metadata
datasets:
- Marcus2112/minipile_low-density-proportioned
language:
- en
base_model:
- EleutherAI/pythia-160m-deduped
Benchmark | Measure | 160M MiniPile | 160M Low Density | |
---|---|---|---|---|
ARC-Challenge | acc | ↑ | 0.2125 ± 0.0120 | 0.1886 ± 0.0114 |
MMLU | acc | ↑ | 0.2699 ± 0.0037 | 0.2295 ± 0.0035 |
HellaSwag | acc | ↑ | 0.2560 ± 0.0044 | 0.2508 ± 0.0044 |
WinoGrande | acc | ↑ | 0.4720 ± 0.0140 | 0.5067 ± 0.0141 |
Lambada (OpenAI) | acc | ↑ | 0.0000 ± 0.0000 | 0.0000 ± 0.0000 |
Lambada (OpenAI) | perplexity | ↓ | 3033175.2693 ± 288926.5827 | 2287598.5548 ± 192724.6151 |
Lambada (Std) | acc | ↑ | 0.0000 ± 0.0000 | 0.0000 ± 0.0000 |
Lambada (Std) | perplexity | ↓ | 27067951.3460 ± 2710040.191 | 16223747.0588 ± 1503858.3054 |
BLiMP | acc | ↑ | 0.5194 ± 0.0018 | 0.5504 ± 0.0170 |