Pre-launch· Token not live yet — no rewards or treasury until launchWhat this means
← Model
Deeper decision trees — retrained on new data

TRAIN v0.09

Same configuration as v0.05 (best so far on the headline benchmark), retrained on the newest dataset.
Completedpreviously deployed

Definition

Model type
Decision-tree ensemble
Signals used
Market signals
Technical details
max_depth
3
subsample
0.8
n_estimators
300
learning_rate
0.03
min_samples_leaf
10
Random seed
1009
Config hash
da2b7258b9e789f8
Created
05 Oct 09:12
Completed
05 Oct 09:13
Artifact
models/v0.09/model.json
sha256 13382a07e62e622d…

Dataset & compute

Dataset
Solana Launch Dataset v8
3,757 snapshots · 753 launches · sha256 7a3cc82a36d5
Training runs
1
Compute
TRAIN training server (CPU)
GPU hours
—
no GPU used
CPU time
17.5 s
Provider cost
$0.00
nothing purchased

Benchmarks

held-out test set · change vs v0.08
Spotting crashes (−70% within 1h)
0.934
Spotting survivors (still traded after 1h)
0.907
Spotting 2× runs (within 1h)
0.856
Calling the 1h direction (down / flat / up)
56.5%
Spotting creator dumps (within 1h)
0.825
Spotting crashes (within 6h)
insufficient data
Spotting survivors (6h)
insufficient data
Calling the 6h direction
insufficient data
Spotting survivors (24h)
insufficient data
Spotting migrations (within 24h)
insufficient data

Validation metrics (during training)

collapse_1h
AUC 0.993
n=425
collapse_6h
—
n=0
reach_2x_1h
AUC 0.979
n=425
survival_1h
AUC 0.897
n=425
survival_6h
—
n=0
survival_24h
—
n=0
migration_24h
—
n=0
trajectory_1h
acc 97.2%
n=425
trajectory_6h
—
n=0
creator_exit_1h
AUC 0.808
n=130

Validation launches are separate from training launches and from the locked test set. Benchmarks above are the public numbers.

What this version relies on

held-out validation launches
This version was trained before TRAIN started measuring which signals each model relies on.

For each signal, how much the score drops when that signal is scrambled across launches. TRAIN learns these weights itself from the data; nobody hand-codes them.

Training runs

Attempt 1Succeeded
05 Oct 09:12 · 00:00:13 · 3,332 examples · $0.00

Timeline

  1. 05 Oct 09:13
    TRAIN v0.09 deployed — now live
    average score across 5 tests 0.812 vs 0.795 for the live v0.08
  2. 05 Oct 09:13
    Benchmark completed: TRAIN v0.09
    Crash-spotting score: 0.911 (n=158).
  3. 05 Oct 09:13
    Benchmark started: TRAIN v0.09
  4. 05 Oct 09:13
    Training completed: TRAIN v0.09
    00:00:13 · trained on 3332 examples · $0 compute cost
  5. 05 Oct 09:12
    Training started: TRAIN v0.09
    Solana Launch Dataset v8 · decision-tree ensemble · TRAIN training server
  6. 05 Oct 09:12
    TRAIN v0.09 queued
    Same configuration as v0.05 (best so far on the headline benchmark), retrained on the newest dataset.