Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator
#1
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.eyJoYXNoIjoiZjhmMTg1M2FmMGNhMjJjMzJmMDgzZTZkN2Q3ZDcyZmJhZjZiMWRhZDYxYWU0OTM4MDc5M2RlYjk4OTY4MTk2NCIsInZlcnNpb24iOjF9.SoR8ISzeiIRmDW8UWhtxSX1a7A2DZWbjGMlPdUEXasBvXQsOTOAEfEk7XI-6Ah5aCnXyYT9FnzY8xQl9c_66Cw
|
| 25 |
+
- type: rouge
|
| 26 |
value: 18.1161
|
| 27 |
+
name: ROUGE-2
|
| 28 |
verified: true
|
| 29 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYTdlMjU1MGE2YTQxZmNjMzU0YmNjNTM5OThhMjFiNGJhOThkNWY0YTQxNDFmZTg5MzliNmUzNmI3NDEwMWE3YSIsInZlcnNpb24iOjF9.BA8OVHy_Pk0lMZON9C42Uu6gd9N_b4etNSduuguAE_dd0PjX0Lw5S_0N7lPD722ro5AjBXHSHcj10BwxsRUsAA
|
| 30 |
+
- type: rouge
|
| 31 |
value: 26.1743
|
| 32 |
+
name: ROUGE-L
|
| 33 |
verified: true
|
| 34 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMGFjYWM1NzBjOTM3Nzg4ODU2MjFlNjAyNDQ5NjQ5YzQ1YmIzMDNlZDE2ZjE1MjZhYTkyMzI5Mzc4MDQ5NDk2MyIsInZlcnNpb24iOjF9.LBFqVbt8MHdJVQ_LiNb6wqVCBRKVnE4OVVUWwsVg6HX0-jnMga1ASEnURtVUvQhk84-gkiPeZZSE4SjKNFulDQ
|
| 35 |
+
- type: rouge
|
| 36 |
value: 34.2773
|
| 37 |
+
name: ROUGE-LSUM
|
| 38 |
verified: true
|
| 39 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiN2Q4ODA3YmFjNGU2ZjBmMWFkYTE1NmUwNzk4Mjk4NmUxZThlM2QyNWQwMzNhN2VkZTU1MTI4ZTY4ZGI0NTQxOCIsInZlcnNpb24iOjF9.D37tnGTOvAKEl5CujVGLGICQPRv9yM5DU3PQJdQyxOIiyNe367bqjmVr00VvLmpQ0VNOZGM9VaycR_dmh_DDDQ
|
| 40 |
+
- type: loss
|
| 41 |
value: 2.1707184314727783
|
| 42 |
+
name: loss
|
| 43 |
verified: true
|
| 44 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNGZlNjRkYzI1YzFlNDJmZmI2ZTI4OGJkZTZjY2QyYWQyZTA4NzEzNzY2ODIwNDVkNTZlNGEyYjZiNTk3NjQ4MiIsInZlcnNpb24iOjF9.8ioVz9nOz4OybNKDCRTKZqGXeLgT5TTz9Bj8yWLKNrFhOI_nTg0O-ZpZDyq7uQUkv0fOQz8ZKAGqHWQfwNeNAw
|
| 45 |
+
- type: meteor
|
| 46 |
value: 0.3513
|
| 47 |
+
name: meteor
|
| 48 |
verified: true
|
| 49 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTA0NTVjZjU1OGU1ODFlODIxZDU0YmYxODIwN2ZmNGM3YjkyMTFiNjMyYzA4MTc1ZjA0YzczYzgwMzE2N2JiOSIsInZlcnNpb24iOjF9.DfmgfbhlCusjv5hh9ND0VEFjbJz7to8_qXH5meU37SIZP-2ApgqShNjAjcRw2nRlgTH9fsrcALwg6zb-41XDDA
|
| 50 |
+
- type: gen_len
|
| 51 |
value: 221.2531
|
| 52 |
+
name: gen_len
|
| 53 |
verified: true
|
| 54 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNWFjNDM3YTAzNGU5NjU0Njg4MWUyZGM0OWJjMTNiMjJjMDRhOTcyMDM0NzdkODNhMDJhZTc0OTJkOTI3YjFmMyIsInZlcnNpb24iOjF9.NieaGIGTbAVP881vaD8zUHzmudvKDaf6Xv3O85TmjsE_rUnBqzF1uRBjfxsNSPZOaAZbRcqffL2Hh-RCcsXrBw
|
| 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.eyJoYXNoIjoiZjc2YmNiZTQ3YWUxYmE3NzM0Yzc2YWMxZTlhMzc3MjMyMmQ0MWJiYWUyZDA1MWExYjQ0ODY4YzM4MzgyNWZiYyIsInZlcnNpb24iOjF9.QoJdI0BEjb08nJe1mSMFxzqHfni7cOCuDdNS82Xg0G4R9uSKDboQhiLXslFup74c0a2O7bTwWasQHu-mtng4Ag
|
| 69 |
+
- type: rouge
|
| 70 |
value: 14.374
|
| 71 |
+
name: ROUGE-2
|
| 72 |
verified: true
|
| 73 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiY2QyMDQ3Y2RjYTY1NjhhYzcxN2IwMGQ3YzU3Zjk4MDMyNTM4MmE5YjE4MmUzNzM3YjVhYTA2YjBiNjI0YzEyNCIsInZlcnNpb24iOjF9.84fv-gyLKj-cljtydFclw9_F18MLiLlbhrBxFCDFYdX31R7zLLfd382JllPfZI9no7cIB9ga-eUvtIQjJXSJCw
|
| 74 |
+
- type: rouge
|
| 75 |
value: 23.4773
|
| 76 |
+
name: ROUGE-L
|
| 77 |
verified: true
|
| 78 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYjdiZWJhZjNlODY0YzMzOTc4MmZmMmUxZmQyMjgwZDMxY2Q2MmM3Y2M5MmNhZjRmNjg2M2YwNWFlOTY4MzZlMSIsInZlcnNpb24iOjF9.6WEJPyxVyirjAD3NK3z2FLguYH7iGXsQGd5R8j_5paBAihrmndm02pTODhNMN-ANjJSxylvuzElUVBTTDm0sAw
|
| 79 |
+
- type: rouge
|
| 80 |
value: 33.772
|
| 81 |
+
name: ROUGE-LSUM
|
| 82 |
verified: true
|
| 83 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMjRkZDkxYTlkYzFhMDYzNWMyZjEwMDU1YzY5YzNiYjFlYjY0ZDZmODVmNWEzYjVhZTMzNDI5ZTM0M2VlNTllMSIsInZlcnNpb24iOjF9.u90bbTq2shxIrcDd2MxoEHbHs9ZBIenLiEhTYWIFnFiXHafXmLdnsxmjWnFXsT2tO_gCFPwYhx2Qla-9BpK8AQ
|
| 84 |
+
- type: loss
|
| 85 |
value: 3.235051393508911
|
| 86 |
+
name: loss
|
| 87 |
verified: true
|
| 88 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZWIyYTBhMTBiZWY1OGIzODk5Y2NjYzgyOWY0MjUwZmFkM2ZlZDhiNGY4ZTI3NWUxYzZhOTg1M2M2NzI3MTBkYyIsInZlcnNpb24iOjF9.HjwTRnmITF5d8zNH7WU-riPfpYgxKUBtxT6r3t2dp92ReMVl3CPk6GdWfZsrRcPmV3F7eZ7jqPuCy2wa-N1sDA
|
| 89 |
+
- type: gen_len
|
| 90 |
value: 186.2003
|
| 91 |
+
name: gen_len
|
| 92 |
verified: true
|
| 93 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNmE5N2FjNjAzNTgyNzEzZTUxYzk2NWRmZDk5YWU5ZTAxMjEwMjZjYThmYjM1OWE0ZDc3MmZlOWEyMDk4YWQ5ZSIsInZlcnNpb24iOjF9.cBmsTsmCN8MaMOp20q95u23oi1YV1G8MWzvUGwYK7I3JblTPmvL0uw8K5_6RMuZJjm6GWSpKp-CwK3styoyTAQ
|
| 94 |
---
|
| 95 |
|
| 96 |
# BigBirdPegasus model (large)
|