Pre-launch· Token not live yet — no rewards or treasury until launchWhat this means
← Model
Price & volume only

TRAIN v0.02

First learned model: logistic regression on price and volume only (12 features).
Completed

Definition

Model type
Linear model
Signals used
Market signals
12 selected signals
Technical details
C
0.5
Random seed
1002
Config hash
e07fd5b508e71b31
Created
05 Oct 02:56
Completed
05 Oct 02:56
Artifact
models/v0.02/model.json
sha256 c98f58dc704dc01f…

Dataset & compute

Dataset
Solana Launch Dataset v1
60 snapshots · 12 launches · sha256 010016f628b3
Training runs
1
Compute
TRAIN training server (CPU)
GPU hours
—
no GPU used
CPU time
4.3 s
Provider cost
$0.00
nothing purchased

Benchmarks

held-out test set · change vs v0.01
Spotting crashes (−70% within 1h)
0.463
Spotting survivors (still traded after 1h)
0.711
Spotting 2× runs (within 1h)
0.500
Calling the 1h direction (down / flat / up)
34.1%
Spotting creator dumps (within 1h)
0.500
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
—
n=0
collapse_6h
—
n=0
reach_2x_1h
—
n=0
survival_1h
—
n=0
survival_6h
—
n=0
survival_24h
—
n=0
migration_24h
—
n=0
trajectory_1h
—
n=0
trajectory_6h
—
n=0
creator_exit_1h
—
n=0

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 02:56 · 00:00:00 · 60 examples · $0.00

Timeline

  1. 05 Oct 02:56
    TRAIN v0.02 not deployed; v0.01 stays live
    Reason: no shared benchmarks yet; keeping the live model.
  2. 05 Oct 02:56
    Benchmark completed: TRAIN v0.02
    No locked test set yet (not enough held-out launches with observed outcomes). Benchmarks will be computed when it is locked.
  3. 05 Oct 02:56
    Benchmark started: TRAIN v0.02
  4. 05 Oct 02:56
    Training completed: TRAIN v0.02
    00:00:00 · trained on 60 examples · $0 compute cost
  5. 05 Oct 02:56
    Training started: TRAIN v0.02
    Solana Launch Dataset v1 · linear model · TRAIN training server
  6. 05 Oct 02:56
    TRAIN v0.02 queued
    First learned model: logistic regression on price and volume only (12 features).