Commit
·
2b0c321
1
Parent(s):
eeb1911
Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator (#3)
Browse files- Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator (04638e9b48a06f66cdc9c63e1cfc914487d49f57)
Co-authored-by: Evaluation Bot <[email protected]>
README.md
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
---
|
| 2 |
language: en
|
|
|
|
| 3 |
tags:
|
| 4 |
- bart
|
| 5 |
- seq2seq
|
| 6 |
- summarization
|
| 7 |
-
license: apache-2.0
|
| 8 |
datasets:
|
| 9 |
- samsum
|
| 10 |
widget:
|
|
@@ -16,30 +16,30 @@ model-index:
|
|
| 16 |
- name: bart-base-samsum
|
| 17 |
results:
|
| 18 |
- task:
|
| 19 |
-
name: Abstractive Text Summarization
|
| 20 |
type: abstractive-text-summarization
|
|
|
|
| 21 |
dataset:
|
| 22 |
name: 'SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization'
|
| 23 |
type: samsum
|
| 24 |
metrics:
|
| 25 |
-
-
|
| 26 |
-
type: rouge-1
|
| 27 |
value: 46.6619
|
| 28 |
-
|
| 29 |
-
|
| 30 |
value: 23.3285
|
| 31 |
-
|
| 32 |
-
|
| 33 |
value: 39.4811
|
| 34 |
-
|
| 35 |
-
|
| 36 |
value: 44.9932
|
| 37 |
-
|
| 38 |
-
|
| 39 |
value: 21.7286
|
| 40 |
-
|
| 41 |
-
|
| 42 |
value: 38.1921
|
|
|
|
| 43 |
- task:
|
| 44 |
type: summarization
|
| 45 |
name: Summarization
|
|
@@ -49,30 +49,36 @@ model-index:
|
|
| 49 |
config: samsum
|
| 50 |
split: test
|
| 51 |
metrics:
|
| 52 |
-
-
|
| 53 |
-
type: rouge
|
| 54 |
value: 45.0148
|
|
|
|
| 55 |
verified: true
|
| 56 |
-
|
| 57 |
-
|
| 58 |
value: 21.6861
|
|
|
|
| 59 |
verified: true
|
| 60 |
-
|
| 61 |
-
|
| 62 |
value: 38.1728
|
|
|
|
| 63 |
verified: true
|
| 64 |
-
|
| 65 |
-
|
| 66 |
value: 41.2794
|
|
|
|
| 67 |
verified: true
|
| 68 |
-
|
| 69 |
-
|
| 70 |
value: 1.597476601600647
|
|
|
|
| 71 |
verified: true
|
| 72 |
-
|
| 73 |
-
|
| 74 |
value: 17.6606
|
|
|
|
| 75 |
verified: true
|
|
|
|
| 76 |
---
|
| 77 |
## `bart-base-samsum`
|
| 78 |
This model was obtained by fine-tuning `facebook/bart-base` on Samsum dataset.
|
|
|
|
| 1 |
---
|
| 2 |
language: en
|
| 3 |
+
license: apache-2.0
|
| 4 |
tags:
|
| 5 |
- bart
|
| 6 |
- seq2seq
|
| 7 |
- summarization
|
|
|
|
| 8 |
datasets:
|
| 9 |
- samsum
|
| 10 |
widget:
|
|
|
|
| 16 |
- name: bart-base-samsum
|
| 17 |
results:
|
| 18 |
- task:
|
|
|
|
| 19 |
type: abstractive-text-summarization
|
| 20 |
+
name: Abstractive Text Summarization
|
| 21 |
dataset:
|
| 22 |
name: 'SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization'
|
| 23 |
type: samsum
|
| 24 |
metrics:
|
| 25 |
+
- type: rouge-1
|
|
|
|
| 26 |
value: 46.6619
|
| 27 |
+
name: Validation ROUGE-1
|
| 28 |
+
- type: rouge-2
|
| 29 |
value: 23.3285
|
| 30 |
+
name: Validation ROUGE-2
|
| 31 |
+
- type: rouge-l
|
| 32 |
value: 39.4811
|
| 33 |
+
name: Validation ROUGE-L
|
| 34 |
+
- type: rouge-1
|
| 35 |
value: 44.9932
|
| 36 |
+
name: Test ROUGE-1
|
| 37 |
+
- type: rouge-2
|
| 38 |
value: 21.7286
|
| 39 |
+
name: Test ROUGE-2
|
| 40 |
+
- type: rouge-l
|
| 41 |
value: 38.1921
|
| 42 |
+
name: Test ROUGE-L
|
| 43 |
- task:
|
| 44 |
type: summarization
|
| 45 |
name: Summarization
|
|
|
|
| 49 |
config: samsum
|
| 50 |
split: test
|
| 51 |
metrics:
|
| 52 |
+
- type: rouge
|
|
|
|
| 53 |
value: 45.0148
|
| 54 |
+
name: ROUGE-1
|
| 55 |
verified: true
|
| 56 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZWNlYWIyNzI4MDg5YTcxNzE2NDg3MTBkZGMzMGFmNjVhNDhiMjdiM2YxODdiMDRhZWYyYTdlY2ZkOTZlMThkNyIsInZlcnNpb24iOjF9.hUpQMm2qHUkBPstp7nldJFNy-9B75Z6zunEQCstfGSxIUYXdIlI9u-o0Y9DHIBr4ZLx_CvBtvR2e0shcFFbUBg
|
| 57 |
+
- type: rouge
|
| 58 |
value: 21.6861
|
| 59 |
+
name: ROUGE-2
|
| 60 |
verified: true
|
| 61 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTAwNjdmM2MwMTcxYjNjMTA4ODk4ZDRhODQ1M2UwN2U2ZjM0MDAyZTJhMTRmMTg0ZThiYThiYTJiN2FiYTk1ZiIsInZlcnNpb24iOjF9._QzKtHvIc_oi1VO-Maxofu-LKINnu9NuAwHmLKka_KwEwrTUZkL74zLa-r4ojKNWpRLRicu02L8W_AQafYoZCw
|
| 62 |
+
- type: rouge
|
| 63 |
value: 38.1728
|
| 64 |
+
name: ROUGE-L
|
| 65 |
verified: true
|
| 66 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNGU0OTEzZTFhMGExOTkzYTI3NzljYjg2YzAxNDM4YzBhM2NjNjI4NWMxYjUwYmFjYzc5YTcxMGVmMTI3YThmMiIsInZlcnNpb24iOjF9.2JgzUAzdOOxUlt8HOWYa8mQuqyRBdyn-LqPiZI-h72zT8mrEO3sIEmmBOvmW40Gf5rvlErYtq87BgxzNwwYUAA
|
| 67 |
+
- type: rouge
|
| 68 |
value: 41.2794
|
| 69 |
+
name: ROUGE-LSUM
|
| 70 |
verified: true
|
| 71 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjI3ODg4YWQ5MjgwZmZkYTMzMGRjMGI2OWU2MDQ0ZDI3MThkZmYzN2U0OGMwMWJlMjhlMTc5YzgwMDBiM2JiZSIsInZlcnNpb24iOjF9.EnYKG7MuM-lNLkKOrlsb6mB94HqOg9sDBG1mCOni8hi7kM0rveSgSDVLk5Z6Adp-cfdRlho8zK-15TJTHJRxAw
|
| 72 |
+
- type: loss
|
| 73 |
value: 1.597476601600647
|
| 74 |
+
name: loss
|
| 75 |
verified: true
|
| 76 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTBmYjJmZDhiYmJiMTcxODM5M2ZmMTBkZTcwYzM2NDFiMDJjNjJhOGMyNGQ3MGI1Y2UxZTBhNTBiMjFjZGZiNyIsInZlcnNpb24iOjF9.UdOhxHcBJGRM-kz46st_vVQR_-KWr9EtsaQnLvj7YjCzE6JqHA2LPXnDogpUQX96PISJj32XoK7jlj-2z-CGBQ
|
| 77 |
+
- type: gen_len
|
| 78 |
value: 17.6606
|
| 79 |
+
name: gen_len
|
| 80 |
verified: true
|
| 81 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMWNlM2IyY2EzZGNiOWE0ZGMxZmJmZjhmMDI2YzE1YTQ3NmM3OGQ1NjY2ODllYjI5MDllODNhMjNmMWMyMDAyMiIsInZlcnNpb24iOjF9.sewPQx2WKY8IOBgr0XZkmzOzgwsvJko2iK0noBHpgbyWp41akxWHiaxmvipTOLcx7rbIroXQEr_UgE_LMv46Dw
|
| 82 |
---
|
| 83 |
## `bart-base-samsum`
|
| 84 |
This model was obtained by fine-tuning `facebook/bart-base` on Samsum dataset.
|