| [paths] |
| train = "./data/training/it/reviewed_annotations-11-2024/train.spacy" |
| dev = "./data/training/it/reviewed_annotations-11-2024/dev.spacy" |
| vectors = null |
| init_tok2vec = null |
|
|
| [system] |
| gpu_allocator = "pytorch" |
| seed = 17 |
|
|
| [nlp] |
| lang = "it" |
| pipeline = ["base_transformer","morphologizer","tagger","parser","trainable_lemmatizer","ner_transformer","ner"] |
| batch_size = 512 |
| disabled = [] |
| before_creation = null |
| after_creation = null |
| after_pipeline_creation = null |
| tokenizer = {"@tokenizers":"customize_tokenizer"} |
| vectors = {"@vectors":"spacy.Vectors.v1"} |
|
|
| [components] |
|
|
| [components.base_transformer] |
| factory = "transformer" |
| max_batch_items = 4096 |
| set_extra_annotations = {"@annotation_setters":"spacy-transformers.null_annotation_setter.v1"} |
|
|
| [components.base_transformer.model] |
| @architectures = "spacy-transformers.TransformerModel.v3" |
| name = "dbmdz/bert-base-italian-xxl-cased" |
| mixed_precision = false |
|
|
| [components.base_transformer.model.get_spans] |
| @span_getters = "spacy-transformers.strided_spans.v1" |
| window = 128 |
| stride = 96 |
|
|
| [components.base_transformer.model.grad_scaler_config] |
|
|
| [components.base_transformer.model.tokenizer_config] |
| use_fast = true |
|
|
| [components.base_transformer.model.transformer_config] |
|
|
| [components.morphologizer] |
| factory = "morphologizer" |
| extend = false |
| label_smoothing = 0.0 |
| 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 |
| pooling = {"@layers":"reduce_mean.v1"} |
| upstream = "*" |
|
|
| [components.ner] |
| factory = "ner" |
| incorrect_spans_key = null |
| moves = null |
| scorer = {"@scorers":"spacy.ner_scorer.v1"} |
| update_with_oracle_cut_size = 100 |
|
|
| [components.ner.model] |
| @architectures = "spacy.TransitionBasedParser.v2" |
| state_type = "ner" |
| extra_state_tokens = false |
| hidden_width = 64 |
| maxout_pieces = 2 |
| use_upper = false |
| nO = null |
|
|
| [components.ner.model.tok2vec] |
| @architectures = "spacy-transformers.TransformerListener.v1" |
| grad_factor = 1.0 |
| pooling = {"@layers":"reduce_mean.v1"} |
| upstream = "ner_transformer" |
|
|
| [components.ner_transformer] |
| factory = "transformer" |
| max_batch_items = 4096 |
| set_extra_annotations = {"@annotation_setters":"spacy-transformers.null_annotation_setter.v1"} |
|
|
| [components.ner_transformer.model] |
| @architectures = "spacy-transformers.TransformerModel.v3" |
| name = "dbmdz/bert-base-italian-xxl-cased" |
| mixed_precision = false |
|
|
| [components.ner_transformer.model.get_spans] |
| @span_getters = "spacy-transformers.strided_spans.v1" |
| window = 128 |
| stride = 96 |
|
|
| [components.ner_transformer.model.grad_scaler_config] |
|
|
| [components.ner_transformer.model.tokenizer_config] |
| use_fast = true |
|
|
| [components.ner_transformer.model.transformer_config] |
|
|
| [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 = 128 |
| maxout_pieces = 3 |
| use_upper = false |
| nO = null |
|
|
| [components.parser.model.tok2vec] |
| @architectures = "spacy-transformers.TransformerListener.v1" |
| grad_factor = 1.0 |
| pooling = {"@layers":"reduce_mean.v1"} |
| upstream = "base_transformer" |
|
|
| [components.tagger] |
| factory = "tagger" |
| label_smoothing = 0.0 |
| neg_prefix = "!" |
| overwrite = false |
| scorer = {"@scorers":"spacy.tagger_scorer.v1"} |
|
|
| [components.tagger.model] |
| @architectures = "spacy.Tagger.v2" |
| nO = null |
| normalize = false |
|
|
| [components.tagger.model.tok2vec] |
| @architectures = "spacy-transformers.TransformerListener.v1" |
| grad_factor = 1.0 |
| pooling = {"@layers":"reduce_mean.v1"} |
| upstream = "*" |
|
|
| [components.trainable_lemmatizer] |
| factory = "trainable_lemmatizer" |
| backoff = "orth" |
| min_tree_freq = 3 |
| overwrite = false |
| scorer = {"@scorers":"spacy.lemmatizer_scorer.v1"} |
| top_k = 1 |
|
|
| [components.trainable_lemmatizer.model] |
| @architectures = "spacy.Tagger.v2" |
| nO = null |
| normalize = false |
|
|
| [components.trainable_lemmatizer.model.tok2vec] |
| @architectures = "spacy-transformers.TransformerListener.v1" |
| grad_factor = 1.0 |
| pooling = {"@layers":"reduce_mean.v1"} |
| upstream = "*" |
|
|
| [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 = 4800 |
| max_epochs = 0 |
| max_steps = 20000 |
| eval_frequency = 200 |
| frozen_components = ["base_transformer","morphologizer","tagger","parser","trainable_lemmatizer"] |
| annotating_components = ["base_transformer","morphologizer","tagger"] |
| before_to_disk = null |
| before_update = null |
|
|
| [training.batcher] |
| @batchers = "spacy.batch_by_padded.v1" |
| discard_oversize = false |
| buffer = 256 |
| get_length = null |
|
|
| [training.batcher.size] |
| @schedules = "compounding.v1" |
| start = 100 |
| stop = 1000 |
| compound = 1.001 |
| t = 0.0 |
|
|
| [training.logger] |
| @loggers = "spacy.ConsoleLogger.v3" |
| progress_bar = "train" |
| console_output = true |
| output_file = 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] |
| pos_acc = 0.1 |
| morph_acc = 0.1 |
| morph_per_feat = null |
| tag_acc = 0.2 |
| dep_uas = 0.1 |
| dep_las = 0.1 |
| dep_las_per_type = null |
| sents_p = null |
| sents_r = null |
| sents_f = 0.0 |
| lemma_acc = 0.2 |
| ents_f = 0.2 |
| ents_p = 0.0 |
| ents_r = 0.0 |
| ents_per_type = 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] |