.github/tests/test_data/report-on-schedule-2022-02-02.json

Summary

Maintainability
Test Coverage
{
  "RasaHQ/financial-demo": {
    "BERT + DIET(bow) + ResponseSelector(bow)": [{
      "accelerator_type": "GPU",
      "config_repository": "training-data",
      "config_repository_branch": "main",
      "dataset_commit": "52a3ad3eb5292d56542687e23b06703431f15ead",
      "dataset_repository_branch": "fix-model-regression-tests",
      "entity_prediction": {
        "macro avg": {
          "f1-score": 0.7333333333333333,
          "precision": 0.8,
          "recall": 0.7,
          "support": 14
        },
        "micro avg": {
          "f1-score": 0.8333333333333333,
          "precision": 1.0,
          "recall": 0.7142857142857143,
          "support": 14
        },
        "weighted avg": {
          "f1-score": 0.738095238095238,
          "precision": 0.7857142857142857,
          "recall": 0.7142857142857143,
          "support": 14
        }
      },
      "external_dataset_repository": true,
      "intent_classification": {
        "accuracy": 1.0,
        "macro avg": {
          "f1-score": 1.0,
          "precision": 1.0,
          "recall": 1.0,
          "support": 28
        },
        "weighted avg": {
          "f1-score": 1.0,
          "precision": 1.0,
          "recall": 1.0,
          "support": 28
        }
      },
      "test_run_time": "35s",
      "total_run_time": "2m2s",
      "train_run_time": "1m28s",
      "type": "nlu"
    }],
    "BERT + DIET(seq) + ResponseSelector(t2t)": [{
      "accelerator_type": "GPU",
      "config_repository": "training-data",
      "config_repository_branch": "main",
      "dataset_commit": "52a3ad3eb5292d56542687e23b06703431f15ead",
      "dataset_repository_branch": "fix-model-regression-tests",
      "entity_prediction": {
        "macro avg": {
          "f1-score": 0.7333333333333333,
          "precision": 0.8,
          "recall": 0.7,
          "support": 14
        },
        "micro avg": {
          "f1-score": 0.8333333333333333,
          "precision": 1.0,
          "recall": 0.7142857142857143,
          "support": 14
        },
        "weighted avg": {
          "f1-score": 0.738095238095238,
          "precision": 0.7857142857142857,
          "recall": 0.7142857142857143,
          "support": 14
        }
      },
      "external_dataset_repository": true,
      "intent_classification": {
        "accuracy": 1.0,
        "macro avg": {
          "f1-score": 1.0,
          "precision": 1.0,
          "recall": 1.0,
          "support": 28
        },
        "weighted avg": {
          "f1-score": 1.0,
          "precision": 1.0,
          "recall": 1.0,
          "support": 28
        }
      },
      "test_run_time": "55s",
      "total_run_time": "2m8s",
      "train_run_time": "1m14s",
      "type": "nlu"
    }],
    "Rules + Memo + TED": [{
      "accelerator_type": "GPU",
      "config_repository": "training-data",
      "config_repository_branch": "main",
      "dataset_commit": "52a3ad3eb5292d56542687e23b06703431f15ead",
      "dataset_repository_branch": "fix-model-regression-tests",
      "external_dataset_repository": true,
      "story_prediction": {
        "accuracy": 1.0,
        "conversation_accuracy": {
          "accuracy": 1.0,
          "correct": 48,
          "total": 48,
          "with_warnings": 0
        },
        "macro avg": {
          "f1-score": 1.0,
          "precision": 1.0,
          "recall": 1.0,
          "support": 317
        },
        "weighted avg": {
          "f1-score": 1.0,
          "precision": 1.0,
          "recall": 1.0,
          "support": 317
        }
      },
      "test_run_time": "51s",
      "total_run_time": "8m15s",
      "train_run_time": "7m24s",
      "type": "core"
    }]
  },
  "RasaHQ/retail-demo": {
    "BERT + DIET(bow) + ResponseSelector(bow)": [{
      "accelerator_type": "GPU",
      "config_repository": "training-data",
      "config_repository_branch": "main",
      "dataset_commit": "8226b51b4312aa4d3723098cf6d4028feea040b4",
      "dataset_repository_branch": "fix-model-regression-tests",
      "entity_prediction": {
        "macro avg": {
          "f1-score": 0.25,
          "precision": 0.25,
          "recall": 0.25,
          "support": 6
        },
        "micro avg": {
          "f1-score": 0.2857142857142857,
          "precision": 1.0,
          "recall": 0.16666666666666666,
          "support": 6
        },
        "weighted avg": {
          "f1-score": 0.16666666666666666,
          "precision": 0.16666666666666666,
          "recall": 0.16666666666666666,
          "support": 6
        }
      },
      "external_dataset_repository": true,
      "intent_classification": {
        "macro avg": {
          "f1-score": 0.8,
          "precision": 0.8,
          "recall": 0.85,
          "support": 16
        },
        "micro avg": {
          "f1-score": 0.8387096774193549,
          "precision": 0.8666666666666667,
          "recall": 0.8125,
          "support": 16
        },
        "weighted avg": {
          "f1-score": 0.8125,
          "precision": 0.875,
          "recall": 0.8125,
          "support": 16
        }
      },
      "test_run_time": "29s",
      "total_run_time": "1m16s",
      "train_run_time": "47s",
      "type": "nlu"
    }],
    "BERT + DIET(seq) + ResponseSelector(t2t)": [{
      "accelerator_type": "GPU",
      "config_repository": "training-data",
      "config_repository_branch": "main",
      "dataset_commit": "8226b51b4312aa4d3723098cf6d4028feea040b4",
      "dataset_repository_branch": "fix-model-regression-tests",
      "entity_prediction": {
        "macro avg": {
          "f1-score": 0.25,
          "precision": 0.25,
          "recall": 0.25,
          "support": 6
        },
        "micro avg": {
          "f1-score": 0.2857142857142857,
          "precision": 1.0,
          "recall": 0.16666666666666666,
          "support": 6
        },
        "weighted avg": {
          "f1-score": 0.16666666666666666,
          "precision": 0.16666666666666666,
          "recall": 0.16666666666666666,
          "support": 6
        }
      },
      "external_dataset_repository": true,
      "intent_classification": {
        "accuracy": 0.875,
        "macro avg": {
          "f1-score": 0.8300000000000001,
          "precision": 0.8166666666666667,
          "recall": 0.85,
          "support": 16
        },
        "weighted avg": {
          "f1-score": 0.85,
          "precision": 0.8333333333333333,
          "recall": 0.875,
          "support": 16
        }
      },
      "test_run_time": "56s",
      "total_run_time": "2m2s",
      "train_run_time": "1m6s",
      "type": "nlu"
    }],
    "Rules + Memo": [{
      "accelerator_type": "GPU",
      "config_repository": "training-data",
      "config_repository_branch": "main",
      "dataset_commit": "8226b51b4312aa4d3723098cf6d4028feea040b4",
      "dataset_repository_branch": "fix-model-regression-tests",
      "external_dataset_repository": true,
      "story_prediction": {
        "conversation_accuracy": {
          "accuracy": 0.8888888888888888,
          "correct": 8,
          "total": 9,
          "with_warnings": 0
        },
        "macro avg": {
          "f1-score": 0.9663698541747322,
          "precision": 1.0,
          "recall": 0.946007696007696,
          "support": 67
        },
        "micro avg": {
          "f1-score": 0.9692307692307692,
          "precision": 1.0,
          "recall": 0.9402985074626866,
          "support": 67
        },
        "weighted avg": {
          "f1-score": 0.9656317714563074,
          "precision": 1.0,
          "recall": 0.9402985074626866,
          "support": 67
        }
      },
      "test_run_time": "10s",
      "total_run_time": "19s",
      "train_run_time": "10s",
      "type": "core"
    }],
    "Rules + Memo + TED": [{
      "accelerator_type": "GPU",
      "config_repository": "training-data",
      "config_repository_branch": "main",
      "dataset_commit": "8226b51b4312aa4d3723098cf6d4028feea040b4",
      "dataset_repository_branch": "fix-model-regression-tests",
      "external_dataset_repository": true,
      "story_prediction": {
        "accuracy": 1.0,
        "conversation_accuracy": {
          "accuracy": 1.0,
          "correct": 9,
          "total": 9,
          "with_warnings": 0
        },
        "macro avg": {
          "f1-score": 1.0,
          "precision": 1.0,
          "recall": 1.0,
          "support": 67
        },
        "weighted avg": {
          "f1-score": 1.0,
          "precision": 1.0,
          "recall": 1.0,
          "support": 67
        }
      },
      "test_run_time": "31s",
      "total_run_time": "4m57s",
      "train_run_time": "4m27s",
      "type": "core"
    }]
  }
}