List your company

Language Modeling on depth-12 LM

32Readable Cells RateDDC
612.7519.526.25Jun 28, 2026

Evaluation results

MethodLinks
DDCSetting=depth-12 LM, over-training, base optimiser=Adam, n=32026.0632
AdamWSetting=depth-12 LM, over-training, base optimiser=Adam, n=32026.067