The TwitterAAE corpus of [Blodgett et al. (2016)](https://aclanthology.org/D16-1120/) for measuring language model performance on White-aligned Tweets.

twitter_aae_white

The TwitterAAE corpus of [Blodgett et al. (2016)](https://aclanthology.org/D16-1120/) for measuring language model performance on White-aligned Tweets.

Bits/byte: Average number of bits per byte according to model probabilities.

The TwitterAAE corpus of [Blodgett et al. (2016)](https://aclanthology.org/D16-1120/) for measuring language model performance on White-aligned Tweets.

Denoised inference runtime (s): Average time to process a request to the model minus performance contention by using profiled runtimes from multiple trials of SyntheticEfficiencyScenario.

The TwitterAAE corpus of [Blodgett et al. (2016)](https://aclanthology.org/D16-1120/) for measuring language model performance on White-aligned Tweets.

# eval: Number of evaluation instances.

The TwitterAAE corpus of [Blodgett et al. (2016)](https://aclanthology.org/D16-1120/) for measuring language model performance on White-aligned Tweets.

# train: Number of training instances (e.g., in-context examples).

The TwitterAAE corpus of [Blodgett et al. (2016)](https://aclanthology.org/D16-1120/) for measuring language model performance on White-aligned Tweets.

truncated: Fraction of instances where the prompt itself was truncated (implies that there were no in-context examples).

The TwitterAAE corpus of [Blodgett et al. (2016)](https://aclanthology.org/D16-1120/) for measuring language model performance on White-aligned Tweets.

# prompt tokens: Number of tokens in the prompt.

The TwitterAAE corpus of [Blodgett et al. (2016)](https://aclanthology.org/D16-1120/) for measuring language model performance on White-aligned Tweets.

# output tokens: Actual number of output tokens.

The TwitterAAE corpus of [Blodgett et al. (2016)](https://aclanthology.org/D16-1120/) for measuring language model performance on White-aligned Tweets.

# trials: Number of trials, where in each trial we choose an independent, random set of training instances.

twitter_aae_white_demographic:white

min=1.829, mean=1.829, max=1.829, sum=1.829 (1)

min=0.263, mean=0.263, max=0.263, sum=0.263 (1)

min=1000, mean=1000, max=1000, sum=1000 (1)

min=12.885, mean=12.885, max=12.885, sum=12.885 (1)

min=1.888, mean=1.888, max=1.888, sum=1.888 (1)

min=0.24, mean=0.24, max=0.24, sum=0.24 (1)

min=1.852, mean=1.852, max=1.852, sum=1.852 (1)

min=0.288, mean=0.288, max=0.288, sum=0.288 (1)

min=1.824, mean=1.824, max=1.824, sum=1.824 (1)

min=1.798, mean=1.798, max=1.798, sum=1.798 (1)

min=1.813, mean=1.813, max=1.813, sum=1.813 (1)

min=1.841, mean=1.841, max=1.841, sum=1.841 (1)

min=1.86, mean=1.86, max=1.86, sum=1.86 (1)

min=0.742, mean=0.742, max=0.742, sum=0.742 (1)

min=17.983, mean=17.983, max=17.983, sum=17.983 (1)

min=6.044, mean=6.044, max=6.044, sum=6.044 (1)

min=1.644, mean=1.644, max=1.644, sum=1.644 (1)

min=0.036, mean=0.036, max=0.036, sum=0.036 (1)

min=17.243, mean=17.243, max=17.243, sum=17.243 (1)

min=1.941, mean=1.941, max=1.941, sum=1.941 (1)

min=0.321, mean=0.321, max=0.321, sum=0.321 (1)

min=18.096, mean=18.096, max=18.096, sum=18.096 (1)

min=1.954, mean=1.954, max=1.954, sum=1.954 (1)

min=0.205, mean=0.205, max=0.205, sum=0.205 (1)

min=1.968, mean=1.968, max=1.968, sum=1.968 (1)

min=0.19, mean=0.19, max=0.19, sum=0.19 (1)

min=2.136, mean=2.136, max=2.136, sum=2.136 (1)

min=0.215, mean=0.215, max=0.215, sum=0.215 (1)

min=1.955, mean=1.955, max=1.955, sum=1.955 (1)

min=2.039, mean=2.039, max=2.039, sum=2.039 (1)

min=2.201, mean=2.201, max=2.201, sum=2.201 (1)

min=1.001, mean=1.001, max=1.001, sum=1.001 (1)

min=2.308, mean=2.308, max=2.308, sum=2.308 (1)

min=1.675, mean=1.675, max=1.675, sum=1.675 (1)

min=0.437, mean=0.437, max=0.437, sum=0.437 (1)

min=1.632, mean=1.632, max=1.632, sum=1.632 (1)

min=0.824, mean=0.824, max=0.824, sum=0.824 (1)

min=18.141, mean=18.141, max=18.141, sum=18.141 (1)

min=1.506, mean=1.506, max=1.506, sum=1.506 (1)

min=0.233, mean=0.233, max=0.233, sum=0.233 (1)

min=1.57, mean=1.57, max=1.57, sum=1.57 (1)

min=1.262, mean=1.262, max=1.262, sum=1.262 (1)

min=1.903, mean=1.903, max=1.903, sum=1.903 (1)

min=1.972, mean=1.972, max=1.972, sum=1.972 (1)

min=1.806, mean=1.806, max=1.806, sum=1.806 (1)

min=0.185, mean=0.185, max=0.185, sum=0.185 (1)

min=1.864, mean=1.864, max=1.864, sum=1.864 (1)

min=0.08, mean=0.08, max=0.08, sum=0.08 (1)

min=1.936, mean=1.936, max=1.936, sum=1.936 (1)

min=0.111, mean=0.111, max=0.111, sum=0.111 (1)

min=2.025, mean=2.025, max=2.025, sum=2.025 (1)

min=0.136, mean=0.136, max=0.136, sum=0.136 (1)

min=1.862, mean=1.862, max=1.862, sum=1.862 (1)

min=1.815, mean=1.815, max=1.815, sum=1.815 (1)

min=0.16, mean=0.16, max=0.16, sum=0.16 (1)

min=2.221, mean=2.221, max=2.221, sum=2.221 (1)

min=0.12, mean=0.12, max=0.12, sum=0.12 (1)

min=2.506, mean=2.506, max=2.506, sum=2.506 (1)

min=0.123, mean=0.123, max=0.123, sum=0.123 (1)

min=3.048, mean=3.048, max=3.048, sum=3.048 (1)

min=0.077, mean=0.077, max=0.077, sum=0.077 (1)