Skip to content

exp show: checkpoint data is no longer returned when running checkpoints based experiment #7329

@mattseddon

Description

@mattseddon

Bug Report

Description

After upgrading to 2.9.4.dev94+g95731e9a I noticed that when running checkpoint experiments only a single experiment is returned in the exp show data. This happens even if multiple experiments are present in the workspace.

The easiest way to demonstrate is with screen recording from the extension and example data.

2.9.3:

Screen.Recording.2022-02-01.at.11.54.21.am.mov
example data
{                                                                     
  "workspace": {
    "baseline": {
      "data": {
        "timestamp": null,
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "queued": false,
        "running": false,
        "executor": null,
        "metrics": {
          "logs.json": {
            "data": {
              "step": 1,
              "loss": 2.271583318710327,
              "acc": 0.1145
            }
          }
        }
      }
    }
  },
  "3a471411a9f37679e4d1ea8be604bbf1396d15ed": {
    "baseline": {
      "data": {
        "timestamp": "2022-02-01T09:57:33",
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "queued": false,
        "running": false,
        "executor": null,
        "metrics": {
          "logs.json": {
            "data": {
              "step": 8,
              "loss": 2.1331353187561035,
              "acc": 0.5172
            }
          }
        },
        "name": "remove-size-update"
      }
    },
    "6e2e530f03d568dd4195f0df6f6c0d8788c96518": {
      "data": {
        "checkpoint_tip": "6e2e530f03d568dd4195f0df6f6c0d8788c96518",
        "timestamp": "2022-02-01T13:12:17",
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "queued": false,
        "running": true,
        "executor": "workspace",
        "metrics": {
          "logs.json": {
            "data": {
              "step": 1,
              "loss": 2.271583318710327,
              "acc": 0.1145
            }
          }
        },
        "name": "exp-1c3f1",
        "checkpoint_parent": "f0020fd8a96dabe8f650a6d5b17938d3eadbc712"
      }
    },
    "f0020fd8a96dabe8f650a6d5b17938d3eadbc712": {
      "data": {
        "checkpoint_tip": "6e2e530f03d568dd4195f0df6f6c0d8788c96518",
        "timestamp": "2022-02-01T13:12:01",
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "queued": false,
        "running": false,
        "executor": null,
        "metrics": {
          "logs.json": {
            "data": {
              "step": 0,
              "loss": 2.290804147720337,
              "acc": 0.1136
            }
          }
        },
        "checkpoint_parent": "3a471411a9f37679e4d1ea8be604bbf1396d15ed"
      }
    },
    "098c17acee68a65760f77e9cfa311955db3a7129": {
      "data": {
        "checkpoint_tip": "098c17acee68a65760f77e9cfa311955db3a7129",
        "timestamp": "2022-02-01T13:03:03",
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "queued": false,
        "running": false,
        "executor": null,
        "metrics": {
          "logs.json": {
            "data": {
              "step": 8,
              "loss": 2.2126705646514893,
              "acc": 0.4163
            }
          }
        },
        "name": "exp-b551e",
        "checkpoint_parent": "c7159c89f690e2798fbe9693ca61992826a997a7"
      }
    },
    "c7159c89f690e2798fbe9693ca61992826a997a7": {
      "data": {
        "checkpoint_tip": "098c17acee68a65760f77e9cfa311955db3a7129",
        "timestamp": "2022-02-01T13:02:59",
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "queued": false,
        "running": false,
        "executor": null,
        "metrics": {
          "logs.json": {
            "data": {
              "step": 8,
              "loss": 2.2126705646514893,
              "acc": 0.4163
            }
          }
        },
        "checkpoint_parent": "7c58a9cb8ed740039d066d64bf9c1ed584482be6"
      }
    },
    "7c58a9cb8ed740039d066d64bf9c1ed584482be6": {
      "data": {
        "checkpoint_tip": "098c17acee68a65760f77e9cfa311955db3a7129",
        "timestamp": "2022-02-01T13:02:38",
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "queued": false,
        "running": false,
        "executor": null,
        "metrics": {
          "logs.json": {
            "data": {
              "step": 7,
              "loss": 2.22721004486084,
              "acc": 0.2427
            }
          }
        },
        "checkpoint_parent": "555e677435df031eb025747e0f3fec956ab15717"
      }
    },
    "555e677435df031eb025747e0f3fec956ab15717": {
      "data": {
        "checkpoint_tip": "098c17acee68a65760f77e9cfa311955db3a7129",
        "timestamp": "2022-02-01T13:02:22",
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "queued": false,
        "running": false,
        "executor": null,
        "metrics": {
          "logs.json": {
            "data": {
              "step": 6,
              "loss": 2.2387068271636963,
              "acc": 0.3312
            }
          }
        },
        "checkpoint_parent": "18bb1ed0c193f0adc8031231eccb3663de7fcca5"
      }
    },
    "18bb1ed0c193f0adc8031231eccb3663de7fcca5": {
      "data": {
        "checkpoint_tip": "098c17acee68a65760f77e9cfa311955db3a7129",
        "timestamp": "2022-02-01T13:02:06",
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "queued": false,
        "running": false,
        "executor": null,
        "metrics": {
          "logs.json": {
            "data": {
              "step": 5,
              "loss": 2.2524354457855225,
              "acc": 0.228
            }
          }
        },
        "checkpoint_parent": "c6fb413d5493c85f5cd766d24755077fd1e93a00"
      }
    },
    "c6fb413d5493c85f5cd766d24755077fd1e93a00": {
      "data": {
        "checkpoint_tip": "098c17acee68a65760f77e9cfa311955db3a7129",
        "timestamp": "2022-02-01T13:01:52",
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "queued": false,
        "running": false,
        "executor": null,
        "metrics": {
          "logs.json": {
            "data": {
              "step": 4,
              "loss": 2.2646212577819824,
              "acc": 0.3335
            }
          }
        },
        "checkpoint_parent": "52ed7aeb1dd8ec0ec29df09db55a6d245b659936"
      }
    },
    "52ed7aeb1dd8ec0ec29df09db55a6d245b659936": {
      "data": {
        "checkpoint_tip": "098c17acee68a65760f77e9cfa311955db3a7129",
        "timestamp": "2022-02-01T13:01:40",
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "queued": false,
        "running": false,
        "executor": null,
        "metrics": {
          "logs.json": {
            "data": {
              "step": 3,
              "loss": 2.2729482650756836,
              "acc": 0.1418
            }
          }
        },
        "checkpoint_parent": "ccd2b8d81f211d5633e8411a3753af9177c06750"
      }
    },
    "ccd2b8d81f211d5633e8411a3753af9177c06750": {
      "data": {
        "checkpoint_tip": "098c17acee68a65760f77e9cfa311955db3a7129",
        "timestamp": "2022-02-01T13:01:29",
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "queued": false,
        "running": false,
        "executor": null,
        "metrics": {
          "logs.json": {
            "data": {
              "step": 2,
              "loss": 2.2822108268737793,
              "acc": 0.1213
            }
          }
        },
        "checkpoint_parent": "f0d0e8f11759450149310e6acabba0d07e303a36"
      }
    },
    "f0d0e8f11759450149310e6acabba0d07e303a36": {
      "data": {
        "checkpoint_tip": "098c17acee68a65760f77e9cfa311955db3a7129",
        "timestamp": "2022-02-01T13:01:17",
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "queued": false,
        "running": false,
        "executor": null,
        "metrics": {
          "logs.json": {
            "data": {
              "step": 1,
              "loss": 2.290830373764038,
              "acc": 0.1135
            }
          }
        },
        "checkpoint_parent": "2ce968bae403a1bbd5185bddd409a7b61f29baad"
      }
    },
    "2ce968bae403a1bbd5185bddd409a7b61f29baad": {
      "data": {
        "checkpoint_tip": "098c17acee68a65760f77e9cfa311955db3a7129",
        "timestamp": "2022-02-01T13:01:00",
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "queued": false,
        "running": false,
        "executor": null,
        "metrics": {
          "logs.json": {
            "data": {
              "step": 0,
              "loss": 2.298349142074585,
              "acc": 0.1135
            }
          }
        },
        "checkpoint_parent": "3a471411a9f37679e4d1ea8be604bbf1396d15ed"
      }
    },
    "2f71e8fab78fd7db7fcf895c300039a5207350b5": {
      "data": {
        "checkpoint_tip": "2f71e8fab78fd7db7fcf895c300039a5207350b5",
        "timestamp": "2022-02-01T12:54:48",
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "queued": false,
        "running": false,
        "executor": null,
        "metrics": {
          "logs.json": {
            "data": {
              "step": 8,
              "loss": 1.9723258018493652,
              "acc": 0.5193
            }
          }
        },
        "name": "exp-2be1c",
        "checkpoint_parent": "6e174c4ffd28990a0f801a3dbc1651cbac5e9277"
      }
    },
    "6e174c4ffd28990a0f801a3dbc1651cbac5e9277": {
      "data": {
        "checkpoint_tip": "2f71e8fab78fd7db7fcf895c300039a5207350b5",
        "timestamp": "2022-02-01T12:54:46",
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "queued": false,
        "running": false,
        "executor": null,
        "metrics": {
          "logs.json": {
            "data": {
              "step": 8,
              "loss": 1.9723258018493652,
              "acc": 0.5193
            }
          }
        },
        "checkpoint_parent": "e08e69bf38bd510f0885a1f8d536b70ea105c174"
      }
    },
    "e08e69bf38bd510f0885a1f8d536b70ea105c174": {
      "data": {
        "checkpoint_tip": "2f71e8fab78fd7db7fcf895c300039a5207350b5",
        "timestamp": "2022-02-01T12:54:32",
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "queued": false,
        "running": false,
        "executor": null,
        "metrics": {
          "logs.json": {
            "data": {
              "step": 7,
              "loss": 2.0126395225524902,
              "acc": 0.3483
            }
          }
        },
        "checkpoint_parent": "68ee2543ccaf579d6cb9fc1ab62fa03011232bdd"
      }
    },
    "68ee2543ccaf579d6cb9fc1ab62fa03011232bdd": {
      "data": {
        "checkpoint_tip": "2f71e8fab78fd7db7fcf895c300039a5207350b5",
        "timestamp": "2022-02-01T12:54:17",
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "queued": false,
        "running": false,
        "executor": null,
        "metrics": {
          "logs.json": {
            "data": {
              "step": 6,
              "loss": 2.0624423027038574,
              "acc": 0.4534
            }
          }
        },
        "checkpoint_parent": "43eab46bbeac11468c49921797d9dd74b359e4f4"
      }
    },
    "43eab46bbeac11468c49921797d9dd74b359e4f4": {
      "data": {
        "checkpoint_tip": "2f71e8fab78fd7db7fcf895c300039a5207350b5",
        "timestamp": "2022-02-01T12:54:01",
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "queued": false,
        "running": false,
        "executor": null,
        "metrics": {
          "logs.json": {
            "data": {
              "step": 5,
              "loss": 2.104891061782837,
              "acc": 0.3504
            }
          }
        },
        "checkpoint_parent": "94047a0d376afda7cdba64f509617997a0dda60c"
      }
    },
    "94047a0d376afda7cdba64f509617997a0dda60c": {
      "data": {
        "checkpoint_tip": "2f71e8fab78fd7db7fcf895c300039a5207350b5",
        "timestamp": "2022-02-01T12:53:48",
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "queued": false,
        "running": false,
        "executor": null,
        "metrics": {
          "logs.json": {
            "data": {
              "step": 4,
              "loss": 2.1485178470611572,
              "acc": 0.4302
            }
          }
        },
        "checkpoint_parent": "25affaa3d8e9fd053c018f1ca5f275fc0eec87a2"
      }
    },
    "25affaa3d8e9fd053c018f1ca5f275fc0eec87a2": {
      "data": {
        "checkpoint_tip": "2f71e8fab78fd7db7fcf895c300039a5207350b5",
        "timestamp": "2022-02-01T12:53:36",
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "queued": false,
        "running": false,
        "executor": null,
        "metrics": {
          "logs.json": {
            "data": {
              "step": 3,
              "loss": 2.194448947906494,
              "acc": 0.2544
            }
          }
        },
        "checkpoint_parent": "f1457704d8f19182328e6704f6b76be0618f427f"
      }
    },
    "f1457704d8f19182328e6704f6b76be0618f427f": {
      "data": {
        "checkpoint_tip": "2f71e8fab78fd7db7fcf895c300039a5207350b5",
        "timestamp": "2022-02-01T12:53:23",
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "queued": false,
        "running": false,
        "executor": null,
        "metrics": {
          "logs.json": {
            "data": {
              "step": 2,
              "loss": 2.2334680557250977,
              "acc": 0.1865
            }
          }
        },
        "checkpoint_parent": "05fa4e31c433efcf5faeda80a561f2cb8b778e2f"
      }
    },
    "05fa4e31c433efcf5faeda80a561f2cb8b778e2f": {
      "data": {
        "checkpoint_tip": "2f71e8fab78fd7db7fcf895c300039a5207350b5",
        "timestamp": "2022-02-01T12:53:10",
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "queued": false,
        "running": false,
        "executor": null,
        "metrics": {
          "logs.json": {
            "data": {
              "step": 1,
              "loss": 2.2640738487243652,
              "acc": 0.098
            }
          }
        },
        "checkpoint_parent": "bbe01af93da3c0502ac1758a0e8b467491b86a13"
      }
    },
    "bbe01af93da3c0502ac1758a0e8b467491b86a13": {
      "data": {
        "checkpoint_tip": "2f71e8fab78fd7db7fcf895c300039a5207350b5",
        "timestamp": "2022-02-01T12:52:57",
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "queued": false,
        "running": false,
        "executor": null,
        "metrics": {
          "logs.json": {
            "data": {
              "step": 0,
              "loss": 2.292071580886841,
              "acc": 0.098
            }
          }
        },
        "checkpoint_parent": "3a471411a9f37679e4d1ea8be604bbf1396d15ed"
      }
    },
    "e197c8aaf027691d91b2da62cb6c75cf00ff3782": {
      "data": {
        "checkpoint_tip": "e197c8aaf027691d91b2da62cb6c75cf00ff3782",
        "timestamp": "2022-02-01T12:51:40",
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "queued": false,
        "running": false,
        "executor": null,
        "metrics": {
          "logs.json": {
            "data": {
              "step": 8,
              "loss": 1.9586313962936401,
              "acc": 0.4724
            }
          }
        },
        "name": "exp-8abfc",
        "checkpoint_parent": "ff6855a8e675145bd26a99015a9a0522d3caf825"
      }
    },
    "ff6855a8e675145bd26a99015a9a0522d3caf825": {
      "data": {
        "checkpoint_tip": "e197c8aaf027691d91b2da62cb6c75cf00ff3782",
        "timestamp": "2022-02-01T12:51:38",
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "queued": false,
        "running": false,
        "executor": null,
        "metrics": {
          "logs.json": {
            "data": {
              "step": 8,
              "loss": 1.9586313962936401,
              "acc": 0.4724
            }
          }
        },
        "checkpoint_parent": "a85c15391567e6a00c8a8cd46512463dcd10da26"
      }
    },
    "a85c15391567e6a00c8a8cd46512463dcd10da26": {
      "data": {
        "checkpoint_tip": "e197c8aaf027691d91b2da62cb6c75cf00ff3782",
        "timestamp": "2022-02-01T12:51:24",
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "queued": false,
        "running": false,
        "executor": null,
        "metrics": {
          "logs.json": {
            "data": {
              "step": 7,
              "loss": 2.006150245666504,
              "acc": 0.4787
            }
          }
        },
        "checkpoint_parent": "c3627b3bec61e280d31cf5d35448025a8f98b456"
      }
    },
    "c3627b3bec61e280d31cf5d35448025a8f98b456": {
      "data": {
        "checkpoint_tip": "e197c8aaf027691d91b2da62cb6c75cf00ff3782",
        "timestamp": "2022-02-01T12:51:11",
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "queued": false,
        "running": false,
        "executor": null,
        "metrics": {
          "logs.json": {
            "data": {
              "step": 6,
              "loss": 2.0480971336364746,
              "acc": 0.4301
            }
          }
        },
        "checkpoint_parent": "92adc43437129fbcde2cd75fa1c3dd9628b34518"
      }
    },
    "92adc43437129fbcde2cd75fa1c3dd9628b34518": {
      "data": {
        "checkpoint_tip": "e197c8aaf027691d91b2da62cb6c75cf00ff3782",
        "timestamp": "2022-02-01T12:50:59",
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "queued": false,
        "running": false,
        "executor": null,
        "metrics": {
          "logs.json": {
            "data": {
              "step": 5,
              "loss": 2.0923407077789307,
              "acc": 0.4648
            }
          }
        },
        "checkpoint_parent": "165feb136ba972630c5fc7ff9e65d19ad3e8dce4"
      }
    },
    "165feb136ba972630c5fc7ff9e65d19ad3e8dce4": {
      "data": {
        "checkpoint_tip": "e197c8aaf027691d91b2da62cb6c75cf00ff3782",
        "timestamp": "2022-02-01T12:50:47",
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "queued": false,
        "running": false,
        "executor": null,
        "metrics": {
          "logs.json": {
            "data": {
              "step": 4,
              "loss": 2.133977174758911,
              "acc": 0.3947
            }
          }
        },
        "checkpoint_parent": "c6f8c0df868570956548e5c3e3ead9eaf0a3e418"
      }
    },
    "c6f8c0df868570956548e5c3e3ead9eaf0a3e418": {
      "data": {
        "checkpoint_tip": "e197c8aaf027691d91b2da62cb6c75cf00ff3782",
        "timestamp": "2022-02-01T12:50:35",
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "queued": false,
        "running": false,
        "executor": null,
        "metrics": {
          "logs.json": {
            "data": {
              "step": 3,
              "loss": 2.174873113632202,
              "acc": 0.3859
            }
          }
        },
        "checkpoint_parent": "bca00f17bb3789fa5c7b2134bcd9cc3c4b41b833"
      }
    },
    "bca00f17bb3789fa5c7b2134bcd9cc3c4b41b833": {
      "data": {
        "checkpoint_tip": "e197c8aaf027691d91b2da62cb6c75cf00ff3782",
        "timestamp": "2022-02-01T12:50:21",
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "queued": false,
        "running": false,
        "executor": null,
        "metrics": {
          "logs.json": {
            "data": {
              "step": 2,
              "loss": 2.21352219581604,
              "acc": 0.3669
            }
          }
        },
        "checkpoint_parent": "01452bf1621f0e00f9dc9754160d2d24618b73a3"
      }
    },
    "01452bf1621f0e00f9dc9754160d2d24618b73a3": {
      "data": {
        "checkpoint_tip": "e197c8aaf027691d91b2da62cb6c75cf00ff3782",
        "timestamp": "2022-02-01T12:50:08",
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "queued": false,
        "running": false,
        "executor": null,
        "metrics": {
          "logs.json": {
            "data": {
              "step": 1,
              "loss": 2.250871181488037,
              "acc": 0.3687
            }
          }
        },
        "checkpoint_parent": "e4b28773e0d860b3e25eddaeb32afc9a454ea128"
      }
    },
    "e4b28773e0d860b3e25eddaeb32afc9a454ea128": {
      "data": {
        "checkpoint_tip": "e197c8aaf027691d91b2da62cb6c75cf00ff3782",
        "timestamp": "2022-02-01T12:49:55",
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "queued": false,
        "running": false,
        "executor": null,
        "metrics": {
          "logs.json": {
            "data": {
              "step": 0,
              "loss": 2.288084030151367,
              "acc": 0.1491
            }
          }
        },
        "checkpoint_parent": "3a471411a9f37679e4d1ea8be604bbf1396d15ed"
      }
    },
    "b3c62703906d674ce0b8cf04280d7ea6d547a2b7": {
      "data": {
        "timestamp": "2022-02-01T13:11:42",
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "queued": true,
        "running": false,
        "executor": null
      }
    }
  }
}

2.9.4.dev94+g95731e9a:

start:

Screen.Recording.2022-02-01.at.1.00.22.pm.mov

end:

Screen.Recording.2022-02-01.at.1.01.59.pm.mov
example data
{                                                                     
  "workspace": {
    "baseline": {
      "data": {
        "timestamp": null,
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "deps": {
          "data/MNIST": {
            "hash": "0aed307494600d178fbdc0d000d6db38.dir",
            "size": 66544866,
            "nfiles": 10
          },
          "train.py": {
            "hash": "b6291190036da6a4c61d408826d1c7d5",
            "size": 3895,
            "nfiles": null
          }
        },
        "outs": {
          "model.pt": {
            "hash": "96219500eba0370875719b57c7684fee",
            "size": 410191,
            "nfiles": null
          },
          "raw": {
            "hash": "8c257df187855c681f88bde92d721ccd.dir",
            "size": 66544770,
            "nfiles": 8
          }
        },
        "queued": false,
        "running": false,
        "executor": null,
        "metrics": {
          "logs.json": {
            "data": {
              "step": 7,
              "loss": 2.22721004486084,
              "acc": 0.2427
            }
          }
        }
      }
    }
  },
  "7c58a9cb8ed740039d066d64bf9c1ed584482be6": {
    "baseline": {
      "data": {
        "timestamp": "2022-02-01T13:02:38",
        "params": {
          "params.yaml": {
            "data": {
              "seed": 473987,
              "lr": 0.001,
              "weight_decay": 0
            }
          }
        },
        "deps": {
          "data/MNIST": {
            "hash": "0aed307494600d178fbdc0d000d6db38.dir",
            "size": 66544866,
            "nfiles": 10
          },
          "train.py": {
            "hash": "b6291190036da6a4c61d408826d1c7d5",
            "size": 3895,
            "nfiles": null
          }
        },
        "outs": {
          "model.pt": {
            "hash": "96219500eba0370875719b57c7684fee",
            "size": 410191,
            "nfiles": null
          },
          "raw": {
            "hash": "8c257df187855c681f88bde92d721ccd.dir",
            "size": 66544770,
            "nfiles": 8
          }
        },
        "queued": false,
        "running": true,
        "executor": "workspace",
        "metrics": {
          "logs.json": {
            "data": {
              "step": 7,
              "loss": 2.22721004486084,
              "acc": 0.2427
            }
          }
        },
        "name": "exp-b551e"
      }
    }
  }
}

Reproduce

  1. have a repo with checkpoints
  2. install dvc from main
  3. run experiment
  4. monitor exp show

Expected

All checkpoint data for experiments within the workspace is returned.

Environment information

Output of dvc doctor:

$ dvc doctor
DVC version: 2.9.4.dev94+g95731e9a 
---------------------------------
Platform: Python 3.9.5 on macOS-12.1-x86_64-i386-64bit
Supports:
        webhdfs (fsspec = 2021.11.1),
        http (aiohttp = 3.7.4.post0, aiohttp-retry = 2.4.5),
        https (aiohttp = 3.7.4.post0, aiohttp-retry = 2.4.5),
        s3 (s3fs = 2021.11.1, boto3 = 1.17.49)
Cache types: reflink, hardlink, symlink
Cache directory: apfs on /dev/disk1s5s1
Caches: local
Remotes: s3
Workspace directory: apfs on /dev/disk1s5s1
Repo: dvc (subdir), git

Additional Information (if any):

Please LMK if I have stumbled across some WIP and you were already addressing this.

Thanks,
Matt

Metadata

Metadata

Assignees

Labels

A: experimentsRelated to dvc expbugDid we break something?product: VSCodeIntegration with VSCode extension

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions