# My usefull comment

# 🤖 PIPELINE DEFINITION

nlp:

  "@core": pipeline

  lang: eds

  components:

    normalizer:

      '@factory': eds.normalizer

    sentencizer:

      '@factory': eds.sentences

    ner:

      '@factory': eds.ner_crf

      mode: "joint"

      target_span_getter: "gold_spans"

      # Set spans as both to ents and in separate `ent.label` groups

      span_setter: [ "ents", "*" ]

      infer_span_setter: true

      embedding:

        '@factory': eds.text_cnn

        kernel_sizes: [ 3 ]

        embedding:

          '@factory': eds.transformer

          model: hf-internal-testing/tiny-bert

          window: 128

          stride: 96

          new_tokens: [ [ "(?:\\n\\s*)*\\n", "⏎" ] ]

    qualifier:

      '@factory': eds.span_classifier

      attributes: { "_.negation": [ "sosy" ], "_.unit": [ "measure" ] }

      span_getter: ["ents", "gold_spans"]

      embedding:

        '@factory': eds.span_pooler

        embedding: # ${ nlp.components.ner.embedding }

          '@factory': eds.text_cnn

          kernel_sizes: [ 3 ]

          embedding:

            '@factory': eds.transformer

            model: hf-internal-testing/tiny-bert

            window: 128

            stride: 96

# 📈 SCORERS

scorer:

  speed: true

  qual:

    '@metrics': eds.span_attributes

    span_getter: ${nlp.components.qualifier.span_getter}

    qualifiers: ${nlp.components.qualifier.attributes}

  ner:

    '@metrics': eds.ner_exact

    span_getter: ${nlp.components.ner.target_span_getter}

# 🎛️ OPTIMIZER

optimizer:

  "@core": optimizer

  optim: AdamW

  module: ${ nlp }

  groups:

    "^transformer": false

    ".*":

      lr:

          "@schedules": linear

          start_value: 1e-3

          max_value: 2e-3

          warmup_rate: 0.5

  total_steps: ${ train.max_steps }

# 📚 DATA

train_data:

  - data:

      '@readers': standoff

      path: tests/training/dataset/

      converter:

        - '@factory': eds.standoff_dict2doc

          span_setter : 'gold_spans'

          span_attributes : ['sosy', 'unit', 'negation']

          bool_attributes : ['negation']  # default standoff to doc converter

        - '@factory': eds.sentences

          nlp: ${nlp}

        - '@factory': eds.split

          nlp: null

          max_length: 2000

          regex: '\n\n+'

    shuffle: dataset

    batch_size: 8 docs

    pipe_names: [ "ner" ]

  - data:

      '@readers': standoff

      path: tests/training/dataset/

      converter:

        - '@factory': eds.standoff_dict2doc

          span_setter : 'gold_spans'

          span_attributes : ['sosy', 'unit', 'negation']

          bool_attributes : ['negation']  # default standoff to doc converter

    shuffle: dataset

    batch_size: 16 spans

    pipe_names: [ "qualifier" ]

val_data:

  '@readers': standoff

  path: tests/training/dataset/

  converter:

    - '@factory': eds.standoff_dict2doc

      span_setter : 'gold_spans'

      span_attributes : ['sosy', 'unit', 'negation']

      bool_attributes : ['negation']  # default standoff to doc converter

# 🚀 TRAIN SCRIPT OPTIONS

train:

  nlp: ${ nlp }

  train_data: ${ train_data }

  val_data: ${ val_data }

  max_steps: 5

  validation_interval: 2

  max_grad_norm: 1.0

  scorer: ${ scorer }

  num_workers: 0

  optimizer: ${ optimizer }

  cpu: true