mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-29 11:26:28 +03:00
06f0a8daa0
* fix grad_clip naming * cleaning up pretrained_vectors out of cfg * further refactoring Model init's * move Model building out of pipes * further refactor to require a model config when creating a pipe * small fixes * making cfg in nn_parser more consistent * fixing nr_class for parser * fixing nn_parser's nO * fix printing of loss * architectures in own file per type, consistent naming * convenience methods default_tagger_config and default_tok2vec_config * let create_pipe access default config if available for that component * default_parser_config * move defaults to separate folder * allow reading nlp from package or dir with argument 'name' * architecture spacy.VocabVectors.v1 to read static vectors from file * cleanup * default configs for nel, textcat, morphologizer, tensorizer * fix imports * fixing unit tests * fixes and clean up * fixing defaults, nO, fix unit tests * restore parser IO * fix IO * 'fix' serialization test * add *.cfg to manifest * fix example configs with additional arguments * replace Morpohologizer with Tagger * add IO bit when testing overfitting of tagger (currently failing) * fix IO - don't initialize when reading from disk * expand overfitting tests to also check IO goes OK * remove dropout from HashEmbed to fix Tagger performance * add defaults for sentrec * update thinc * always pass a Model instance to a Pipe * fix piped_added statement * remove obsolete W029 * remove obsolete errors * restore byte checking tests (work again) * clean up test * further test cleanup * convert from config to Model in create_pipe * bring back error when component is not initialized * cleanup * remove calls for nlp2.begin_training * use thinc.api in imports * allow setting charembed's nM and nC * fix for hardcoded nM/nC + unit test * formatting fixes * trigger build
67 lines
1.3 KiB
INI
67 lines
1.3 KiB
INI
[training]
|
|
patience = 10000
|
|
eval_frequency = 200
|
|
dropout = 0.2
|
|
init_tok2vec = null
|
|
vectors = null
|
|
max_epochs = 100
|
|
orth_variant_level = 0.0
|
|
gold_preproc = true
|
|
max_length = 0
|
|
use_gpu = -1
|
|
scores = ["tags_acc", "uas", "las"]
|
|
score_weights = {"las": 0.8, "tags_acc": 0.2}
|
|
limit = 0
|
|
|
|
[training.batch_size]
|
|
@schedules = "compounding.v1"
|
|
start = 100
|
|
stop = 1000
|
|
compound = 1.001
|
|
|
|
[optimizer]
|
|
@optimizers = "Adam.v1"
|
|
learn_rate = 0.001
|
|
beta1 = 0.9
|
|
beta2 = 0.999
|
|
|
|
[nlp]
|
|
lang = "en"
|
|
vectors = ${training:vectors}
|
|
|
|
[nlp.pipeline.tok2vec]
|
|
factory = "tok2vec"
|
|
|
|
[nlp.pipeline.tagger]
|
|
factory = "tagger"
|
|
|
|
[nlp.pipeline.parser]
|
|
factory = "parser"
|
|
|
|
[nlp.pipeline.tagger.model]
|
|
@architectures = "spacy.Tagger.v1"
|
|
|
|
[nlp.pipeline.tagger.model.tok2vec]
|
|
@architectures = "spacy.Tok2VecTensors.v1"
|
|
width = ${nlp.pipeline.tok2vec.model:width}
|
|
|
|
[nlp.pipeline.parser.model]
|
|
@architectures = "spacy.TransitionBasedParser.v1"
|
|
nr_feature_tokens = 8
|
|
hidden_width = 64
|
|
maxout_pieces = 3
|
|
|
|
[nlp.pipeline.parser.model.tok2vec]
|
|
@architectures = "spacy.Tok2VecTensors.v1"
|
|
width = ${nlp.pipeline.tok2vec.model:width}
|
|
|
|
[nlp.pipeline.tok2vec.model]
|
|
@architectures = "spacy.HashEmbedCNN.v1"
|
|
pretrained_vectors = ${nlp:vectors}
|
|
width = 96
|
|
depth = 4
|
|
window_size = 1
|
|
embed_size = 2000
|
|
maxout_pieces = 3
|
|
subword_features = true
|