diff --git a/examples/experiments/ptb-joint-pos-dep/defaults.cfg b/examples/experiments/ptb-joint-pos-dep/defaults.cfg index 48741c433..5850eaf3a 100644 --- a/examples/experiments/ptb-joint-pos-dep/defaults.cfg +++ b/examples/experiments/ptb-joint-pos-dep/defaults.cfg @@ -4,16 +4,16 @@ patience = 10000 eval_frequency = 200 dropout = 0.2 init_tok2vec = null -vectors = null +vectors = "tmp/fasttext_vectors/vocab" max_epochs = 100 orth_variant_level = 0.0 gold_preproc = true max_length = 0 -scores = ["tag_acc", "dep_uas", "dep_las"] +scores = ["tag_acc", "dep_uas", "dep_las", "speed"] score_weights = {"dep_las": 0.8, "tag_acc": 0.2} limit = 0 seed = 0 -accumulate_gradient = 2 +accumulate_gradient = 1 discard_oversize = false raw_text = null tag_map = null @@ -22,7 +22,7 @@ base_model = null eval_batch_size = 128 use_pytorch_for_gpu_memory = false -batch_by = "padded" +batch_by = "words" [training.batch_size] @schedules = "compounding.v1" @@ -65,7 +65,7 @@ min_action_freq = 1 [components.tagger.model.tok2vec] @architectures = "spacy.Tok2VecListener.v1" -width = ${components.tok2vec.model:width} +width = ${components.tok2vec.model.encode:width} [components.parser.model] @architectures = "spacy.TransitionBasedParser.v1" @@ -75,20 +75,21 @@ maxout_pieces = 3 [components.parser.model.tok2vec] @architectures = "spacy.Tok2VecListener.v1" -width = ${components.tok2vec.model:width} +width = ${components.tok2vec.model.encode:width} [components.tok2vec.model] @architectures = "spacy.Tok2Vec.v1" [components.tok2vec.model.embed] -@architectures = "spacy.HashEmbed.v1" -width = 96 +@architectures = "spacy.MultiHashEmbed.v1" +width = ${components.tok2vec.model.encode:width} rows = 2000 -also_use_subwords = true -also_use_static_vectors = false +also_embed_subwords = true +also_use_static_vectors = true [components.tok2vec.model.encode] -@architectures = "spacy.MaxoutWindowEncode.v1" +@architectures = "spacy.MaxoutWindowEncoder.v1" +width = 96 depth = 4 window_size = 1 maxout_pieces = 3