Benchmark	Measure		160M MiniPile	160M MiniPile Lossi
ARC-Challenge	acc	↑	0.2125 ± 0.0120	0.1980 ± 0.0116
MMLU	acc	↑	0.2699 ± 0.0037	0.2295 ± 0.0035
HellaSwag	acc	↑	0.2560 ± 0.0044	0.2599 ± 0.0044
WinoGrande	acc	↑	0.4720 ± 0.0140	0.5107 ± 0.0140
Lambada (OpenAI)	acc	↑	0.0000 ± 0.0000	0.0000 ± 0.0000
Lambada (OpenAI)	perplexity	↓	3033175.2693 ± 288926.5827	2116445.1732 ± 175403.0579
Lambada (Std)	acc	↑	0.0000 ± 0.0000	0.0000 ± 0.0000
Lambada (Std)	perplexity	↓	27067951.3460 ± 2710040.191	14896599.9251 ± 1366937.5470
BLiMP	acc	↑	0.5194 ± 0.0018	0.5492 ± 0.0017

Safetensors

Model size

0.2B 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_loss-sampled

Base model

Finetuned

(52)

this model

Dataset used to train Marcus2112/pythia-160m-minipile_loss-sampled