| [paths] |
| train = "/home/daza/ids-projects/DeReKo/spacy_train/spacy_bin_corpora/Tiger.NewOrth.train.spacy" |
| dev = "/home/daza/ids-projects/DeReKo/spacy_train/spacy_bin_corpora/Tiger.NewOrth.test.spacy" |
| |
| [system] |
| gpu_allocator = "pytorch" |
| |
| |
| [nlp] |
| lang = "de" |
| pipeline = ["transformer", "tagger"] |
| tokenizer = {"@tokenizers": "spacy.Tokenizer.v1"} |
| |
| [components] |
| |
| [components.transformer] |
| factory = "transformer" |
| |
| [components.transformer.model] |
| @architectures = "spacy-transformers.TransformerModel.v1" |
| name = "bert-base-german-cased" |
| tokenizer_config = {"use_fast": true} |
| |
| [components.transformer.model.get_spans] |
| @span_getters = "spacy-transformers.strided_spans.v1" |
| window = 128 |
| stride = 96 |
| |
| |
| [components.tagger] |
| factory = "tagger" |
| |
| [components.tagger.model] |
| @architectures = "spacy.Tagger.v1" |
| nO = null |
| |
| [components.tagger.model.tok2vec] |
| @architectures = "spacy-transformers.TransformerListener.v1" |
| grad_factor = 1.0 |
| |
| [components.tagger.model.tok2vec.pooling] |
| @layers = "reduce_mean.v1" |
| |
| |
| |
| [corpora] |
| |
| [corpora.train] |
| @readers = "spacy.Corpus.v1" |
| path = ${paths.train} |
| max_length = 500 |
| |
| [corpora.dev] |
| @readers = "spacy.Corpus.v1" |
| path = ${paths.dev} |
| max_length = 0 |
| |
| [training] |
| accumulate_gradient = 3 |
| dev_corpus = "corpora.dev" |
| train_corpus = "corpora.train" |
| |
| [training.optimizer] |
| @optimizers = "Adam.v1" |
| |
| [training.optimizer.learn_rate] |
| @schedules = "warmup_linear.v1" |
| warmup_steps = 250 |
| total_steps = 20000 |
| initial_rate = 5e-5 |
| |
| |
| |
| [training.batcher] |
| @batchers = "spacy.batch_by_padded.v1" |
| discard_oversize = true |
| size = 2000 |
| buffer = 256 |
| |
| [initialize] |
| vectors = null |