HMM symbol prediction on HMM High-entropy v1 (val)
0.001Excess 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 | 0.001 | 0.335 | 25.7 | 0.027 | 0 | 0 |