| [paths] |
| train = "data/bin/train-spanfinder.spacy" |
| dev = "data/bin/train-spanfinder.spacy" |
| vectors = "en_core_web_lg" |
| init_tok2vec = null |
|
|
| [system] |
| gpu_allocator = "pytorch" |
| seed = 0 |
|
|
| [nlp] |
| lang = "en" |
| pipeline = ["tok2vec","span_finder"] |
| disabled = [] |
| before_creation = null |
| after_creation = null |
| after_pipeline_creation = null |
| batch_size = 128 |
| tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"} |
| vectors = {"@vectors":"spacy.Vectors.v1"} |
|
|
| [components] |
|
|
| [components.span_finder] |
| factory = "span_finder" |
| max_length = 30 |
| min_length = null |
| scorer = {"@scorers":"spacy.span_finder_scorer.v1"} |
| spans_key = "sc" |
| threshold = 0.3 |
|
|
| [components.span_finder.model] |
| @architectures = "spacy.SpanFinder.v1" |
|
|
| [components.span_finder.model.scorer] |
| @layers = "spacy.LinearLogistic.v1" |
| nO = 2 |
| nI = null |
|
|
| [components.span_finder.model.tok2vec] |
| @architectures = "spacy.Tok2VecListener.v1" |
| width = 96 |
| upstream = "*" |
|
|
| [components.tok2vec] |
| factory = "tok2vec" |
|
|
| [components.tok2vec.model] |
| @architectures = "spacy.Tok2Vec.v2" |
|
|
| [components.tok2vec.model.embed] |
| @architectures = "spacy.MultiHashEmbed.v2" |
| width = 96 |
| attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY","IS_SPACE"] |
| rows = [5000,1000,2500,2500,50,50] |
| include_static_vectors = true |
|
|
| [components.tok2vec.model.encode] |
| @architectures = "spacy.MaxoutWindowEncoder.v2" |
| width = 96 |
| depth = 4 |
| window_size = 1 |
| maxout_pieces = 3 |
|
|
| [corpora] |
|
|
| [corpora.dev] |
| @readers = "spacy.Corpus.v1" |
| path = ${paths.dev} |
| max_length = 0 |
| gold_preproc = false |
| limit = 0 |
| augmenter = null |
|
|
| [corpora.train] |
| @readers = "spacy.Corpus.v1" |
| path = ${paths.train} |
| max_length = 0 |
| gold_preproc = false |
| limit = 0 |
| augmenter = null |
|
|
| [training] |
| train_corpus = "corpora.train" |
| dev_corpus = "corpora.dev" |
| seed = ${system:seed} |
| gpu_allocator = ${system:gpu_allocator} |
| dropout = 0.1 |
| accumulate_gradient = 1 |
| patience = 2000 |
| max_epochs = 0 |
| max_steps = 20000 |
| eval_frequency = 200 |
| before_to_disk = null |
| annotating_components = [] |
| before_update = null |
| frozen_components = [] |
|
|
| [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 = true |
|
|
| [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 = true |
| eps = 0.00000001 |
| learn_rate = 0.001 |
|
|
| [training.score_weights] |
| spans_sc_f = 1.0 |
| spans_sc_p = 0.0 |
| spans_sc_r = 0.0 |
|
|
| [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] |
