Spaces:
Running
Running
File size: 6,560 Bytes
b9e00cb 2f9157a b9e00cb 2f9157a b9e00cb 2f9157a b9e00cb 2f9157a b9e00cb 2f9157a b9e00cb 2f9157a b9e00cb 2f9157a b9e00cb 2f9157a b9e00cb 2f9157a b9e00cb 2f9157a b9e00cb 2f9157a b9e00cb 2f9157a b9e00cb 2f9157a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 |
from intel_evaluate_extension.evaluation_suite.model_card_suite import ModelCardSuiteResults
from evaluate.evaluation_suite import SubTask
from evaluate.visualization import radar_plot
_HEADER = "GLUE/AdvGlue Evaluation Results"
_DESCRIPTION = """
The suite compares the GLUE results with Adversarial GLUE (AdvGLUE), a
multi-task benchmark that tests the vulnerability of modern large-scale
language models againstvarious adversarial attacks."""
class Suite(ModelCardSuiteResults):
def __init__(self, name):
super().__init__(name)
self.result_keys = ["accuracy", "f1"]
self.preprocessor = lambda x: {"text": x["text"].lower()}
self.suite = [
SubTask(
task_type="text-classification",
data="glue",
subset="sst2",
split="validation[:5]",
args_for_task={
"metric": "glue",
"input_column": "sentence",
"label_column": "label",
"config_name": "sst2",
"label_mapping": {"LABEL_0": 0.0, "LABEL_1": 1.0},
},
),
SubTask(
task_type="text-classification",
data="adv_glue",
subset="adv_sst2",
split="validation[:5]",
args_for_task={
"metric": "glue",
"input_column": "sentence",
"label_column": "label",
"config_name": "sst2",
"label_mapping": {"LABEL_0": 0.0, "LABEL_1": 1.0},
},
),
SubTask(
task_type="text-classification",
data="glue",
subset="qqp",
split="validation[:5]",
args_for_task={
"metric": "glue",
"input_column": "question1",
"second_input_column": "question2",
"label_column": "label",
"config_name": "qqp",
"label_mapping": {"LABEL_0": 0, "LABEL_1": 1},
},
),
SubTask(
task_type="text-classification",
data="adv_glue",
subset="adv_qqp",
split="validation[:5]",
args_for_task={
"metric": "glue",
"input_column": "question1",
"second_input_column": "question2",
"label_column": "label",
"config_name": "qqp",
"label_mapping": {"LABEL_0": 0, "LABEL_1": 1},
},
),
SubTask(
task_type="text-classification",
data="glue",
subset="qnli",
split="validation[:5]",
args_for_task={
"metric": "glue",
"input_column": "question",
"second_input_column": "sentence",
"label_column": "label",
"config_name": "qnli",
"label_mapping": {"LABEL_0": 0, "LABEL_1": 1},
},
),
SubTask(
task_type="text-classification",
data="adv_glue",
subset="adv_qnli",
split="validation[:5]",
args_for_task={
"metric": "glue",
"input_column": "question",
"second_input_column": "sentence",
"label_column": "label",
"config_name": "qnli",
"label_mapping": {"LABEL_0": 0, "LABEL_1": 1},
},
),
SubTask(
task_type="text-classification",
data="glue",
subset="rte",
split="validation[:5]",
args_for_task={
"metric": "glue",
"input_column": "sentence1",
"second_input_column": "sentence2",
"label_column": "label",
"config_name": "rte",
"label_mapping": {"LABEL_0": 0, "LABEL_1": 1},
},
),
SubTask(
task_type="text-classification",
data="adv_glue",
subset="adv_rte",
split="validation[:5]",
args_for_task={
"metric": "glue",
"input_column": "sentence1",
"second_input_column": "sentence2",
"label_column": "label",
"config_name": "rte",
"label_mapping": {"LABEL_0": 0, "LABEL_1": 1},
},
),
SubTask(
task_type="text-classification",
data="glue",
subset="mnli",
split="validation_mismatched[:5]",
args_for_task={
"metric": "glue",
"input_column": "premise",
"second_input_column": "hypothesis",
"config_name": "mnli",
"label_mapping": {"LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2},
},
),
SubTask(
task_type="text-classification",
data="adv_glue",
subset="adv_mnli",
split="validation[:5]",
args_for_task={
"metric": "glue",
"input_column": "premise",
"second_input_column": "hypothesis",
"config_name": "mnli",
"label_mapping": {"LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2},
},
),
]
def process_results(self, results):
radar_data = [
{"accuracy " + result["task_name"].split("/")[-1]: result["accuracy"] for result in results[::2]},
{
"accuracy " + result["task_name"].replace("adv_", "").split("/")[-1]: result["accuracy"]
for result in results[1::2]
},
]
return radar_plot(radar_data, ["GLUE", "AdvGLUE"])
def plot_results(self, results, model_or_pipeline):
radar_data = self.process_results(results)
graphic = radar_plot(radar_data, ["GLUE " + model_or_pipeline, "AdvGLUE " + model_or_pipeline])
return graphic
|