autoevaluator HF staff commited on
Commit
f6be60c
1 Parent(s): cb993e1

Add evaluation results on the pubmed config and train split of scientific_papers

Browse files

Beep boop, I am a bot from Hugging Face's automatic model evaluator 👋!\
Your model has been evaluated on the pubmed config and train split of the [scientific_papers](https://huggingface.co/datasets/scientific_papers) dataset by

@NessTechIntl

, using the predictions stored [here](https://huggingface.co/datasets/autoevaluate/autoeval-eval-scientific_papers-pubmed-c3b6df-51381145313).\
Accept this pull request to see the results displayed on the [Hub leaderboard](https://huggingface.co/spaces/autoevaluate/leaderboards?dataset=scientific_papers).\
Evaluate your model on more datasets [here](https://huggingface.co/spaces/autoevaluate/model-evaluator?dataset=scientific_papers).

Files changed (1) hide show
  1. README.md +76 -37
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
  language: en
 
3
  tags:
4
  - summarization
5
- license: mit
6
  model-index:
7
  - name: SamuelAllen123/t5-efficient-large-nl36_fine_tune_sum_V2
8
  results:
@@ -15,29 +15,29 @@ model-index:
15
  config: samsum
16
  split: test
17
  metrics:
18
- - name: ROUGE-1
19
- type: rouge
20
  value: 50.5049
 
21
  verified: true
22
- - name: ROUGE-2
23
- type: rouge
24
  value: 25.6469
 
25
  verified: true
26
- - name: ROUGE-L
27
- type: rouge
28
  value: 41.7544
 
29
  verified: true
30
- - name: ROUGE-LSUM
31
- type: rouge
32
  value: 46.2055
 
33
  verified: true
34
- - name: loss
35
- type: loss
36
  value: 1.5158178806304932
 
37
  verified: true
38
- - name: gen_len
39
- type: gen_len
40
  value: 24.0342
 
41
  verified: true
42
  - task:
43
  type: summarization
@@ -48,29 +48,29 @@ model-index:
48
  config: 3.0.0
49
  split: test
50
  metrics:
51
- - name: ROUGE-1
52
- type: rouge
53
  value: 34.4055
 
54
  verified: true
55
- - name: ROUGE-2
56
- type: rouge
57
  value: 14.127
 
58
  verified: true
59
- - name: ROUGE-L
60
- type: rouge
61
  value: 24.3353
 
62
  verified: true
63
- - name: ROUGE-LSUM
64
- type: rouge
65
  value: 31.6582
 
66
  verified: true
67
- - name: loss
68
- type: loss
69
  value: 2.4456119537353516
 
70
  verified: true
71
- - name: gen_len
72
- type: gen_len
73
  value: 45.928
 
74
  verified: true
75
  - task:
76
  type: summarization
@@ -81,30 +81,69 @@ model-index:
81
  config: samsum
82
  split: train
83
  metrics:
84
- - name: ROUGE-1
85
- type: rouge
86
  value: 54.933
 
87
  verified: true
88
- - name: ROUGE-2
89
- type: rouge
90
  value: 31.7965
 
91
  verified: true
92
- - name: ROUGE-L
93
- type: rouge
94
  value: 47.0057
 
95
  verified: true
96
- - name: ROUGE-LSUM
97
- type: rouge
98
  value: 51.2027
 
99
  verified: true
100
- - name: loss
101
- type: loss
102
  value: 1.130684494972229
 
103
  verified: true
104
- - name: gen_len
105
- type: gen_len
106
  value: 23.7989
 
107
  verified: true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
108
  ---
109
  *NOT SELF REPORTED VALUES FOR THE LEADERBOARD, I HAVE NO CLUE WHY ITS BROKE. CHECK PULL REQUEST*
110
 
 
1
  ---
2
  language: en
3
+ license: mit
4
  tags:
5
  - summarization
 
6
  model-index:
7
  - name: SamuelAllen123/t5-efficient-large-nl36_fine_tune_sum_V2
8
  results:
 
15
  config: samsum
16
  split: test
17
  metrics:
18
+ - type: rouge
 
19
  value: 50.5049
20
+ name: ROUGE-1
21
  verified: true
22
+ - type: rouge
 
23
  value: 25.6469
24
+ name: ROUGE-2
25
  verified: true
26
+ - type: rouge
 
27
  value: 41.7544
28
+ name: ROUGE-L
29
  verified: true
30
+ - type: rouge
 
31
  value: 46.2055
32
+ name: ROUGE-LSUM
33
  verified: true
34
+ - type: loss
 
35
  value: 1.5158178806304932
36
+ name: loss
37
  verified: true
38
+ - type: gen_len
 
39
  value: 24.0342
40
+ name: gen_len
41
  verified: true
42
  - task:
43
  type: summarization
 
48
  config: 3.0.0
49
  split: test
50
  metrics:
51
+ - type: rouge
 
52
  value: 34.4055
53
+ name: ROUGE-1
54
  verified: true
55
+ - type: rouge
 
56
  value: 14.127
57
+ name: ROUGE-2
58
  verified: true
59
+ - type: rouge
 
60
  value: 24.3353
61
+ name: ROUGE-L
62
  verified: true
63
+ - type: rouge
 
64
  value: 31.6582
65
+ name: ROUGE-LSUM
66
  verified: true
67
+ - type: loss
 
68
  value: 2.4456119537353516
69
+ name: loss
70
  verified: true
71
+ - type: gen_len
 
72
  value: 45.928
73
+ name: gen_len
74
  verified: true
75
  - task:
76
  type: summarization
 
81
  config: samsum
82
  split: train
83
  metrics:
84
+ - type: rouge
 
85
  value: 54.933
86
+ name: ROUGE-1
87
  verified: true
88
+ - type: rouge
 
89
  value: 31.7965
90
+ name: ROUGE-2
91
  verified: true
92
+ - type: rouge
 
93
  value: 47.0057
94
+ name: ROUGE-L
95
  verified: true
96
+ - type: rouge
 
97
  value: 51.2027
98
+ name: ROUGE-LSUM
99
  verified: true
100
+ - type: loss
 
101
  value: 1.130684494972229
102
+ name: loss
103
  verified: true
104
+ - type: gen_len
 
105
  value: 23.7989
106
+ name: gen_len
107
  verified: true
108
+ - task:
109
+ type: summarization
110
+ name: Summarization
111
+ dataset:
112
+ name: scientific_papers
113
+ type: scientific_papers
114
+ config: pubmed
115
+ split: train
116
+ metrics:
117
+ - type: rouge
118
+ value: 23.6698
119
+ name: ROUGE-1
120
+ verified: true
121
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTg4OTMwYjkyNmU1ZjdmN2Q4MWE4YzFkZjUyMDZhNDNhYjBkODg3ZjI5NDQxMTcyNDUyMzkwNDZlNjNhZGRiOSIsInZlcnNpb24iOjF9.0kRK7iA642z0YWAH81v1_-pil6TyM3bezGfZtqGev5O7AgGkxzfQaIDNhkVVvVIJdUPJFD7L36XyLx3AWO5BCQ
122
+ - type: rouge
123
+ value: 7.5691
124
+ name: ROUGE-2
125
+ verified: true
126
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiY2Q2MDc1ZjZlYjRmZDZkNjY3MmFhODAzZWUwZjA1M2RlZGUwYTY2ZjM2ZTM1NzQ3YjAxMDFiMWZlMGMwNTgyOCIsInZlcnNpb24iOjF9._Y59aEEGLn0Ij622V8Rwljp-h4uTuCfoPgJdvMN6GvCyKRzwugHo8tedfTpbTAb6cicjiWjKvKurqXTjpw1KAw
127
+ - type: rouge
128
+ value: 15.6071
129
+ name: ROUGE-L
130
+ verified: true
131
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjMwM2Q2ODYwZWE4MzNhNDNlNzlhNjU2NGUxYjlhNDM3MzM5MmJjNzU4YTYxNzI4ZmQ3YzQ1YjMzMDZkMTQ4ZCIsInZlcnNpb24iOjF9.zyfiVsuCEXCTkGAqNxCZ8hTKVxAE0JmJRbNZ04HoBi7qYFB13_7JTB6tOvAEH34W-2yvpOs4cBsFqtXg7RvnCA
132
+ - type: rouge
133
+ value: 21.4565
134
+ name: ROUGE-LSUM
135
+ verified: true
136
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTE4MjVlZjI5NDBkZjRmODA3MmIzY2I0YWUwZjEyMzYwNjFjNTY3N2NjMmY3ZThlODBjN2VhZWZlODliZmEyZSIsInZlcnNpb24iOjF9.RFZbr5R9cJtrhzWMKys62fiBxKv8MYe6_115NBjEZ6wOwzVih5SdJE8r2EK-1wdCMF_jLGPYQvZ-zyj3KHGWCw
137
+ - type: loss
138
+ value: 3.9369945526123047
139
+ name: loss
140
+ verified: true
141
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTc3MzMwYTg5OWIyZGQxNGJlYzExNTY0MjUyY2M5M2NiOGQ2ODI0MWFiMzJjYWY4ZGNkZmY2MmUyZjVjODRiYSIsInZlcnNpb24iOjF9.iDxSfTwZRV5VboHLjF4a47kPXagG7bY78WIejIM37ykpksXxVYssZlmK6UxtkEmZuWypqbQjz6oOjTjy6x3tDQ
142
+ - type: gen_len
143
+ value: 65.9987
144
+ name: gen_len
145
+ verified: true
146
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiODdmYzFiNzU3N2VlMWMyMGEwZmFkZmExZWRlN2NjNWI3ZGJjNmYzMWExYWM5MWY2MzJkMmY0ZGE2NjFjMjRjYyIsInZlcnNpb24iOjF9.3ByM1s1Ux-PDBBnf6i3FUtFLzpmZXcikIfrsR3vTIi9567r789Wm8sW81blFHNfnST-ZHQxPKJOuv4ho8S4eCg
147
  ---
148
  *NOT SELF REPORTED VALUES FOR THE LEADERBOARD, I HAVE NO CLUE WHY ITS BROKE. CHECK PULL REQUEST*
149