You are on page 1of 11

OPEN AI

PLAYGROUND
PARAMETERS
AGENDA

PLAYGROUND Frequency Penalty

Models Presence Penalty

Temperature Best of

Maximum Length Inject starter Text

Stop Sequences Inject restart Text

Top P Show Probabilities

2023 PARAMETERS 2
PLAYGROUND

2023 PARAMETERS 3
TEMPERATURE
The temperature controls how much randomness is in the output.
 TEMPERATURE

• Lower the temperature, the more likely GPT-3 will choose words with a higher probability of
occurrence
• It’s useful when we want GPT3 to complete something  where there is only one answer and vice versa
• Example: Generate Ideas or Complete a story
• Higher temperature will bring us more variety.
• Sometimes people call Temperature a creativity setting, but official documentation discourages such a
label. Creativity is more complex than just raising the randomness.
TEMPERATURE = 0

• Let’s test the lowest temperature on a fairly common sentence: “My favorite animal is.” As you
might expect with randomness limited to zero, GPT-3 will come up with the most probable
completion — “a dog”

One run (Engine = davinci; Response Length = 12; Temperature= 0, Stop Sequences = “.”)

2023 PARAMETERS 6
TEMPERATURE = 0

• Eliminating randomness has another effect: GPT-3 will always produce the same output for a given
prompt. We ran the prompt 10 times, and we received 10 exact same outputs. Lower temperature is
suitable for cases when we need stability, most probable output (factual output, classification, etc.)

ten runs (Engine = davinci; Response Length = 12; Temperature= 0, Stop Sequences = “.”)
2023 PARAMETERS 7
TEMPERATURE = 0
• Thanks to the “Show Probabilities” setting, we can see how GPT-3 sees the world, and the words
(tokens) that should come next (the list in the screenshot covers ~38% of possible cases).
• Not surprisingly, the second most probable output after “dog” is “cat,” and a third is “gir,” which is very
likely token from the word “giraffe.” So when we talk about randomness, we mean that GPT-3 is going
for tokens with various levels of probability.

2023 PARAMETERS 8
TEMPERATURE = 1.0
• Setting the temperature value to 1 will deliver very inconsistent and sometimes interesting results.
Even for open-ended tasks you should use a temperature value of 1 only in special situations. It is more
common for story completion or idea generation to see temperature values between 0.7 to 0.9.

ten runs (Engine = Davinci, Temperature= 1, Stop Sequences = “.”)

2023 PARAMETERS 9
TEMPERATURE = 0.75
• Typically, a temperature between 0.70–0.90 is the most common for creative tasks. Before looking at
the output below, try to guess what kind of output GPT-3 will generate on a setting temperature of 0.75
for “My favorite animal is” completion.

With slightly lower randomness, we are getting more consistent results. GPT-3
more often ends with a period right after the animal. We got Velociraptor,
which is nice, but no nonexistent animals.

2023 PARAMETERS 10
SUMMARY
• Although there are some general recommendations on Temperature settings, nothing is set in stone.
As this is one of the most important settings, it’s worth playing around, see what impact the changes
have on different kinds of prompts. It will help you to be a better prompter

2023 PARAMETERS 11

You might also like