blob: 71d9851168932d416e4cf45859290d7b8b675b0f (
plain)
1
2
3
4
5
6
7
8
9
10
11
|
{
"author": "Spokane Way",
"github_id": "spokane-way",
"name": "Training Opt Seq4096 v1",
"blurb": "SP-1024 9x512 KV4 run at TRAIN_SEQ_LEN=4096 with aggressively tuned Muon optimizer: momentum 0.99, lower LR (0.020/0.020/0.030), 3/4 batch (393K tokens), warmdown 3000 steps, and extended momentum warmup (1500 steps from 0.92). Combines long-context training with training optimization to beat the naive baseline by 0.023 BPB.",
"date": "2026-03-19T04:28:00Z",
"val_loss": 2.02857127,
"val_bpb": 1.20143417,
"bytes_total": 15868326,
"bytes_code": 47759
}
|
