xianchaowu
commited on
Commit
•
c55ede9
1
Parent(s):
50ab133
json format
Browse files
README.md
CHANGED
@@ -80,71 +80,72 @@ print('after adding lazy lora parameters:')
|
|
80 |
model.print_trainable_parameters()
|
81 |
# trainable params: 0 || all params: 3,660,359,168 || trainable%: 0.0
|
82 |
|
83 |
-
|
84 |
```
|
85 |
|
86 |
## MMLU result:
|
87 |
|
88 |
-
|
89 |
-
|
90 |
-
|
91 |
-
|
92 |
-
|
93 |
-
|
94 |
-
|
95 |
-
|
96 |
-
|
97 |
-
|
98 |
-
|
99 |
-
|
100 |
-
|
101 |
-
|
102 |
-
|
103 |
-
|
104 |
-
|
105 |
-
|
106 |
-
|
107 |
-
|
108 |
-
|
109 |
-
|
110 |
-
|
111 |
-
|
112 |
-
|
113 |
-
|
114 |
-
|
115 |
-
|
116 |
-
|
117 |
-
|
118 |
-
|
119 |
-
|
120 |
-
|
121 |
-
|
122 |
-
|
123 |
-
|
124 |
-
|
125 |
-
|
126 |
-
|
127 |
-
|
128 |
-
|
129 |
-
|
130 |
-
|
131 |
-
|
132 |
-
|
133 |
-
|
134 |
-
|
135 |
-
|
136 |
-
|
137 |
-
|
138 |
-
|
139 |
-
|
140 |
-
|
141 |
-
|
142 |
-
|
143 |
-
|
144 |
-
|
145 |
-
|
146 |
-
|
147 |
-
|
|
|
|
|
148 |
|
149 |
## License and intended use
|
150 |
|
|
|
80 |
model.print_trainable_parameters()
|
81 |
# trainable params: 0 || all params: 3,660,359,168 || trainable%: 0.0
|
82 |
|
|
|
83 |
```
|
84 |
|
85 |
## MMLU result:
|
86 |
|
87 |
+
```json
|
88 |
+
{"mmlu_loss": 1.8361594152170253,
|
89 |
+
"mmlu_eval_accuracy_us_foreign_policy": 0.6363636363636364,
|
90 |
+
"mmlu_eval_accuracy_world_religions": 0.7368421052631579,
|
91 |
+
"mmlu_eval_accuracy_high_school_us_history": 0.6363636363636364,
|
92 |
+
"mmlu_eval_accuracy_high_school_psychology": 0.6166666666666667,
|
93 |
+
"mmlu_eval_accuracy_public_relations": 0.3333333333333333,
|
94 |
+
"mmlu_eval_accuracy_high_school_european_history": 0.6666666666666666,
|
95 |
+
"mmlu_eval_accuracy_econometrics": 0.16666666666666666,
|
96 |
+
"mmlu_eval_accuracy_high_school_microeconomics": 0.34615384615384615,
|
97 |
+
"mmlu_eval_accuracy_machine_learning": 0.18181818181818182,
|
98 |
+
"mmlu_eval_accuracy_high_school_mathematics": 0.3448275862068966,
|
99 |
+
"mmlu_eval_accuracy_high_school_computer_science": 0.5555555555555556,
|
100 |
+
"mmlu_eval_accuracy_professional_accounting": 0.3548387096774194,
|
101 |
+
"mmlu_eval_accuracy_high_school_world_history": 0.5,
|
102 |
+
"mmlu_eval_accuracy_marketing": 0.72,
|
103 |
+
"mmlu_eval_accuracy_sociology": 0.7272727272727273,
|
104 |
+
"mmlu_eval_accuracy_nutrition": 0.5454545454545454,
|
105 |
+
"mmlu_eval_accuracy_high_school_chemistry": 0.4090909090909091,
|
106 |
+
"mmlu_eval_accuracy_logical_fallacies": 0.5555555555555556,
|
107 |
+
"mmlu_eval_accuracy_college_mathematics": 0.18181818181818182,
|
108 |
+
"mmlu_eval_accuracy_computer_security": 0.2727272727272727,
|
109 |
+
"mmlu_eval_accuracy_miscellaneous": 0.6046511627906976,
|
110 |
+
"mmlu_eval_accuracy_high_school_statistics": 0.2608695652173913,
|
111 |
+
"mmlu_eval_accuracy_philosophy": 0.4117647058823529,
|
112 |
+
"mmlu_eval_accuracy_global_facts": 0.4,
|
113 |
+
"mmlu_eval_accuracy_management": 0.2727272727272727,
|
114 |
+
"mmlu_eval_accuracy_human_aging": 0.6956521739130435,
|
115 |
+
"mmlu_eval_accuracy_moral_scenarios": 0.25,
|
116 |
+
"mmlu_eval_accuracy_human_sexuality": 0.5,
|
117 |
+
"mmlu_eval_accuracy_abstract_algebra": 0.36363636363636365,
|
118 |
+
"mmlu_eval_accuracy_high_school_macroeconomics": 0.3488372093023256,
|
119 |
+
"mmlu_eval_accuracy_electrical_engineering": 0.375,
|
120 |
+
"mmlu_eval_accuracy_professional_medicine": 0.45161290322580644,
|
121 |
+
"mmlu_eval_accuracy_high_school_government_and_politics": 0.6666666666666666,
|
122 |
+
"mmlu_eval_accuracy_high_school_biology": 0.3125,
|
123 |
+
"mmlu_eval_accuracy_astronomy": 0.4375,
|
124 |
+
"mmlu_eval_accuracy_security_studies": 0.4074074074074074,
|
125 |
+
"mmlu_eval_accuracy_prehistory": 0.42857142857142855,
|
126 |
+
"mmlu_eval_accuracy_conceptual_physics": 0.3076923076923077,
|
127 |
+
"mmlu_eval_accuracy_college_medicine": 0.36363636363636365,
|
128 |
+
"mmlu_eval_accuracy_moral_disputes": 0.39473684210526316,
|
129 |
+
"mmlu_eval_accuracy_anatomy": 0.5,
|
130 |
+
"mmlu_eval_accuracy_clinical_knowledge": 0.41379310344827586,
|
131 |
+
"mmlu_eval_accuracy_college_computer_science": 0.5454545454545454,
|
132 |
+
"mmlu_eval_accuracy_high_school_geography": 0.5909090909090909,
|
133 |
+
"mmlu_eval_accuracy_college_chemistry": 0.125,
|
134 |
+
"mmlu_eval_accuracy_professional_psychology": 0.36231884057971014,
|
135 |
+
"mmlu_eval_accuracy_virology": 0.4444444444444444,
|
136 |
+
"mmlu_eval_accuracy_international_law": 0.8461538461538461,
|
137 |
+
"mmlu_eval_accuracy_medical_genetics": 0.8181818181818182,
|
138 |
+
"mmlu_eval_accuracy_formal_logic": 0.14285714285714285,
|
139 |
+
"mmlu_eval_accuracy_professional_law": 0.34705882352941175,
|
140 |
+
"mmlu_eval_accuracy_college_biology": 0.25,
|
141 |
+
"mmlu_eval_accuracy_jurisprudence": 0.45454545454545453,
|
142 |
+
"mmlu_eval_accuracy_business_ethics": 0.5454545454545454,
|
143 |
+
"mmlu_eval_accuracy_college_physics": 0.5454545454545454,
|
144 |
+
"mmlu_eval_accuracy_high_school_physics": 0.29411764705882354,
|
145 |
+
"mmlu_eval_accuracy_elementary_mathematics": 0.3170731707317073,
|
146 |
+
"mmlu_eval_accuracy": 0.4435841258637352,
|
147 |
+
"epoch": 1.36}
|
148 |
+
```
|
149 |
|
150 |
## License and intended use
|
151 |
|