| [paths] | |
| train = "drive/MyDrive/ARCHES/TAL/donnees/pretraitement/modele_segmentation/extraction_wavestone/spacy/train.spacy" | |
| dev = "drive/MyDrive/ARCHES/TAL/donnees/pretraitement/modele_segmentation/extraction_wavestone/spacy/dev.spacy" | |
| vectors = null | |
| init_tok2vec = null | |
| [system] | |
| gpu_allocator = "pytorch" | |
| seed = 0 | |
| [nlp] | |
| lang = "fr" | |
| pipeline = ["preprocess_text","senter"] | |
| batch_size = 128 | |
| disabled = [] | |
| before_creation = null | |
| after_creation = null | |
| after_pipeline_creation = null | |
| tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"} | |
| [components] | |
| [components.preprocess_text] | |
| factory = "preprocess_text" | |
| [components.senter] | |
| factory = "senter" | |
| overwrite = false | |
| scorer = {"@scorers":"spacy.senter_scorer.v1"} | |
| [components.senter.model] | |
| @architectures = "spacy.Tagger.v2" | |
| nO = null | |
| normalize = false | |
| [components.senter.model.tok2vec] | |
| @architectures = "spacy.HashEmbedCNN.v2" | |
| pretrained_vectors = null | |
| width = 12 | |
| depth = 1 | |
| embed_size = 2000 | |
| window_size = 1 | |
| maxout_pieces = 2 | |
| subword_features = true | |
| [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] | |
| accumulate_gradient = 3 | |
| dev_corpus = "corpora.dev" | |
| train_corpus = "corpora.train" | |
| seed = ${system.seed} | |
| gpu_allocator = ${system.gpu_allocator} | |
| dropout = 0.1 | |
| 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_padded.v1" | |
| discard_oversize = true | |
| size = 2000 | |
| buffer = 256 | |
| get_length = null | |
| [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 | |
| [training.optimizer.learn_rate] | |
| @schedules = "warmup_linear.v1" | |
| warmup_steps = 250 | |
| total_steps = 20000 | |
| initial_rate = 0.00005 | |
| [training.score_weights] | |
| sents_f = 1.0 | |
| sents_p = 0.0 | |
| sents_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] |