Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator
#8
by
autoevaluator
HF Staff
- opened
README.md
CHANGED
|
@@ -14,30 +14,36 @@ model-index:
|
|
| 14 |
config: samsum
|
| 15 |
split: train
|
| 16 |
metrics:
|
| 17 |
-
-
|
| 18 |
-
type: rouge
|
| 19 |
value: 21.8096
|
|
|
|
| 20 |
verified: true
|
| 21 |
-
|
| 22 |
-
|
| 23 |
value: 4.2525
|
|
|
|
| 24 |
verified: true
|
| 25 |
-
|
| 26 |
-
|
| 27 |
value: 17.4469
|
|
|
|
| 28 |
verified: true
|
| 29 |
-
|
| 30 |
-
|
| 31 |
value: 18.8907
|
|
|
|
| 32 |
verified: true
|
| 33 |
-
|
| 34 |
-
|
| 35 |
value: 3.0317161083221436
|
|
|
|
| 36 |
verified: true
|
| 37 |
-
|
| 38 |
-
|
| 39 |
value: 20.3122
|
|
|
|
| 40 |
verified: true
|
|
|
|
| 41 |
- task:
|
| 42 |
type: summarization
|
| 43 |
name: Summarization
|
|
@@ -47,30 +53,36 @@ model-index:
|
|
| 47 |
config: default
|
| 48 |
split: test
|
| 49 |
metrics:
|
| 50 |
-
-
|
| 51 |
-
type: rouge
|
| 52 |
value: 46.8623
|
|
|
|
| 53 |
verified: true
|
| 54 |
-
|
| 55 |
-
|
| 56 |
value: 24.4533
|
|
|
|
| 57 |
verified: true
|
| 58 |
-
|
| 59 |
-
|
| 60 |
value: 39.0548
|
|
|
|
| 61 |
verified: true
|
| 62 |
-
|
| 63 |
-
|
| 64 |
value: 39.0994
|
|
|
|
| 65 |
verified: true
|
| 66 |
-
|
| 67 |
-
|
| 68 |
value: 1.5717021226882935
|
|
|
|
| 69 |
verified: true
|
| 70 |
-
|
| 71 |
-
|
| 72 |
value: 22.8821
|
|
|
|
| 73 |
verified: true
|
|
|
|
| 74 |
- task:
|
| 75 |
type: summarization
|
| 76 |
name: Summarization
|
|
@@ -80,30 +92,36 @@ model-index:
|
|
| 80 |
config: 3.0.0
|
| 81 |
split: test
|
| 82 |
metrics:
|
| 83 |
-
-
|
| 84 |
-
type: rouge
|
| 85 |
value: 22.2062
|
|
|
|
| 86 |
verified: true
|
| 87 |
-
|
| 88 |
-
|
| 89 |
value: 7.6701
|
|
|
|
| 90 |
verified: true
|
| 91 |
-
|
| 92 |
-
|
| 93 |
value: 15.4046
|
|
|
|
| 94 |
verified: true
|
| 95 |
-
|
| 96 |
-
|
| 97 |
value: 19.2182
|
|
|
|
| 98 |
verified: true
|
| 99 |
-
|
| 100 |
-
|
| 101 |
value: 2.681241273880005
|
|
|
|
| 102 |
verified: true
|
| 103 |
-
|
| 104 |
-
|
| 105 |
value: 25.0234
|
|
|
|
| 106 |
verified: true
|
|
|
|
| 107 |
---
|
| 108 |
|
| 109 |
### Pegasus Models
|
|
|
|
| 14 |
config: samsum
|
| 15 |
split: train
|
| 16 |
metrics:
|
| 17 |
+
- type: rouge
|
|
|
|
| 18 |
value: 21.8096
|
| 19 |
+
name: ROUGE-1
|
| 20 |
verified: true
|
| 21 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTM5ZTVlMTk2M2JiM2Y3ZTZkOWQyODQwZTQ1Nzc3ZDJiZDc5NzhhNTViNGRlYTI2MjkyMDBjMDMzNGU3MjFhYiIsInZlcnNpb24iOjF9.cETaihI9hH44D3QZh_yXTjEhOgumUlKr5wZqIZ_IlnE_jg0_q_KKWM986acH1K8nfHfJbDH_uZbQqqJUEuGXDQ
|
| 22 |
+
- type: rouge
|
| 23 |
value: 4.2525
|
| 24 |
+
name: ROUGE-2
|
| 25 |
verified: true
|
| 26 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDU2YTMwYmRmMGJlMzhlZDczNzczZWM4ZjBjMzE5ZmM0ZmIwYzA2MWQ2MTBhMTUwODM4YjdhYjFmZmY1OGNjOSIsInZlcnNpb24iOjF9.PAtZSns7ubNapkT-P3PzfvWUGET1dHN8AnsjYbYoaSZJ8AUl-5d3rCutt0bEAFffHFCpq23YT3Go2KOaE16PDg
|
| 27 |
+
- type: rouge
|
| 28 |
value: 17.4469
|
| 29 |
+
name: ROUGE-L
|
| 30 |
verified: true
|
| 31 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiM2VmMTRlNmIzYzlhNzY0Y2ZlYzAyOGJhNDQwNjk1YTdhZTZjNDU2ZmJhZDc5MTlhYjgyYjg4NWE0ZTA1NWExMiIsInZlcnNpb24iOjF9.CznDprjeWu6XWUwgFjGmsV2Z1W7xXuy9jDRpH5NMFlZCHAkqzoZSlMbUTwPnJF51LVJrS_WXJaXfAxKEX_LCCQ
|
| 32 |
+
- type: rouge
|
| 33 |
value: 18.8907
|
| 34 |
+
name: ROUGE-LSUM
|
| 35 |
verified: true
|
| 36 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiM2I2ZDZjMzUzNzFjNzdmMGVmODJmNzY0ZGIxY2Q3MWEwNThmODNjN2FhZTE4N2M4NjlhZjU1ZTBiODI0NThiYiIsInZlcnNpb24iOjF9.JgWVNm7FZ0r6Kn-cGAfzYszUEuYooLxbxSxSDQUvqiZVuI7tjoDp-dP8-DkgTH0yH2sqNSGBNsBnXNo63YP-AQ
|
| 37 |
+
- type: loss
|
| 38 |
value: 3.0317161083221436
|
| 39 |
+
name: loss
|
| 40 |
verified: true
|
| 41 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzg3MjRmYzRjYmIzYjk3NTZhZGM2Mzc3NjNkNTIzY2IwYmEwYWZlMGE4NTUwNjQ5YWFkNTdhMjRjNjIzZmFhYSIsInZlcnNpb24iOjF9.nns3EN07Q66USOa_TIx465wYQajhg1DcTQjU47EeKayi1uxbroU6fi90I-9k52xCGIr8RmeT2W7eNkkfFW2sCw
|
| 42 |
+
- type: gen_len
|
| 43 |
value: 20.3122
|
| 44 |
+
name: gen_len
|
| 45 |
verified: true
|
| 46 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTgxZWNhZjM4ZjE1YTY2MDBhN2ZmYWNiODU1YjNjMjQxMjVhMWYwYzNkMWU4MDM0NTYzN2IxMjIyYjNhZGIxZiIsInZlcnNpb24iOjF9.yMAFwoI4EebWho-7Jy9vAFFUHNytiAAPxr_2a99jL_d72sKjZdVQdU0Ag3fg_dRnVhqDeTVEIqwIkAJfIr8PDA
|
| 47 |
- task:
|
| 48 |
type: summarization
|
| 49 |
name: Summarization
|
|
|
|
| 53 |
config: default
|
| 54 |
split: test
|
| 55 |
metrics:
|
| 56 |
+
- type: rouge
|
|
|
|
| 57 |
value: 46.8623
|
| 58 |
+
name: ROUGE-1
|
| 59 |
verified: true
|
| 60 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiM2NjMjg2Y2Q4NjNlNmZmNmZkODlkOWU1OTg1YTcwODVmNDBiZmY4MmIwYmIyNjFiMzRkMDhkNzM2ZjFiMDYwYyIsInZlcnNpb24iOjF9.aunhAPHEDSc_V855wQiRALNEsOyD_ZTbFvi_Mu-CeZYMXO05G3ERYD6mUvdtaIP7X_Yo0vPq0y2uTQ9nVVmEDA
|
| 61 |
+
- type: rouge
|
| 62 |
value: 24.4533
|
| 63 |
+
name: ROUGE-2
|
| 64 |
verified: true
|
| 65 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjNiZTI0ODUyNGJlOTEwMGU5YjcyYzA2MzA3NThlY2ZjZTUzYTc1NThlNWZmYTNkYmQxYmI4NGUzODNlMTIzNCIsInZlcnNpb24iOjF9.8NPuJo_8Gx8EW66O835sxyYz0pteEYJ2jwwF3R24gadj0cdi7IM1LGUIPyS0IRGmYYWtqu6ybKx8xClL0TO-Ag
|
| 66 |
+
- type: rouge
|
| 67 |
value: 39.0548
|
| 68 |
+
name: ROUGE-L
|
| 69 |
verified: true
|
| 70 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiY2EyZDk4MWUyNDQ1MDA3N2QxZTMwOWM4YTJiMzM2NzZhYTE5YmE0NTYyMjg0M2NhMmQzZGYxNjQ4YjIxNDYyNyIsInZlcnNpb24iOjF9.4zORYWUO7fMkwR_HkDnd-g17Ar_MOJF_8T2rLHujBIW1HnCrNIzXHSIp1vgvn4zh6fO0tnjZDQvCD9yEfzrtDw
|
| 71 |
+
- type: rouge
|
| 72 |
value: 39.0994
|
| 73 |
+
name: ROUGE-LSUM
|
| 74 |
verified: true
|
| 75 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZDAxY2MxZTYzNWRhNWM3YTc2NjE5NzRmMzEwYTgyNDI0NmRlYjIyOTJiNzJjZWYzYThjZjczNTQzOTQzODZmNSIsInZlcnNpb24iOjF9.q3avkS3k-ljplHJbGl4nKhhH0coxe5ybHlwAJy_I1mtLoAW12k_iafy8kpXwQCmiKjqE6bgmFNPs0kkOo6JDAQ
|
| 76 |
+
- type: loss
|
| 77 |
value: 1.5717021226882935
|
| 78 |
+
name: loss
|
| 79 |
verified: true
|
| 80 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNmJlMzZiNjExNGU4ZjliOTgwZGZiZDFjNGI2N2NjYWZhNmEyMTI3YmZiYWRmNGE1MmZiNjcwZDZmOWFmNmMwZiIsInZlcnNpb24iOjF9.T5ecj6AYQ8eK-IDNqqtvkOWFvW2Q-f5kswto85P1fX_UMy9rgr2IwBRud-FAcQMnKktHK1ld94mjnDO9LcUcCQ
|
| 81 |
+
- type: gen_len
|
| 82 |
value: 22.8821
|
| 83 |
+
name: gen_len
|
| 84 |
verified: true
|
| 85 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzNiN2ExMDJhYjNmMDU2NmIxMTgwZjM5NGNmMzIxZGVmNGVkNzJmNGU4OWEwNjI1NmRmOTYyYjM5NTA1YWE0YSIsInZlcnNpb24iOjF9.pI2ulnlSyqN-EUcl9v5xbKiK-z6FDKeMpIjwqhw0WvjMf623WnqzSJZo-foFbf6DM7yFhMScgVbOOC3JEsKNCQ
|
| 86 |
- task:
|
| 87 |
type: summarization
|
| 88 |
name: Summarization
|
|
|
|
| 92 |
config: 3.0.0
|
| 93 |
split: test
|
| 94 |
metrics:
|
| 95 |
+
- type: rouge
|
|
|
|
| 96 |
value: 22.2062
|
| 97 |
+
name: ROUGE-1
|
| 98 |
verified: true
|
| 99 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjFiNGZkNDExNjUwMjhkNzY3M2NmMDgxNGVhMzZmN2E4YjIzN2Y0ZjMxNDUyOGU2NGYwNDNlOTkzMWI1OTYwNSIsInZlcnNpb24iOjF9.F_6E8QID6kjOGEFCFaUKiBmgUTtSDTQKf4F-L2NDLSDX7drF6HvTMtm9oXUeP_P9cSUNX5OvDUSJPSlfl-C0Cw
|
| 100 |
+
- type: rouge
|
| 101 |
value: 7.6701
|
| 102 |
+
name: ROUGE-2
|
| 103 |
verified: true
|
| 104 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzRhMzVmYjcyNTRlZmVhMzM4NjY3ODczZjc2M2MwM2Y5MTRhNjYxZjY4YTQ3ZmU2YzA2MGMxMzE2YjZiNGMxZSIsInZlcnNpb24iOjF9.U7IY76kNrcYgGh-Uy3H9DtaSRugShwK6Lp-I9Ov6g_r3X16Pi2cI8ZS68BaQiRvowXOKIi9R5iJLLUK3C4J2Cg
|
| 105 |
+
- type: rouge
|
| 106 |
value: 15.4046
|
| 107 |
+
name: ROUGE-L
|
| 108 |
verified: true
|
| 109 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzZjNDUxYWJjNWU0ZGY4M2I2NTBmYTBmODhiMDJiNjIzNzViNGY4YjVlMTM5Y2FlNjUyMWFkYTljYjRhM2NlZCIsInZlcnNpb24iOjF9.tyvSIMTYmFFsD6zzo_CD2tYIZiovH5Ll26qGO78kUZEvYRWfxPMhUwtrylaOsaNdTdwDz-M-TF6IQxpSXl8eBw
|
| 110 |
+
- type: rouge
|
| 111 |
value: 19.2182
|
| 112 |
+
name: ROUGE-LSUM
|
| 113 |
verified: true
|
| 114 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiY2Q3N2ZiYjVlZTY1OTYzZWRiY2RmZDkwMjM0YzIxYTUyYmJlMWQ2NDBhNTVjYjM0NGNmNWFjOWJmYzc4NDkwYiIsInZlcnNpb24iOjF9.LV3UbhyIL4EP1n5KBqAc29GMh7IIxo5tFbzPBV9Mc8Ew08d6zMs1U5aZwc0an7ClBP20B-haYHwk8JNDBZHcCg
|
| 115 |
+
- type: loss
|
| 116 |
value: 2.681241273880005
|
| 117 |
+
name: loss
|
| 118 |
verified: true
|
| 119 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiY2FjNzRjNGY0ZDkzZDM1NDIzNTQwYmQyNzE3NDQzNTBlMjIxZTFhYmZlZTRmYWI2YjRiYTA5NDYyZTM4NjM3MSIsInZlcnNpb24iOjF9.h1WwEclg4cWWYlCH8O6ifsRvOVFZ2uZj6nk7_m89rHllmOhUtVxCeSTPdNEynyv9B_SKUWPLaS_5Uj55FpF2AA
|
| 120 |
+
- type: gen_len
|
| 121 |
value: 25.0234
|
| 122 |
+
name: gen_len
|
| 123 |
verified: true
|
| 124 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjAxM2Y1ZDgzMTc3ZmVlOWI5YzYyMmExMzc3Y2JkYzJjZDRkODY5MWE4ZGQzZjFmNTFjNDZlMTcyZmQ3MWM5MyIsInZlcnNpb24iOjF9.6XKMtrC2IqCcphlUI8aJp673IRfsnjJhOJrvftxyA_k3YxSDI_3Iyo_mURpXAVo4llb52lB638bRHZv1tvdvDg
|
| 125 |
---
|
| 126 |
|
| 127 |
### Pegasus Models
|