metadata
datasets:
- roneneldan/TinyStories
metrics:
- babylm
Basemodel: GPT-Neo
Configs: Vocab size: 10,000 Hidden size: 512 Max position embeddings: 512 Number of layers: 2 Number of heads: 4 Window size: 256 Intermediate-size: 1024
Results:
- Task: glue Score: 59.41 Confidence Interval: [59.0, 59.82]
- Task: blimp Score: 56.91 Confidence Interval: [55.93, 57.8]