Legal Bert

[ALEKS0805]

Hi ,

I am trying to implement nlpaueb/legal-bert-base-uncased into NER model to get some legal terms. This is my config file:

[paths]
train = null
dev = null
vectors = null
init_tok2vec = null

[system]
gpu_allocator = "pytorch"
seed = 0

[nlp]
lang = "en"
pipeline = ["transformer","ner"]
batch_size = 512
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
tokenizer = {"@Tokenizers":"spacy.Tokenizer.v1"}

[components]

[components.transformer]
factory = "transformer"

[components.transformer.model]
@architectures = "spacy-transformers.TransformerModel.v3"
name = "nlpaueb/legal-bert-base-uncased"
tokenizer_config = {"use_fast": true}

[components.transformer.model.get_spans]
@span_getters = "spacy-transformers.strided_spans.v1"
window = 128
stride = 96

[components.ner]
factory = "ner"

[components.ner.model]
@architectures = "spacy.TransitionBasedParser.v2"
state_type = "ner"
extra_state_tokens = false
hidden_width = 256
maxout_pieces = 2
use_upper = false
nO = null

[components.ner.model.tok2vec]
@architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 1.0

[components.ner.model.tok2vec.pooling]
@layers = "reduce_mean.v1"

[corpora]

[corpora.train]
@readers = "spacy.Corpus.v1"
gold_preproc = false
path = ${paths.train}
max_length = 0

[corpora.dev]
@readers = "spacy.Corpus.v1"
gold_preproc = false
path = ${paths.dev}
max_length = 0

[training]
train_corpus = "corpora.train"
dev_corpus = "corpora.dev"
seed = ${system:seed}
gpu_allocator = ${system:gpu_allocator}
dropout = 0.1
accumulate_gradient = 3
patience = 5000
max_epochs = 0
max_steps = 20000
eval_frequency = 1000
frozen_components = []
before_to_disk = null
annotating_components = []

[training.logger]
@Loggers = "spacy.ConsoleLogger.v1"
progress_bar = false

[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 = ${paths.vectors}
init_tok2vec = ${paths.init_tok2vec}
vocab_data = null
lookups = null
before_init = null
after_init = null

[initialize.components]

[initialize.tokenizer]

I got an error:
Traceback (most recent call last):
File "/usr/lib/python3.9/runpy.py", line 197, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/usr/lib/python3.9/runpy.py", line 87, in _run_code
exec(code, run_globals)
File "/root/.cache/pypoetry/virtualenvs/mlbuddy-spacy-TEOiTIHv-py3.9/lib/python3.9/site-packages/spacy/main.py", line 4, in
setup_cli()

How should I fix this? Any help will be appreciated.

[polm]

Please use Markdown code blocks to make your code easier to read.

You appear to have omitted the actual command you're running and error you're getting, so I'm not sure what's going on here. Can you include the part after the traceback with the error name?