Jakolo121 commited on
Commit
1a002f3
1 Parent(s): 93dc212

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -116
README.md CHANGED
@@ -35,123 +35,7 @@ parameters:
35
  value: [1, 0.5, 0.7, 0.3, 0]
36
  - value: 0.5
37
  ```
38
- | Model | ARC |HellaSwag| MMLU |TruthfulQA|Winogrande|GSM8K|
39
- |---------------------------------------------------------------|----:|--------:|--------------------------|---------:|---------:|----:|
40
- |[Sappho_V0.0.4](https://huggingface.co/Jakolo121/Sappho_V0.0.4)|63.65| 84.1|Error: File does not exist| 52.99| 77.66|55.27|
41
 
42
- ### ARC
43
- | Task |Version| Metric | Value | |Stderr|
44
- |-------------|------:|--------------------|-------------|---|------|
45
- |arc_challenge| 1|acc,none | 0.61| | |
46
- | | |acc_stderr,none | 0.01| | |
47
- | | |acc_norm,none | 0.64| | |
48
- | | |acc_norm_stderr,none| 0.01| | |
49
- | | |alias |arc_challenge| | |
50
-
51
- Average: 63.65%
52
-
53
- ### HellaSwag
54
- | Task |Version| Metric | Value | |Stderr|
55
- |---------|------:|--------------------|---------|---|------|
56
- |hellaswag| 1|acc,none | 0.66| | |
57
- | | |acc_stderr,none | 0| | |
58
- | | |acc_norm,none | 0.84| | |
59
- | | |acc_norm_stderr,none| 0| | |
60
- | | |alias |hellaswag| | |
61
-
62
- Average: 84.1%
63
-
64
- ### MMLU
65
-
66
- Average: Error: File does not exist%
67
-
68
- ### TruthfulQA
69
- | Task |Version| Metric | Value | |Stderr|
70
- |--------------|-------|-----------------------|-----------------|---|------|
71
- |truthfulqa |N/A |rouge2_max,none | 36.50| | |
72
- | | |rouge2_max_stderr,none | 1.02| | |
73
- | | |rouge1_max,none | 50.18| | |
74
- | | |rouge1_max_stderr,none | 0.88| | |
75
- | | |rouge1_acc,none | 0.52| | |
76
- | | |rouge1_acc_stderr,none | 0.02| | |
77
- | | |bleu_max,none | 25.40| | |
78
- | | |bleu_max_stderr,none | 0.81| | |
79
- | | |rouge2_acc,none | 0.45| | |
80
- | | |rouge2_acc_stderr,none | 0.02| | |
81
- | | |rouge2_diff,none | 5.12| | |
82
- | | |rouge2_diff_stderr,none| 1.14| | |
83
- | | |acc,none | 0.45| | |
84
- | | |acc_stderr,none | 0.01| | |
85
- | | |bleu_acc,none | 0.52| | |
86
- | | |bleu_acc_stderr,none | 0.02| | |
87
- | | |rouge1_diff,none | 4.67| | |
88
- | | |rouge1_diff_stderr,none| 1.08| | |
89
- | | |rougeL_diff,none | 3.92| | |
90
- | | |rougeL_diff_stderr,none| 1.09| | |
91
- | | |bleu_diff,none | 4| | |
92
- | | |bleu_diff_stderr,none | 0.79| | |
93
- | | |rougeL_acc,none | 0.50| | |
94
- | | |rougeL_acc_stderr,none | 0.02| | |
95
- | | |rougeL_max,none | 46.87| | |
96
- | | |rougeL_max_stderr,none | 0.91| | |
97
- | | |alias |truthfulqa | | |
98
- |truthfulqa_gen| 3|bleu_max,none | 25.40| | |
99
- | | |bleu_max_stderr,none | 0.81| | |
100
- | | |bleu_acc,none | 0.52| | |
101
- | | |bleu_acc_stderr,none | 0.02| | |
102
- | | |bleu_diff,none | 4| | |
103
- | | |bleu_diff_stderr,none | 0.79| | |
104
- | | |rouge1_max,none | 50.18| | |
105
- | | |rouge1_max_stderr,none | 0.88| | |
106
- | | |rouge1_acc,none | 0.52| | |
107
- | | |rouge1_acc_stderr,none | 0.02| | |
108
- | | |rouge1_diff,none | 4.67| | |
109
- | | |rouge1_diff_stderr,none| 1.08| | |
110
- | | |rouge2_max,none | 36.50| | |
111
- | | |rouge2_max_stderr,none | 1.02| | |
112
- | | |rouge2_acc,none | 0.45| | |
113
- | | |rouge2_acc_stderr,none | 0.02| | |
114
- | | |rouge2_diff,none | 5.12| | |
115
- | | |rouge2_diff_stderr,none| 1.14| | |
116
- | | |rougeL_max,none | 46.87| | |
117
- | | |rougeL_max_stderr,none | 0.91| | |
118
- | | |rougeL_acc,none | 0.50| | |
119
- | | |rougeL_acc_stderr,none | 0.02| | |
120
- | | |rougeL_diff,none | 3.92| | |
121
- | | |rougeL_diff_stderr,none| 1.09| | |
122
- | | |alias | - truthfulqa_gen| | |
123
- |truthfulqa_mc1| 2|acc,none | 0.37| | |
124
- | | |acc_stderr,none | 0.02| | |
125
- | | |alias | - truthfulqa_mc1| | |
126
- |truthfulqa_mc2| 2|acc,none | 0.53| | |
127
- | | |acc_stderr,none | 0.02| | |
128
- | | |alias | - truthfulqa_mc2| | |
129
-
130
- Average: 52.99%
131
-
132
- ### Winogrande
133
- | Task |Version| Metric | Value | |Stderr|
134
- |----------|------:|---------------|----------|---|------|
135
- |winogrande| 1|acc,none | 0.78| | |
136
- | | |acc_stderr,none| 0.01| | |
137
- | | |alias |winogrande| | |
138
-
139
- Average: 77.66%
140
-
141
- ### GSM8K
142
- |Task |Version| Metric |Value| |Stderr|
143
- |-----|------:|-----------------------------------|-----|---|------|
144
- |gsm8k| 3|exact_match,strict-match | 0.55| | |
145
- | | |exact_match_stderr,strict-match | 0.01| | |
146
- | | |exact_match,flexible-extract | 0.56| | |
147
- | | |exact_match_stderr,flexible-extract| 0.01| | |
148
- | | |alias |gsm8k| | |
149
-
150
- Average: 55.27%
151
-
152
- Average score: Not available due to errors
153
-
154
- Elapsed time: 06:08:53
155
  ## 💻 Usage
156
 
157
  ```python
 
35
  value: [1, 0.5, 0.7, 0.3, 0]
36
  - value: 0.5
37
  ```
 
 
 
38
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39
  ## 💻 Usage
40
 
41
  ```python