Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator
#10
by autoevaluator HF Staff - opened
README.md
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
---
|
| 2 |
language: en
|
| 3 |
license: apache-2.0
|
| 4 |
-
datasets:
|
| 5 |
-
- scientific_papers
|
| 6 |
tags:
|
| 7 |
- summarization
|
|
|
|
|
|
|
| 8 |
model-index:
|
| 9 |
- name: google/bigbird-pegasus-large-pubmed
|
| 10 |
results:
|
|
@@ -17,34 +17,41 @@ model-index:
|
|
| 17 |
config: pubmed
|
| 18 |
split: test
|
| 19 |
metrics:
|
| 20 |
-
-
|
| 21 |
-
type: rouge
|
| 22 |
value: 40.8966
|
|
|
|
| 23 |
verified: true
|
| 24 |
-
|
| 25 |
-
|
| 26 |
value: 18.1161
|
|
|
|
| 27 |
verified: true
|
| 28 |
-
|
| 29 |
-
|
| 30 |
value: 26.1743
|
|
|
|
| 31 |
verified: true
|
| 32 |
-
|
| 33 |
-
|
| 34 |
value: 34.2773
|
|
|
|
| 35 |
verified: true
|
| 36 |
-
|
| 37 |
-
|
| 38 |
value: 2.1707184314727783
|
|
|
|
| 39 |
verified: true
|
| 40 |
-
|
| 41 |
-
|
| 42 |
value: 0.3513
|
|
|
|
| 43 |
verified: true
|
| 44 |
-
|
| 45 |
-
|
| 46 |
value: 221.2531
|
|
|
|
| 47 |
verified: true
|
|
|
|
| 48 |
- task:
|
| 49 |
type: summarization
|
| 50 |
name: Summarization
|
|
@@ -54,30 +61,36 @@ model-index:
|
|
| 54 |
config: arxiv
|
| 55 |
split: test
|
| 56 |
metrics:
|
| 57 |
-
-
|
| 58 |
-
type: rouge
|
| 59 |
value: 40.3815
|
|
|
|
| 60 |
verified: true
|
| 61 |
-
|
| 62 |
-
|
| 63 |
value: 14.374
|
|
|
|
| 64 |
verified: true
|
| 65 |
-
|
| 66 |
-
|
| 67 |
value: 23.4773
|
|
|
|
| 68 |
verified: true
|
| 69 |
-
|
| 70 |
-
|
| 71 |
value: 33.772
|
|
|
|
| 72 |
verified: true
|
| 73 |
-
|
| 74 |
-
|
| 75 |
value: 3.235051393508911
|
|
|
|
| 76 |
verified: true
|
| 77 |
-
|
| 78 |
-
|
| 79 |
value: 186.2003
|
|
|
|
| 80 |
verified: true
|
|
|
|
| 81 |
---
|
| 82 |
|
| 83 |
# BigBirdPegasus model (large)
|
|
|
|
| 1 |
---
|
| 2 |
language: en
|
| 3 |
license: apache-2.0
|
|
|
|
|
|
|
| 4 |
tags:
|
| 5 |
- summarization
|
| 6 |
+
datasets:
|
| 7 |
+
- scientific_papers
|
| 8 |
model-index:
|
| 9 |
- name: google/bigbird-pegasus-large-pubmed
|
| 10 |
results:
|
|
|
|
| 17 |
config: pubmed
|
| 18 |
split: test
|
| 19 |
metrics:
|
| 20 |
+
- type: rouge
|
|
|
|
| 21 |
value: 40.8966
|
| 22 |
+
name: ROUGE-1
|
| 23 |
verified: true
|
| 24 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMDE0MTgzMGZjYmNjZDFjYjVmN2IzNzIyZDZmOTJhZDQwZTdiMzBhN2M1NjY1NDViYmIzZDY5MzgyZmJkYjRiMyIsInZlcnNpb24iOjF9.iB1O0J1xzCKzT8dyjPMFhJKS4KYP315Ho7quLP1tCrarAaTJhYNTPfUWVWIPiNZfFMGHfrbbwfPwAWFPbe1cDg
|
| 25 |
+
- type: rouge
|
| 26 |
value: 18.1161
|
| 27 |
+
name: ROUGE-2
|
| 28 |
verified: true
|
| 29 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYThjYzNjY2MzYTk4YzQ1YWUzMGQ2ODFhMmVmNzBjZTNiNDU5YjMxOTk1OGY3YzlkYjBlMDkyY2I2MWM1MmViOCIsInZlcnNpb24iOjF9.bfgTrSm2EBmJxHUAL1778BnjuyrsUgDAWGLkSfDOS2UlAmbacjsgzRC9URGYRk0HM46-eG-8LaH_QOeStNQqBA
|
| 30 |
+
- type: rouge
|
| 31 |
value: 26.1743
|
| 32 |
+
name: ROUGE-L
|
| 33 |
verified: true
|
| 34 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNGU1ZDNlOTgzNmYwZDY2ZWJiNjI1MWNkNmQ4MThjYzhhYWIyMWFlYzYyNmIxNjI1Y2RmYmM0NWEwYTdmMDVmOCIsInZlcnNpb24iOjF9.0K6vGPV2lkDjeMHbK_HfO4oUj1u1Y4B-1BKXJwqz0rw_CVt5zPTh23ap1BzgAoVxLm7BucqmqG9KjOa0gTUZCw
|
| 35 |
+
- type: rouge
|
| 36 |
value: 34.2773
|
| 37 |
+
name: ROUGE-LSUM
|
| 38 |
verified: true
|
| 39 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYTkwZDYyZDJkMTNmYjhkOGE2MDI2MjQ4NzMxNjU3NTNmNWJiZTQ1Mjg3OWVkMzdlMWUxOWYxNTY4YTk5MzA5OSIsInZlcnNpb24iOjF9.kNIBlWwKGWm_xgrThPORu21-dcRxH_PdylKGbjMY981xZXNwo50UxhaIkb4nmtAQvNfpDSAgBS79hNGRUKy6Aw
|
| 40 |
+
- type: loss
|
| 41 |
value: 2.1707184314727783
|
| 42 |
+
name: loss
|
| 43 |
verified: true
|
| 44 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZGU0NzcwNDA0ZTIwNDZkZTAxNzg2NmM4NWMzNDg4ZTM1NTdlYzE0N2U1NjE2NDI1ZWI1OWJkMTFkZmY5MDMzMSIsInZlcnNpb24iOjF9.bAoZ95-VIQ3_pWQFfkQn3cX6h1MnTmvWHmpFZjGZbuNxLBCpRFd24LXx_qAXZAmTrIew7SUIvIeoiRrEgYw8BA
|
| 45 |
+
- type: meteor
|
| 46 |
value: 0.3513
|
| 47 |
+
name: meteor
|
| 48 |
verified: true
|
| 49 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzAwNjFjYzQzMzhiYmNkMzMyNDc1MGFiOTIxODdjYTFlYzMyYzRiNDRmMTRjOWRjZjQyMGJkZjRlYzc2NzAwZSIsInZlcnNpb24iOjF9.Z6d0UlPTCg5BqaX5uZWOjQTJqV0MozJcgvmu4XimI-DJ8O826-xMg7wReNePdc8Qi_4L0v7X2NtT8Ko_t3-QCA
|
| 50 |
+
- type: gen_len
|
| 51 |
value: 221.2531
|
| 52 |
+
name: gen_len
|
| 53 |
verified: true
|
| 54 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiODgxOTE2NjFjNmEzYmQ2ZWIwMWIxNjk2YmQ0ZGE4NzYyNzlhMmNhYmYwZWZjNTliOWUxOWY1NTI1YmE0MmJmZiIsInZlcnNpb24iOjF9.DeOPOsD_IcAyywX8uYuj67R5Wf4Xfv2oTfb4_DNE1xrjNHMNv1ZyX7Fw0dRh0yEkAupxLWa_M5OwAILX-3CQAA
|
| 55 |
- task:
|
| 56 |
type: summarization
|
| 57 |
name: Summarization
|
|
|
|
| 61 |
config: arxiv
|
| 62 |
split: test
|
| 63 |
metrics:
|
| 64 |
+
- type: rouge
|
|
|
|
| 65 |
value: 40.3815
|
| 66 |
+
name: ROUGE-1
|
| 67 |
verified: true
|
| 68 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYjYxNWRhYTNlNzk0MGY1NzQzMTFkNjlmMTdiNGQxNjNkZDI4OTdjYzE4MDkzY2JkNzA5MGMzZmU2ZDM0NDE1ZiIsInZlcnNpb24iOjF9.hsWiQlJTCD_LURjhnLi5s0uQqZUxa6YDC5wUrT0CAnZkpb7HrluHfMP_xxM0Zw-vvQm9e2J8l-liX98oXEOCDQ
|
| 69 |
+
- type: rouge
|
| 70 |
value: 14.374
|
| 71 |
+
name: ROUGE-2
|
| 72 |
verified: true
|
| 73 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOGIxZDI1ZjEzMDQ1NTE0ZTMzZTc1MWVhZjZjYmRiMjY3MGVlZWRjNDQ4ZTM4Y2FiYzJlZGQ3YWYzYTgyNmJlYSIsInZlcnNpb24iOjF9.UbMLU8ighxu3Az75GviU_CYW2MNzC-1TIKmS4SmOWllCnAKgCEski6h32jErZYbSkrwle6VY0qJz1s_RnKq7DQ
|
| 74 |
+
- type: rouge
|
| 75 |
value: 23.4773
|
| 76 |
+
name: ROUGE-L
|
| 77 |
verified: true
|
| 78 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDVlZjRjNTRjMTI4NTQyMGFjZmMzNjNmODQ5MzI2YzE0MjM4Zjc4MDA4NDIzNzZhMjBlM2M5NjFiM2Y1YzE1MCIsInZlcnNpb24iOjF9.wk92Lmo2jTK6r1S9rHAPIMDSF2McFOT88-cg_NaGW_cWfvqXW_YNnQnRwad2UjKJc5MGmBwXYv6BP9riZ1qhBQ
|
| 79 |
+
- type: rouge
|
| 80 |
value: 33.772
|
| 81 |
+
name: ROUGE-LSUM
|
| 82 |
verified: true
|
| 83 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMmVhYTZhYjY5N2RhNDIzMDI5OWUxZjBmOTRjMjQzZmY5YWMxOThiZTU2YzZhZjJmMGQ2NzY3NzYwNDBhNDY2YSIsInZlcnNpb24iOjF9.sA8nsnsJZmetwc6jc6dsy4jmblYMoE-T4TM3JGdcZO7MZylLm9qyKOo052E17CDSJ93UiT04ZuRTvupQ-GRLDg
|
| 84 |
+
- type: loss
|
| 85 |
value: 3.235051393508911
|
| 86 |
+
name: loss
|
| 87 |
verified: true
|
| 88 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNmQyMmY4NTRjMjM3YzE3MWE4Nzc3NWFiZDEyOGM2Nzg0OWFjZWI2MjdkMmE5ZjJiZGUyOGE0Y2IzZDM5ZDkzMyIsInZlcnNpb24iOjF9.j6BJBLjVpnrbHkyjLI01tNBeyBTlxHOWZMwJDUThyQfhOWBI4ZU-XVBY02BnZvDjQ1f64xxb8YDrbm7SRezsBg
|
| 89 |
+
- type: gen_len
|
| 90 |
value: 186.2003
|
| 91 |
+
name: gen_len
|
| 92 |
verified: true
|
| 93 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZjIzM2ZiMTViOGJlMTZkYzEwZTI0ZDRmZjIyMjA5YWQxYzJjMjRkMWEyNmVjMGJmOTE2ZTYyYjk3ZWE3YTlmZSIsInZlcnNpb24iOjF9.dXJOk1Jr_x_5Dp2aI_32Sc1vghTEezJwZ6V_Pc69prIz-6Qq9bmdUCKRq1iznifLfWusFPXSsOnmd4Y7jMtlAA
|
| 94 |
---
|
| 95 |
|
| 96 |
# BigBirdPegasus model (large)
|