gitea_admin/sientia-dataops-model-manager
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

SIENTIAPDE-1645: Add comprehensive model training observability metrics and Grafana dashboard.

Browse Source
This commit is contained in:
vitor-aignosi
2026-06-17 10:34:56 -03:00
parent 445fe643fe
commit 76f926a8ab
12 changed files with 866 additions and 175 deletions
Download Patch File Download Diff File Expand all files Collapse all files

197
dashboards/sientia-dataops-model-manager.json Normal file
View File

@@ -0,0 +1,197 @@
{
"annotations": { "list": [] },
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 1,
"links": [],
"panels": [
{
"id": 1,
"title": "Data Preparation Latency (p50 / p95)",
"type": "timeseries",
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 0 },
"targets": [
{
"expr": "histogram_quantile(0.5, rate(sientia_training_data_preparation_lag_bucket[5m]))",
"legendFormat": "p50",
"refId": "A"
},
{
"expr": "histogram_quantile(0.95, rate(sientia_training_data_preparation_lag_bucket[5m]))",
"legendFormat": "p95",
"refId": "B"
}
],
"fieldConfig": {
"defaults": { "unit": "s", "color": { "mode": "palette-classic" } }
},
"options": { "tooltip": { "mode": "multi" } }
},
{
"id": 2,
"title": "Model Fit Latency (p50 / p95)",
"type": "timeseries",
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 0 },
"targets": [
{
"expr": "histogram_quantile(0.5, rate(sientia_training_model_fit_lag_bucket[5m]))",
"legendFormat": "p50",
"refId": "A"
},
{
"expr": "histogram_quantile(0.95, rate(sientia_training_model_fit_lag_bucket[5m]))",
"legendFormat": "p95",
"refId": "B"
}
],
"fieldConfig": {
"defaults": { "unit": "s", "color": { "mode": "palette-classic" } }
},
"options": { "tooltip": { "mode": "multi" } }
},
{
"id": 3,
"title": "Data Preparation Errors / s",
"type": "timeseries",
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 8 },
"targets": [
{
"expr": "rate(sientia_training_data_preparation_error_count_total[5m])",
"legendFormat": "{{model_name}} / {{model_type}}",
"refId": "A"
}
],
"fieldConfig": {
"defaults": { "unit": "ops", "color": { "mode": "palette-classic" } }
}
},
{
"id": 4,
"title": "Model Fit Errors / s",
"type": "timeseries",
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 8 },
"targets": [
{
"expr": "rate(sientia_training_model_fit_error_count_total[5m])",
"legendFormat": "{{model_name}} / {{model_type}}",
"refId": "A"
}
],
"fieldConfig": {
"defaults": { "unit": "ops", "color": { "mode": "palette-classic" } }
}
},
{
"id": 5,
"title": "Model Quality — MSE",
"type": "stat",
"gridPos": { "h": 4, "w": 8, "x": 0, "y": 16 },
"targets": [
{
"expr": "sientia_training_model_quality_mse",
"legendFormat": "{{model_name}}",
"refId": "A"
}
],
"fieldConfig": {
"defaults": { "unit": "none", "decimals": 4 }
},
"options": { "reduceOptions": { "calcs": ["lastNotNull"] }, "orientation": "auto", "textMode": "auto", "colorMode": "value" }
},
{
"id": 6,
"title": "Model Quality — MAE",
"type": "stat",
"gridPos": { "h": 4, "w": 8, "x": 8, "y": 16 },
"targets": [
{
"expr": "sientia_training_model_quality_mae",
"legendFormat": "{{model_name}}",
"refId": "A"
}
],
"fieldConfig": {
"defaults": { "unit": "none", "decimals": 4 }
},
"options": { "reduceOptions": { "calcs": ["lastNotNull"] }, "orientation": "auto", "textMode": "auto", "colorMode": "value" }
},
{
"id": 7,
"title": "Model Quality — R²",
"type": "stat",
"gridPos": { "h": 4, "w": 8, "x": 16, "y": 16 },
"targets": [
{
"expr": "sientia_training_model_quality_r2",
"legendFormat": "{{model_name}}",
"refId": "A"
}
],
"fieldConfig": {
"defaults": { "unit": "percentunit", "decimals": 3, "min": -1, "max": 1 }
},
"options": { "reduceOptions": { "calcs": ["lastNotNull"] }, "orientation": "auto", "textMode": "auto", "colorMode": "background" }
},
{
"id": 8,
"title": "Dataset — Train Rows",
"type": "stat",
"gridPos": { "h": 4, "w": 8, "x": 0, "y": 20 },
"targets": [
{
"expr": "sientia_training_dataset_train_rows",
"legendFormat": "{{model_name}}",
"refId": "A"
}
],
"fieldConfig": {
"defaults": { "unit": "short", "decimals": 0 }
},
"options": { "reduceOptions": { "calcs": ["lastNotNull"] }, "orientation": "auto", "textMode": "auto", "colorMode": "value" }
},
{
"id": 9,
"title": "Dataset — Val Rows",
"type": "stat",
"gridPos": { "h": 4, "w": 8, "x": 8, "y": 20 },
"targets": [
{
"expr": "sientia_training_dataset_val_rows",
"legendFormat": "{{model_name}}",
"refId": "A"
}
],
"fieldConfig": {
"defaults": { "unit": "short", "decimals": 0 }
},
"options": { "reduceOptions": { "calcs": ["lastNotNull"] }, "orientation": "auto", "textMode": "auto", "colorMode": "value" }
},
{
"id": 10,
"title": "Dataset — Feature Count",
"type": "stat",
"gridPos": { "h": 4, "w": 8, "x": 16, "y": 20 },
"targets": [
{
"expr": "sientia_training_feature_count",
"legendFormat": "{{model_name}}",
"refId": "A"
}
],
"fieldConfig": {
"defaults": { "unit": "short", "decimals": 0 }
},
"options": { "reduceOptions": { "calcs": ["lastNotNull"] }, "orientation": "auto", "textMode": "auto", "colorMode": "value" }
}
],
"refresh": "30s",
"schemaVersion": 38,
"tags": ["sientia", "model-manager", "training"],
"templating": { "list": [] },
"time": { "from": "now-3h", "to": "now" },
"timepicker": {},
"timezone": "browser",
"title": "Sientia DataOps Model Manager",
"uid": "sientia-dataops-model-manager",
"version": 1
}