Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity
spaCy/extra/experiments/onto-joint/pretrain.cfg

153 lines
3.3 KiB
INI
Raw Normal View History

pretrain from config
2020-06-03 12:45:00 +00:00
# Training hyper-parameters and additional features.
[training]
# Whether to train on sequences with 'gold standard' sentence boundaries
# and tokens. If you set this to true, take care to ensure your run-time
# data is passed in sentence-by-sentence via some prior preprocessing.
gold_preproc = false
# Limitations on training document length or number of examples.
max_length = 0
limit = 0
# Data augmentation
orth_variant_level = 0.0
dropout = 0.1
# Controls early-stopping. 0 or -1 mean unlimited.
patience = 1600
max_epochs = 0
max_steps = 20000
eval_frequency = 400
# Other settings
seed = 0
accumulate_gradient = 1
use_pytorch_for_gpu_memory = false
# Control how scores are printed and checkpoints are evaluated.
scores = ["speed", "tags_acc", "uas", "las", "ents_f"]
score_weights = {"las": 0.4, "ents_f": 0.4, "tags_acc": 0.2}
# These settings are invalid for the transformer models.
init_tok2vec = null
discard_oversize = false
Update config and commands
2020-07-11 11:03:53 +00:00
omit_extra_lookups = false
batch_by = "words"
use_gpu = -1
raw_text = null
tag_map = null
pretrain from config
2020-06-03 12:45:00 +00:00
[training.batch_size]
@schedules = "compounding.v1"
start = 1000
stop = 1000
compound = 1.001
[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 = true
eps = 1e-8
learn_rate = 0.001
[pretraining]
small fixes to pretrain config, init_tok2vec TODO
2020-06-03 17:32:40 +00:00
max_epochs = 1000
pretrain from config
2020-06-03 12:45:00 +00:00
min_length = 5
max_length = 500
dropout = 0.2
n_save_every = null
batch_size = 3000
small fixes to pretrain config, init_tok2vec TODO
2020-06-03 17:32:40 +00:00
seed = ${training:seed}
use_pytorch_for_gpu_memory = ${training:use_pytorch_for_gpu_memory}
remove duplicate model definition of tok2vec layer
2020-06-04 13:49:23 +00:00
tok2vec_model = "nlp.pipeline.tok2vec.model"
pretrain from config
2020-06-03 12:45:00 +00:00
Refactor pretrain and support character-based objective for v3 (#5706) * Start adding character-based stuff * Start adding character-based objective * Start adding character-based stuff * Start adding character-based objective * Remove outdated comment * Update pretraining models * Add/fix character-based multi-task models * Refactor pretrain and support character-based objective * Update pretrain config * Remove unused * Fix flake8 errors * Clean up imports * Format * Format * Update Thinc version * Raise error if vectors objective but no vectors
2020-07-03 15:57:28 +00:00
[pretraining.objective]
type = "characters"
n_characters = 4
pretrain from config
2020-06-03 12:45:00 +00:00
[pretraining.optimizer]
@optimizers = "Adam.v1"
beta1 = 0.9
beta2 = 0.999
L2_is_weight_decay = true
L2 = 0.01
grad_clip = 1.0
use_averages = true
eps = 1e-8
learn_rate = 0.001
[nlp]
lang = "en"
train is from-config by default (#5575) * verbose and tag_map options * adding init_tok2vec option and only changing the tok2vec that is specified * adding omit_extra_lookups and verifying textcat config * wip * pretrain bugfix * add replace and resume options * train_textcat fix * raw text functionality * improve UX when KeyError or when input data can't be parsed * avoid unnecessary access to goldparse in TextCat pipe * save performance information in nlp.meta * add noise_level to config * move nn_parser's defaults to config file * multitask in config - doesn't work yet * scorer offering both F and AUC options, need to be specified in config * add textcat verification code from old train script * small fixes to config files * clean up * set default config for ner/parser to allow create_pipe to work as before * two more test fixes * small fixes * cleanup * fix NER pickling + additional unit test * create_pipe as before
2020-06-12 00:02:07 +00:00
vectors = null
Update config and commands
2020-07-11 11:03:53 +00:00
base_model = null
[nlp.pipeline]
pretrain from config
2020-06-03 12:45:00 +00:00
[nlp.pipeline.tok2vec]
factory = "tok2vec"
[nlp.pipeline.senter]
factory = "senter"
[nlp.pipeline.ner]
factory = "ner"
train is from-config by default (#5575) * verbose and tag_map options * adding init_tok2vec option and only changing the tok2vec that is specified * adding omit_extra_lookups and verifying textcat config * wip * pretrain bugfix * add replace and resume options * train_textcat fix * raw text functionality * improve UX when KeyError or when input data can't be parsed * avoid unnecessary access to goldparse in TextCat pipe * save performance information in nlp.meta * add noise_level to config * move nn_parser's defaults to config file * multitask in config - doesn't work yet * scorer offering both F and AUC options, need to be specified in config * add textcat verification code from old train script * small fixes to config files * clean up * set default config for ner/parser to allow create_pipe to work as before * two more test fixes * small fixes * cleanup * fix NER pickling + additional unit test * create_pipe as before
2020-06-12 00:02:07 +00:00
learn_tokens = false
min_action_freq = 1
beam_width = 1
beam_update_prob = 1.0
pretrain from config
2020-06-03 12:45:00 +00:00
[nlp.pipeline.tagger]
factory = "tagger"
[nlp.pipeline.parser]
factory = "parser"
train is from-config by default (#5575) * verbose and tag_map options * adding init_tok2vec option and only changing the tok2vec that is specified * adding omit_extra_lookups and verifying textcat config * wip * pretrain bugfix * add replace and resume options * train_textcat fix * raw text functionality * improve UX when KeyError or when input data can't be parsed * avoid unnecessary access to goldparse in TextCat pipe * save performance information in nlp.meta * add noise_level to config * move nn_parser's defaults to config file * multitask in config - doesn't work yet * scorer offering both F and AUC options, need to be specified in config * add textcat verification code from old train script * small fixes to config files * clean up * set default config for ner/parser to allow create_pipe to work as before * two more test fixes * small fixes * cleanup * fix NER pickling + additional unit test * create_pipe as before
2020-06-12 00:02:07 +00:00
learn_tokens = false
min_action_freq = 1
beam_width = 1
beam_update_prob = 1.0
pretrain from config
2020-06-03 12:45:00 +00:00
[nlp.pipeline.senter.model]
@architectures = "spacy.Tagger.v1"
[nlp.pipeline.senter.model.tok2vec]
@architectures = "spacy.Tok2VecTensors.v1"
width = ${nlp.pipeline.tok2vec.model:width}
[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 = 128
maxout_pieces = 3
use_upper = false
[nlp.pipeline.parser.model.tok2vec]
@architectures = "spacy.Tok2VecTensors.v1"
width = ${nlp.pipeline.tok2vec.model:width}
[nlp.pipeline.ner.model]
@architectures = "spacy.TransitionBasedParser.v1"
nr_feature_tokens = 3
hidden_width = 128
maxout_pieces = 3
use_upper = false
[nlp.pipeline.ner.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 = 256
depth = 6
window_size = 1
embed_size = 10000
maxout_pieces = 3
subword_features = true
dropout = null