
| 41 |
+
value: 3.1161859035491943
|
| 42 |
+
verified: true
|
| 43 |
+
- name: gen_len
|
| 44 |
+
type: gen_len
|
| 45 |
+
value: 14.9915
|
| 46 |
+
verified: true
|
| 47 |
---
|
| 48 |
|
| 49 |
# Model Trained Using AutoTrain
|