| [paths] |
| train = null |
| dev = null |
| vectors = null |
| init_tok2vec = null |
|
|
| [system] |
| gpu_allocator = null |
| seed = 0 |
|
|
| [nlp] |
| lang = "en" |
| pipeline = ["textcat_multilabel"] |
| batch_size = 1000 |
| disabled = [] |
| before_creation = null |
| after_creation = null |
| after_pipeline_creation = null |
| tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"} |
| vectors = {"@vectors":"spacy.Vectors.v1"} |
|
|
| [components] |
|
|
| [components.textcat_multilabel] |
| factory = "textcat_multilabel" |
| scorer = {"@scorers":"spacy.textcat_multilabel_scorer.v2"} |
| threshold = 0.5 |
|
|
| [components.textcat_multilabel.model] |
| @architectures = "spacy.TextCatBOW.v3" |
| exclusive_classes = false |
| length = 262144 |
| ngram_size = 1 |
| no_output_layer = false |
| nO = null |
|
|
| [corpora] |
| @readers = "prodigy.MergedCorpus.v1" |
| eval_split = 0.2 |
| sample_size = 1.0 |
| ner = null |
| textcat = null |
| parser = null |
| tagger = null |
| senter = null |
| spancat = null |
| experimental_coref = null |
|
|
| [corpora.textcat_multilabel] |
| @readers = "prodigy.TextCatCorpus.v1" |
| datasets = ["prodigy3trainComplete"] |
| eval_datasets = ["golden3"] |
| exclusive = false |
|
|
| [training] |
| dev_corpus = "corpora.dev" |
| train_corpus = "corpora.train" |
| seed = ${system.seed} |
| gpu_allocator = ${system.gpu_allocator} |
| dropout = 0.1 |
| accumulate_gradient = 1 |
| patience = 1600 |
| max_epochs = 0 |
| max_steps = 20000 |
| eval_frequency = 200 |
| frozen_components = [] |
| annotating_components = [] |
| before_to_disk = null |
| before_update = null |
|
|
| [training.batcher] |
| @batchers = "spacy.batch_by_words.v1" |
| discard_oversize = false |
| tolerance = 0.2 |
| get_length = null |
|
|
| [training.batcher.size] |
| @schedules = "compounding.v1" |
| start = 100 |
| stop = 1000 |
| compound = 1.001 |
| t = 0.0 |
|
|
| [training.logger] |
| @loggers = "spacy.ConsoleLogger.v1" |
| progress_bar = false |
|
|
| [training.optimizer] |
| @optimizers = "Adam.v1" |
| beta1 = 0.9 |
| beta2 = 0.999 |
| L2_is_weight_decay = true |
| L2 = 0.01 |
| grad_clip = 1.0 |
| use_averages = false |
| eps = 0.00000001 |
| learn_rate = 0.001 |
|
|
| [training.score_weights] |
| cats_score = 1.0 |
| cats_score_desc = null |
| cats_micro_p = null |
| cats_micro_r = null |
| cats_micro_f = null |
| cats_macro_p = null |
| cats_macro_r = null |
| cats_macro_f = null |
| cats_macro_auc = null |
| cats_f_per_type = null |
|
|
| [pretraining] |
|
|
| [initialize] |
| vectors = ${paths.vectors} |
| init_tok2vec = ${paths.init_tok2vec} |
| vocab_data = null |
| lookups = null |
| before_init = null |
| after_init = null |
|
|
| [initialize.components] |
|
|
| [initialize.tokenizer] |
