{ "containerStatuses": [ { "name": "node", "state": { "terminated": { "exitCode": 0, "reason": "Completed", "message": "{\"progressPercentage\": 100, \"estimatedRemainingSeconds\": 0, \"currentStep\": 100, \"totalSteps\": 100, \"currentEpoch\": 5.0, \"totalEpochs\": 5, \"trainMetrics\": {\"loss\": 2.0777618408203127, \"grad_norm\": 7.419865131378174, \"learning_rate\": 5.000000000000001e-07, \"throughput_samples_sec\": 0.984, \"train_loss\": 2.4961353015899657}, \"evalMetrics\": {\"eval_loss\": 2.5037848949432373, \"eval_runtime\": 4.5446, \"eval_samples_per_second\": 4.401, \"eval_steps_per_second\": 0.66}}", "startedAt": "2026-11-02T22:34:53Z", "finishedAt": "2026-11-02T22:42:01Z", "containerID": "cri-o://448accbda517e7632811718993cfab66f35c2af5c5e1953b1e2c3d595c4f5128" } }, "lastState": {}, "ready": false, "restartCount": 0, "image": "quay.io/opendatahub/odh-th-torch-cpu-py312:odh-stable", "imageID": "quay.io/opendatahub/odh-th-torch-cpu-py312@sha256:26f3e19a98daad50ac5c633a9ab0b6a99d8ee11ae6f988d147a7589d74bc17ce", "containerID": "cri-o://448accbda517e7632811718993cfab66f35c2af5c5e1953b1e2c3d595c4f5128", "started": false, "allocatedResources": { "cpu": "1", "memory": "8Gi" }, "resources": { "limits": { "cpu": "1", "memory": "8Gi" }, "requests": { "cpu": "1", "memory": "8Gi" } }, "volumeMounts": [ { "name": "workspace", "mountPath": "/workspace" }, { "name": "kube-api-access-lgcl8", "mountPath": "/var/run/secrets/kubernetes.io/serviceaccount", "readOnly": true, "recursiveReadOnly": "Disabled" } ], "user": { "linux": { "uid": 1000910000, "gid": 0, "supplementalGroups": [ 0, 1000910000 ] } } } ], "initStatuses": null, "phase": "Succeeded" }