Legacy Product

Fusion 5.10
    Fusion 5.10

    Trains QnA model on a supervised basis with with pre-trained or trained embeddings and deploys the trained model to the ML Model Service

    aMaxLen - integer

    Average length of question by number of tokens

    answerColName - stringrequired

    Name of the field containing answers

    >= 1 characters

    baseLR - number

    Base learning rate used in cyclical training

    cudnn - boolean

    Use GPU for training if available (recommended NVIDIA GPU with 8Gb or more memory)

    Default: false

    deployModelName - stringrequired

    Name of the model to be used for deployment (must be a valid DNS subdomain with no underscores)

    <= 30 characters

    Match pattern: [a-zA-Z][\-a-zA-Z0-9]*[a-zA-Z0-9]?

    embSPDP - number

    Fraction of input to drop with Dropout layer (from 0-1)

    Default: 0.15

    epochs - integer

    extraTrainingArgs - string

    Add any additional arguments for the Python training scripts in this field

    id - stringrequired

    The ID for this job. Used in the API to reference this job. Allowed characters: a-z, A-Z, dash (-) and underscore (_)

    <= 63 characters

    Match pattern: [a-zA-Z][_\-a-zA-Z0-9]*[a-zA-Z0-9]?

    infBatch - integer

    Batch size during validation. If left blank, this will be set automatically based on the input data

    kList - string

    The k retrieval position that will be used to compute for each metric

    Default: [1,3,5]

    lowerCases - boolean

    Whether to lower case all words in training, i.e. whether to treat upper case and lower case words equally.

    Default: false

    maxLR - number

    Maximum learning rate used in cyclical training

    maxTokensNum - integer

    Drop document if the total words is greater than this value

    >= 1

    exclusiveMinimum: false

    Default: 5000

    maxVocabSize - integer

    Maximum number of words in vocabulary, words will be trimmed if frequency is too low

    >= 1

    exclusiveMinimum: false

    Default: 100000

    minTokensNum - integer

    Drop document if the total words is lower than this value

    >= 1

    exclusiveMinimum: false

    Default: 1

    modelReplicas - integer

    How many replicas of the model should be deployed by Seldon Core

    Default: 1

    monitorMetric - string

    The metric that is chosen among all possible metrics at k to be used to decide when to stop training

    Default: mrr@3

    monitorMetricsList - string

    List of evaluation metrics on validation data that will be printed in the log at the end of each epoch

    Default: ["map", "mrr", "precision", "recall", "roc_auc"]

    monitorPatience - integer

    Stop training if no improvement in metrics by this number of epochs

    numClusters - integer

    Number of clusters to be used for fast dense vector retrieval. Note no clustering will be applied if this is set to 0. If left blank, cluster count will be inferred by the job depending on the data

    numNeg - integer

    Number of non-matching answers randomly sampled for each question to be used as negative examples when constructing

    Default: 15

    numPos - integer

    Number of answers to be used for each question when constructing validation data

    Default: 5

    qMaxLen - integer

    Average length of question by number of tokens

    questionColName - stringrequired

    Name of the field containing questions

    >= 1 characters

    rnnNamesList - string

    List of layers of RNNs can be used, with possible values of lstm, gru. E.g. ["lstm", "lstm"]. This value will be automatically decided based on data if left blank

    rnnUnitsList - string

    List of RNN layer units numbers, corresponding to RNN function list. E.g. 150, 150. This value will be automatically decided based on data if left blank

    samplingProportion - number

    The proportion of data to be sampled from the full dataset. Use a value between 0 and 1 for a proportion (e.g. 0.5 for 50%), or for a specific number of examples, use an integer larger than 1. Leave blank for no sampling

    sparkConfig - array[object]

    Provide additional key/value pairs to be injected into the training JSON map at runtime. Values will be inserted as-is, so use " to surround string values

    object attributes:{key required : {
     display name: Parameter Name
     type: string
    value : {
     display name: Parameter Value
     type: string

    topKClusters - integer

    How many closest clusters the model can find for each query. At retrieval time, all answers in top k nearest clusters will be returned and reranked

    Default: 10

    trainBatch - integer

    Batch size during training. If left blank, this will be set automatically based on the input data

    trainingCollection - stringrequired

    Solr Collection containing question and answer pairs

    >= 1 characters

    type - stringrequired

    Default: argo-qna-supervised

    Allowed values: argo-qna-supervised

    useAutoML - boolean

    Automatically tune hyperparameters (will take longer to train)

    Default: false

    useCustomEmbeddings - boolean

    Choose this option when there are many uncommon words or jargons in data. NOTE: please look at log for warning about percentage of covered vocabulary words, if this proportion is less than 80%, please set this parameter to true and do not use the pre-trained embeddings shipped with our package

    Default: false

    valSize - number

    Proportion of the original data to be used as validation sample

    >= 0.001

    exclusiveMinimum: false

    Default: 0.1

    w2vEpochs - integer

    Number of epochs to train custom word2vec embeddings

    Default: 15

    w2vTextColumns - string

    Which fields in the Word2Vec training collection to use in Word2Vec vocabulary embedding training. If multiple fields, please separate them by comma, e.g. description_t,title_t.

    w2vTextsCollection - string

    Name of the collection which contains the documents that will be used to train Word2Vec if pre-trained word2vec embeddings won't be used.

    w2vVectorSize - integer

    Word-vector dimensionality to represent text (suggested dimension ranges: 100~150

    Default: 150

    w2vWindowSize - integer

    The window size (context words from [-window, window]) for Word2Vec

    Default: 8

    weightDecay - number

    L2 penalty used in Adam optimization. Bigger values will provide stronger regularization

    Default: 0.0001