Activity
Everything TRAIN does, in order
Training runs, benchmarks, deployments, dataset updates, data-provider failures — and, once the token exists, rewards and compute purchases. Everything here really happened.
- 05 Oct 03:24Training completed: TRAIN v0.0300:00:00 · trained on 110 examples · $0 compute cost
- 05 Oct 03:24Training started: TRAIN v0.03Solana Launch Dataset v2 · linear model · TRAIN training server
- 05 Oct 03:24Dataset updated: Solana Launch Dataset v2115 snapshots from 23 launches.
- 05 Oct 03:24TRAIN v0.03 queuedAdds trade-flow, holder-estimate, creator-history and social features (all 36 features in set f1).
- 05 Oct 02:56TRAIN v0.02 not deployed; v0.01 stays liveReason: no shared benchmarks yet; keeping the live model.
- 05 Oct 02:56Benchmark completed: TRAIN v0.02No locked test set yet (not enough held-out launches with observed outcomes). Benchmarks will be computed when it is locked.
- 05 Oct 02:56Benchmark started: TRAIN v0.02
- 05 Oct 02:56Training completed: TRAIN v0.0200:00:00 · trained on 60 examples · $0 compute cost
- 05 Oct 02:56Training started: TRAIN v0.02Solana Launch Dataset v1 · linear model · TRAIN training server
- 05 Oct 02:56TRAIN v0.02 queuedFirst learned model: logistic regression on price and volume only (12 features).
- 05 Oct 02:55TRAIN v0.01 deployed — now livefirst completed model
- 05 Oct 02:55Benchmark completed: TRAIN v0.01No locked test set yet (not enough held-out launches with observed outcomes). Benchmarks will be computed when it is locked.
- 05 Oct 02:55Benchmark started: TRAIN v0.01
- 05 Oct 02:55Training completed: TRAIN v0.0100:00:00 · trained on 60 examples · $0 compute cost
- 05 Oct 02:55Training started: TRAIN v0.01Solana Launch Dataset v1 · baseline (averages) · TRAIN training server
- 05 Oct 02:55Dataset updated: Solana Launch Dataset v160 snapshots from 12 launches.
- 05 Oct 02:55TRAIN v0.01 queuedBaseline. Predicts each outcome's historical base rate and ignores the token entirely. Every later version has to beat this to be worth anything.