Benchmark Measure 160M MiniPile 160M Density Pico Percentage Difference in Means
ARC-Challenge acc 0.2125 ± 0.0120 0.1903 ± 0.0115 -10.4471
MMLU acc 0.2699 ± 0.0037 0.2295 ± 0.0035 -14.9685
HellaSwag acc 0.2560 ± 0.0044 0.2583 ± 0.0044 0.8984
WinoGrande acc 0.4720 ± 0.0140 0.4957 ± 0.0141 5.0212
Lambada (OpenAI) acc 0.0000 ± 0.0000 0.0000 ± 0.0000 -
Lambada (OpenAI) perplexity 3033175.2693 ± 288926.5827 1964196.9255 ± 153419.7846 -35.2429
Lambada (Std) acc 0.0000 ± 0.0000 0.0000 ± 0.0000 -
Lambada (Std) perplexity 27067951.3461 ± 2710040.1910 10720344.5522 ± 925236.7038 -60.3947
BLiMP acc 0.5194 ± 0.0018 0.5383 ± 0.0017 3.6388
Downloads last month
12
Safetensors
Model size
162M params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Marcus2112/pythia-160m-minipile_pico_density-proportioned

Finetuned
(123)
this model

Dataset used to train Marcus2112/pythia-160m-minipile_pico_density-proportioned

Collection including Marcus2112/pythia-160m-minipile_pico_density-proportioned