Create .eval_results/olmocrbench.yaml

#6
by staghado - opened
Files changed (1) hide show
  1. .eval_results/olmocrbench.yaml +73 -0
.eval_results/olmocrbench.yaml ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ - dataset:
2
+ id: allenai/olmOCR-bench
3
+ task_id: overall
4
+ value: 70.2
5
+ notes: "Excluding Headers & Footers category"
6
+ source:
7
+ url: https://huggingface.co/FireRedTeam/FireRed-OCR
8
+ name: FireRed-OCR evaluation
9
+ user: staghado
10
+ - dataset:
11
+ id: allenai/olmOCR-bench
12
+ task_id: arxiv_math
13
+ value: 77.7
14
+ source:
15
+ url: https://huggingface.co/FireRedTeam/FireRed-OCR
16
+ name: FireRed-OCR evaluation
17
+ user: staghado
18
+ - dataset:
19
+ id: allenai/olmOCR-bench
20
+ task_id: old_scans_math
21
+ value: 58.3
22
+ source:
23
+ url: https://huggingface.co/FireRedTeam/FireRed-OCR
24
+ name: FireRed-OCR evaluation
25
+ user: staghado
26
+ - dataset:
27
+ id: allenai/olmOCR-bench
28
+ task_id: table_tests
29
+ value: 89.0
30
+ source:
31
+ url: https://huggingface.co/FireRedTeam/FireRed-OCR
32
+ name: FireRed-OCR evaluation
33
+ user: staghado
34
+ - dataset:
35
+ id: allenai/olmOCR-bench
36
+ task_id: old_scans
37
+ value: 31.6
38
+ source:
39
+ url: https://huggingface.co/FireRedTeam/FireRed-OCR
40
+ name: FireRed-OCR evaluation
41
+ user: staghado
42
+ - dataset:
43
+ id: allenai/olmOCR-bench
44
+ task_id: multi_column
45
+ value: 68.1
46
+ source:
47
+ url: https://huggingface.co/FireRedTeam/FireRed-OCR
48
+ name: FireRed-OCR evaluation
49
+ user: staghado
50
+ - dataset:
51
+ id: allenai/olmOCR-bench
52
+ task_id: long_tiny_text
53
+ value: 78.1
54
+ source:
55
+ url: https://huggingface.co/FireRedTeam/FireRed-OCR
56
+ name: FireRed-OCR evaluation
57
+ user: staghado
58
+ - dataset:
59
+ id: allenai/olmOCR-bench
60
+ task_id: headers_footers
61
+ value: 29.2
62
+ source:
63
+ url: https://huggingface.co/FireRedTeam/FireRed-OCR
64
+ name: FireRed-OCR evaluation
65
+ user: staghado
66
+ - dataset:
67
+ id: allenai/olmOCR-bench
68
+ task_id: baseline
69
+ value: 97.3
70
+ source:
71
+ url: https://huggingface.co/FireRedTeam/FireRed-OCR
72
+ name: FireRed-OCR evaluation
73
+ user: staghado