| [paths] | |
| train = "corpus/UD_Russian-GSD/train.spacy" | |
| dev = "corpus/UD_Russian-GSD/dev.spacy" | |
| vectors = null | |
| init_tok2vec = null | |
| tokenizer_source = "training/UD_Russian-GSD/tokenizer/model-best" | |
| transformer_source = "training/UD_Russian-GSD/transformer/model-best" | |
| [system] | |
| gpu_allocator = "pytorch" | |
| seed = 0 | |
| [nlp] | |
| lang = "ru" | |
| pipeline = ["experimental_char_ner_tokenizer","transformer","senter","tagger","morphologizer","parser","experimental_edit_tree_lemmatizer"] | |
| batch_size = 64 | |
| disabled = ["senter"] | |
| before_creation = null | |
| after_creation = null | |
| after_pipeline_creation = null | |
| tokenizer = {"@tokenizers":"spacy-experimental.char_pretokenizer.v1"} | |
| [components] | |
| [components.experimental_char_ner_tokenizer] | |
| factory = "experimental_char_ner_tokenizer" | |
| scorer = {"@scorers":"spacy-experimental.tokenizer_scorer.v1"} | |
| [components.experimental_char_ner_tokenizer.model] | |
| @architectures = "spacy.TransitionBasedParser.v2" | |
| state_type = "ner" | |
| extra_state_tokens = false | |
| hidden_width = 64 | |
| maxout_pieces = 2 | |
| use_upper = true | |
| nO = null | |
| [components.experimental_char_ner_tokenizer.model.tok2vec] | |
| @architectures = "spacy.Tok2Vec.v2" | |
| [components.experimental_char_ner_tokenizer.model.tok2vec.embed] | |
| @architectures = "spacy.MultiHashEmbed.v2" | |
| width = 128 | |
| attrs = ["ORTH","LOWER","IS_DIGIT","IS_ALPHA","IS_SPACE","IS_PUNCT"] | |
| rows = [1000,500,50,50,50,50] | |
| include_static_vectors = false | |
| [components.experimental_char_ner_tokenizer.model.tok2vec.encode] | |
| @architectures = "spacy.MaxoutWindowEncoder.v2" | |
| width = 128 | |
| depth = 4 | |
| window_size = 4 | |
| maxout_pieces = 2 | |
| [components.experimental_edit_tree_lemmatizer] | |
| factory = "experimental_edit_tree_lemmatizer" | |
| backoff = "orth" | |
| min_tree_freq = 1 | |
| overwrite = false | |
| scorer = {"@scorers":"spacy.lemmatizer_scorer.v1"} | |
| top_k = 1 | |
| [components.experimental_edit_tree_lemmatizer.model] | |
| @architectures = "spacy.Tagger.v1" | |
| nO = null | |
| [components.experimental_edit_tree_lemmatizer.model.tok2vec] | |
| @architectures = "spacy-transformers.TransformerListener.v1" | |
| grad_factor = 1.0 | |
| upstream = "transformer" | |
| pooling = {"@layers":"reduce_mean.v1"} | |
| [components.morphologizer] | |
| factory = "morphologizer" | |
| extend = false | |
| overwrite = false | |
| scorer = {"@scorers":"spacy.morphologizer_scorer.v1"} | |
| [components.morphologizer.model] | |
| @architectures = "spacy.Tagger.v1" | |
| nO = null | |
| [components.morphologizer.model.tok2vec] | |
| @architectures = "spacy-transformers.TransformerListener.v1" | |
| grad_factor = 1.0 | |
| upstream = "transformer" | |
| pooling = {"@layers":"reduce_mean.v1"} | |
| [components.parser] | |
| factory = "parser" | |
| learn_tokens = false | |
| min_action_freq = 5 | |
| moves = null | |
| scorer = {"@scorers":"spacy.parser_scorer.v1"} | |
| update_with_oracle_cut_size = 100 | |
| [components.parser.model] | |
| @architectures = "spacy.TransitionBasedParser.v2" | |
| state_type = "parser" | |
| extra_state_tokens = false | |
| hidden_width = 64 | |
| maxout_pieces = 3 | |
| use_upper = false | |
| nO = null | |
| [components.parser.model.tok2vec] | |
| @architectures = "spacy-transformers.TransformerListener.v1" | |
| grad_factor = 1.0 | |
| upstream = "transformer" | |
| pooling = {"@layers":"reduce_mean.v1"} | |
| [components.senter] | |
| factory = "senter" | |
| overwrite = false | |
| scorer = {"@scorers":"spacy.senter_scorer.v1"} | |
| [components.senter.model] | |
| @architectures = "spacy.Tagger.v1" | |
| nO = null | |
| [components.senter.model.tok2vec] | |
| @architectures = "spacy-transformers.TransformerListener.v1" | |
| grad_factor = 1.0 | |
| upstream = "transformer" | |
| pooling = {"@layers":"reduce_mean.v1"} | |
| [components.tagger] | |
| factory = "tagger" | |
| neg_prefix = "!!!" | |
| overwrite = false | |
| scorer = {"@scorers":"spacy.tagger_scorer.v1"} | |
| [components.tagger.model] | |
| @architectures = "spacy.Tagger.v1" | |
| nO = null | |
| [components.tagger.model.tok2vec] | |
| @architectures = "spacy-transformers.TransformerListener.v1" | |
| grad_factor = 1.0 | |
| upstream = "transformer" | |
| pooling = {"@layers":"reduce_mean.v1"} | |
| [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 = "xlm-roberta-base" | |
| mixed_precision = true | |
| [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 = ${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 = 3 | |
| patience = 5000 | |
| max_epochs = 0 | |
| max_steps = 20000 | |
| eval_frequency = 200 | |
| frozen_components = [] | |
| before_to_disk = null | |
| annotating_components = [] | |
| [training.batcher] | |
| @batchers = "spacy.batch_by_padded.v1" | |
| discard_oversize = true | |
| get_length = null | |
| size = 2000 | |
| buffer = 256 | |
| [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 = true | |
| eps = 0.00000001 | |
| [training.optimizer.learn_rate] | |
| @schedules = "warmup_linear.v1" | |
| warmup_steps = 250 | |
| total_steps = 20000 | |
| initial_rate = 0.00005 | |
| [training.score_weights] | |
| token_f = 0.0 | |
| token_p = null | |
| token_r = null | |
| token_acc = null | |
| sents_f = 0.05 | |
| sents_p = 0.0 | |
| sents_r = 0.0 | |
| tag_acc = 0.11 | |
| pos_acc = 0.05 | |
| morph_acc = 0.05 | |
| morph_per_feat = null | |
| dep_uas = 0.11 | |
| dep_las = 0.11 | |
| dep_las_per_type = null | |
| lemma_acc = 0.52 | |
| [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] |