| [paths] | |
| train = "./realec/train.spacy" | |
| dev = "./realec/dev.spacy" | |
| vectors = null | |
| init_tok2vec = null | |
| [system] | |
| gpu_allocator = "pytorch" | |
| seed = 0 | |
| [nlp] | |
| lang = "en" | |
| pipeline = ["transformer","spancat"] | |
| batch_size = 16 | |
| disabled = [] | |
| before_creation = null | |
| after_creation = null | |
| after_pipeline_creation = null | |
| tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"} | |
| [components] | |
| [components.spancat] | |
| factory = "spancat" | |
| max_positive = null | |
| scorer = {"@scorers":"spacy.spancat_scorer.v1"} | |
| spans_key = "errors" | |
| threshold = 0.5 | |
| [components.spancat.model] | |
| @architectures = "spacy.SpanCategorizer.v1" | |
| [components.spancat.model.reducer] | |
| @layers = "spacy.mean_max_reducer.v1" | |
| hidden_size = 128 | |
| [components.spancat.model.scorer] | |
| @layers = "spacy.LinearLogistic.v1" | |
| nO = null | |
| nI = null | |
| [components.spancat.model.tok2vec] | |
| @architectures = "spacy-transformers.TransformerListener.v1" | |
| grad_factor = 1.0 | |
| pooling = {"@layers":"reduce_mean.v1"} | |
| upstream = "*" | |
| [components.spancat.suggester] | |
| @misc = "spacy.ngram_suggester.v1" | |
| sizes = [1,2,3] | |
| [components.transformer] | |
| factory = "transformer" | |
| max_batch_items = 4096 | |
| set_extra_annotations = {"@annotation_setters":"spacy-transformers.null_annotation_setter.v1"} | |
| [components.transformer.model] | |
| @architectures = "spacy-transformers.TransformerModel.v3" | |
| name = "bert-base-cased" | |
| mixed_precision = false | |
| [components.transformer.model.get_spans] | |
| @span_getters = "spacy-transformers.strided_spans.v1" | |
| window = 128 | |
| stride = 96 | |
| [components.transformer.model.grad_scaler_config] | |
| [components.transformer.model.tokenizer_config] | |
| use_fast = true | |
| [components.transformer.model.transformer_config] | |
| [corpora] | |
| [corpora.dev] | |
| @readers = "spacy.Corpus.v1" | |
| path = "./realec/dev.spacy" | |
| max_length = 0 | |
| gold_preproc = false | |
| limit = 0 | |
| augmenter = null | |
| [corpora.train] | |
| @readers = "spacy.Corpus.v1" | |
| path = "./realec/train.spacy" | |
| max_length = 0 | |
| gold_preproc = false | |
| limit = 0 | |
| augmenter = null | |
| [training] | |
| accumulate_gradient = 3 | |
| dev_corpus = "corpora.dev" | |
| train_corpus = "corpora.train" | |
| seed = 0 | |
| gpu_allocator = "pytorch" | |
| dropout = 0.1 | |
| patience = 1600 | |
| max_epochs = 0 | |
| max_steps = 20000 | |
| eval_frequency = 200 | |
| frozen_components = [] | |
| annotating_components = [] | |
| before_to_disk = null | |
| [training.batcher] | |
| @batchers = "spacy.batch_by_padded.v1" | |
| discard_oversize = true | |
| size = 2000 | |
| buffer = 256 | |
| get_length = null | |
| [training.logger] | |
| @loggers = "spacy.WandbLogger.v3" | |
| project_name = "my-awesome-project" | |
| remove_config_values = ["paths.train","paths.dev","corpora.train.path","corpora.dev.path"] | |
| log_dataset_dir = null | |
| entity = null | |
| run_name = "grammar-checker" | |
| model_log_interval = null | |
| [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] | |
| spans_sc_f = 0.5 | |
| spans_sc_p = 0.0 | |
| spans_sc_r = 0.0 | |
| spans_Agreement_errors_f = 0.06 | |
| spans_Articles_f = 0.03 | |
| spans_Capitalisation_f = 0.05 | |
| spans_Formational_affixes_f = 0.1 | |
| spans_Noun_number_f = 0.04 | |
| spans_Numerals_f = 0.06 | |
| spans_Prepositions_f = 0.05 | |
| spans_Punctuation_f = 0.03 | |
| spans_Spelling_f = 0.02 | |
| spans_Tense_choice_f = 0.03 | |
| spans_lex_item_choice_f = 0.03 | |
| [pretraining] | |
| [initialize] | |
| vectors = null | |
| init_tok2vec = null | |
| vocab_data = null | |
| lookups = null | |
| before_init = null | |
| after_init = null | |
| [initialize.components] | |
| [initialize.tokenizer] |