| [paths] |
| base = "../data/ggponc_spacy_up" |
| vectors = null |
| init_tok2vec = null |
| train = null |
| dev = null |
|
|
| [system] |
| gpu_allocator = "pytorch" |
| seed = 0 |
|
|
| [nlp] |
| lang = "de" |
| pipeline = ["transformer","morphologizer","parser","transformer_spancat","spancat"] |
| batch_size = 1000 |
| disabled = [] |
| before_creation = null |
| after_creation = null |
| after_pipeline_creation = null |
| tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"} |
|
|
| [components] |
|
|
| [components.morphologizer] |
| factory = "morphologizer" |
| extend = false |
| overwrite = true |
| scorer = {"@scorers":"spacy.morphologizer_scorer.v1"} |
|
|
| [components.morphologizer.model] |
| @architectures = "spacy.Tagger.v2" |
| nO = null |
| normalize = false |
|
|
| [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 = 30 |
| 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 = 2 |
| 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.spancat] |
| factory = "spancat" |
| max_positive = 1 |
| scorer = {"@scorers":"phlobo.flat_scorer"} |
| spans_key = "entities" |
| threshold = 0.25 |
|
|
| [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 = "transformer_spancat" |
|
|
| [components.spancat.suggester] |
| @misc = "phlobo.chunk_and_ngram_suggester" |
| max_depth = 5 |
| sizes = [1,2,3,4,5,6,7,8] |
|
|
| [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-german-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] |
|
|
| [components.transformer_spancat] |
| factory = "transformer" |
| max_batch_items = 4096 |
| set_extra_annotations = {"@annotation_setters":"spacy-transformers.null_annotation_setter.v1"} |
|
|
| [components.transformer_spancat.model] |
| @architectures = "spacy-transformers.TransformerModel.v3" |
| name = "GerMedBERT/medbert-512" |
| mixed_precision = true |
|
|
| [components.transformer_spancat.model.get_spans] |
| @span_getters = "spacy-transformers.strided_spans.v1" |
| window = 128 |
| stride = 96 |
|
|
| [components.transformer_spancat.model.grad_scaler_config] |
|
|
| [components.transformer_spancat.model.tokenizer_config] |
| use_fast = true |
|
|
| [components.transformer_spancat.model.transformer_config] |
|
|
| [corpora] |
|
|
| [corpora.dev] |
| @readers = "spacy.Corpus.v1" |
| path = ${paths.base}/validation.spacy |
| max_length = 0 |
| gold_preproc = false |
| limit = 0 |
| augmenter = null |
|
|
| [corpora.train] |
| @readers = "spacy.Corpus.v1" |
| path = ${paths.base}/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 = ${system.seed} |
| gpu_allocator = ${system.gpu_allocator} |
| dropout = 0.1 |
| patience = 3200 |
| max_epochs = 100 |
| max_steps = 40000 |
| eval_frequency = 100 |
| frozen_components = ["transformer","morphologizer","parser"] |
| annotating_components = ["transformer","morphologizer","parser"] |
| 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 = "ggponc" |
| remove_config_values = [] |
| run_name = "2023-12-27_18-02-08-cuda-4" |
| model_log_interval = null |
| log_dataset_dir = null |
| entity = 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 = 40000 |
| initial_rate = 0.000025 |
|
|
| [training.score_weights] |
| pos_acc = null |
| morph_acc = null |
| morph_per_feat = null |
| dep_uas = null |
| dep_las = null |
| dep_las_per_type = null |
| sents_p = null |
| sents_r = null |
| sents_f = null |
| spans_sc_f = null |
| spans_sc_p = null |
| spans_sc_r = null |
| tag_acc = null |
| spans_entities_f = 1.0 |
| spans_entities_p = 0.0 |
| spans_entities_r = 0.0 |
| Diagnosis_or_Pathology_f = null |
| Other_Finding_f = null |
| Clinical_Drug_f = null |
| Nutrient_or_Body_Substance_f = 0.0 |
| External_Substance_f = 0.0 |
| Therapeutic_f = null |
| Diagnostic_f = null |
|
|
| [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] |
