wandbot-eval2 Workspace – Weights & Biases

Skip to main content

Evaluations

Filter

inputs

output

get_answer_correctness

model_latency

model_output

answer_correctness

answer_in_context

Trace

Feedback

Status

model

self

true_count

true_fraction

mean

true_count

true_fraction

Evaluation.evaluate

EvaluatorModel:v12

2

1

117.6286

N/A

N/A

Evaluation.evaluate

EvaluatorModel:v12

1

1

121.0161

N/A

N/A

Evaluation.evaluate

EvaluatorModel:v12

N/A

N/A

N/A

N/A

N/A

Evaluation.evaluate

EvaluatorModel:v12

76

0.8

37.6104

N/A

N/A

Evaluation.evaluate

EvaluatorModel:v12

2

1

42.7512

N/A

N/A

Evaluation.evaluate

EvaluatorModel:v12

N/A

N/A

N/A

N/A

N/A

Evaluation.evaluate

EvaluatorModel:v12

N/A

N/A

N/A

N/A

N/A

Evaluation.evaluate

EvaluatorModel:v12

N/A

N/A

N/A

N/A

N/A

top_k@10|threshold@0.5

EvaluatorModel:v11

18

0.2195

7.504

82

1

top_k@10|threshold@0.3

EvaluatorModel:v10

13

0.1566

7.9207

83

1

top_k@15|threshold@0.3

EvaluatorModel:v9

14

0.1772

8.6152

79

1

default-top_k@15

EvaluatorModel:v8

11

0.131

8.3827

84

1

default-top_k@5

EvaluatorModel:v7

14

0.1818

8.54

77

1

with_few-shot-examples

EvaluatorModel:v6

11

0.1196

15.6598

92

1

1-17 of 17

Per page:

50