HMM symbol prediction on HMM Ambiguous family v1 (val)
0.003Excess 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 | 0.003 | 0.152 | 31.5 | 0.441 | 0.004 | 0.001 |