Files
foxhunt/infra/k8s/argo/train-baseline-rl-template.yaml
jgrusewski f01c7f8181 fix: baseline-rl template adds required volumes + volumeClaimTemplates
Mirrors train-dqn's volume setup: git-ssh-key, training-data (rw),
cargo-target-cuda, workspace (dynamic PVC). training-data NOT
readOnly — needs write for checkpoints.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-01 21:05:38 +02:00

103 lines
2.6 KiB
YAML

# Baseline RL training — compile-and-train with hyperopt disabled.
#
# Identical to train-dqn but hardcodes hyperopt-trials=0.
# Compiles from source, skips hyperopt, trains with default params.
#
# Usage:
# argo submit -n foxhunt --from=wftmpl/train-baseline-rl
# argo submit -n foxhunt --from=wftmpl/train-baseline-rl -p train-epochs=100
---
apiVersion: argoproj.io/v1alpha1
kind: WorkflowTemplate
metadata:
name: train-baseline-rl
namespace: foxhunt
labels:
app.kubernetes.io/name: train-baseline-rl
app.kubernetes.io/part-of: foxhunt
spec:
entrypoint: pipeline
serviceAccountName: argo-workflow
podMetadata:
labels:
app.kubernetes.io/part-of: foxhunt
app.kubernetes.io/component: compile-and-train
securityContext:
fsGroup: 0
ttlStrategy:
secondsAfterCompletion: 3600
activeDeadlineSeconds: 14400
# Mirror ALL compile-and-train parameters — Argo resolves
# {{workflow.parameters.*}} in the caller's scope.
arguments:
parameters:
- name: commit-sha
value: HEAD
- name: git-branch
value: main
- name: cuda-compute-cap
value: "90"
- name: model
value: dqn
- name: gpu-pool
value: ci-training-h100
- name: hyperopt-trials
value: "0"
- name: hyperopt-epochs
value: "0"
- name: train-epochs
value: "50"
- name: symbol
value: ES.FUT
- name: data-dir
value: /data/futures-baseline
- name: mbp10-data-dir
value: /data/futures-baseline-mbp10
- name: trades-data-dir
value: /data/futures-baseline-trades
- name: feature-cache-dir
value: /data/feature-cache
- name: tx-cost-bps
value: "0.1"
- name: tick-size
value: "0.25"
- name: spread-ticks
value: "1.0"
- name: min-hold-bars
value: "5"
- name: initial-capital
value: "35000"
- name: ensemble-top-k
value: "5"
volumes:
- name: git-ssh-key
secret:
secretName: argo-git-ssh-key
defaultMode: 256
- name: training-data
persistentVolumeClaim:
claimName: training-data-pvc
- name: cargo-target-cuda
persistentVolumeClaim:
claimName: cargo-target-cuda
volumeClaimTemplates:
- metadata:
name: workspace
spec:
accessModes: ["ReadWriteOnce"]
storageClassName: scw-bssd
resources:
requests:
storage: 5Gi
templates:
- name: pipeline
steps:
- - name: run
templateRef:
name: compile-and-train
template: pipeline