| { |
| "step": 6500, |
| "max_steps": 28820, |
| "percent_complete": 22.554, |
| "tokens_seen": 20786970624, |
| "compute_tokens_seen": 3464495104, |
| "compute_tokens_total": 15109980160, |
| "percent_tokens": 22.929, |
| "val_loss": 5.523073740303516, |
| "val_ppl": 250.40353093471919, |
| "params_M": 149.976, |
| "pushed_at": "2026-11-13T07:27:27Z", |
| "architecture": "Oleander-150M", |
| "features": [ |
| "GDN2 (gated delta net 2) x21: 9h x 64, conv4", |
| "gated GQA x7: 9 Q / 3 KV heads, head_dim 64", |
| "QK-Norm (offset form)", |
| "partial RoPE (rotary_dim 32, theta 100000)", |
| "value residual (v_mix)", |
| "SwiGLU", |
| "RMSNorm", |
| "AttnRes (block attention residuals)", |
| "tied embeddings", |
| "TST (token superposition training, bag 6)" |
| ], |
| "optimizer": "muon_adamw", |
| "phase": "tst", |
| "kind": "export" |
| } |
