HMM symbol prediction on HMM Persistent family v1 (val)
0.029Excess over BayesTwo-layer causal transformer
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| Two-layer causal transformerWidth=128, Attention heads=4, MLP width=256, Parameters=275k, Sequence length=64, Training sequences=60002026.05 | 0.029 | 0.448 | 49.8 | 0.388 | 0.075 | 0.022 |