| [paths] | |
| train = "data/train.spacy" | |
| dev = "data/dev.spacy" | |
| raw = null | |
| init_tok2vec = null | |
| vectors = null | |
| [system] | |
| seed = 342 | |
| gpu_allocator = "pytorch" | |
| [nlp] | |
| lang = "ru" | |
| pipeline = ["transformer","relation_extractor"] | |
| disabled = [] | |
| before_creation = null | |
| after_creation = null | |
| after_pipeline_creation = null | |
| tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"} | |
| batch_size = 200 | |
| vectors = {"@vectors":"spacy.Vectors.v1"} | |
| [components] | |
| [components.relation_extractor] | |
| factory = "relation_extractor" | |
| eval_frequency = ${training.eval_frequency} | |
| threshold = 0.5 | |
| [components.relation_extractor.model] | |
| @architectures = "rel_model.v1" | |
| [components.relation_extractor.model.classification_layer] | |
| @architectures = "rel_classification_layer.v1" | |
| nI = null | |
| nO = null | |
| [components.relation_extractor.model.create_instance_tensor] | |
| @architectures = "rel_instance_tensor.v1" | |
| pooling = {"@layers":"reduce_mean.v1"} | |
| [components.relation_extractor.model.create_instance_tensor.get_instances] | |
| @misc = "rel_instance_generator.v1" | |
| max_length = 100 | |
| [components.relation_extractor.model.create_instance_tensor.tok2vec] | |
| @architectures = "spacy-transformers.TransformerListener.v1" | |
| grad_factor = 1.0 | |
| pooling = {"@layers":"reduce_mean.v1"} | |
| upstream = "*" | |
| [components.transformer] | |
| factory = "transformer" | |
| max_batch_items = 2096 | |
| set_extra_annotations = {"@annotation_setters":"spacy-transformers.null_annotation_setter.v1"} | |
| [components.transformer.model] | |
| @architectures = "spacy-transformers.TransformerModel.v3" | |
| name = "cointegrated/rubert-tiny2" | |
| 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 = "Gold_ents_Corpus.v1" | |
| file = ${paths.dev} | |
| [corpora.train] | |
| @readers = "Gold_ents_Corpus.v1" | |
| file = ${paths.train} | |
| [training] | |
| seed = ${system.seed} | |
| gpu_allocator = ${system.gpu_allocator} | |
| dropout = 0.2 | |
| accumulate_gradient = 1 | |
| patience = 1600000 | |
| max_epochs = 0 | |
| max_steps = 5000 | |
| eval_frequency = 50 | |
| frozen_components = [] | |
| dev_corpus = "corpora.dev" | |
| train_corpus = "corpora.train" | |
| before_to_disk = null | |
| annotating_components = [] | |
| 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] | |
| rel_micro_p = 0.0 | |
| rel_micro_r = 0.0 | |
| rel_micro_f = 0.1 | |
| rel_macro_f = 0.1 | |
| rel_weighted_f = 0.1 | |
| f1_PART-OF = 0.1 | |
| f1_LOCATED-AT = 0.1 | |
| f1_CONNECTED-WITH = 0.1 | |
| f1_IN-MANNER-OF = 0.1 | |
| f1_ATTRIBUTE-FOR = 0.1 | |
| f1_macro = 0.1 | |
| f1_weighted = 0.1 | |
| [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] |