search

Hyperparticle / udify

A single model that parses Universal Dependencies across 75 languages. Given a sentence, jointly predicts part-of-speech tags, morphology tags, lemmas, and dependency trees.
https://arxiv.org/abs/1904.02099
MIT License
219 stars 56 forks source link

RuntimeError: unexpected EOF #23

Open ftyers opened 3 years ago

ftyers commented 3 years ago

I'm trying to run udify on some data and have followed the instructions, e.g. 

$ git clone https://github.com/Hyperparticle/udify
$ pip install -r ./requirements.txt
$ curl --remote-name-all https://lindat.mff.cuni.cz/repository/xmlui/bitstream/handle/11234/1-3042{/udify-model.tar.gz,/udify-bert.tar.gz}

I get the following output:

fran@ipek:~/source/udify$ python3.8 predict.py --device -1 udify-model.tar.gz test.0.conllu.input logs/pred.0.conllu --eval_file logs/pred.0.json
2021-01-15 16:27:42,512 - INFO - allennlp.models.archival - loading archive file /home/fran/source/udify from cache at /home/fran/source/udify
2021-01-15 16:27:42,548 - INFO - allennlp.common.registrable - instantiating registered subclass udify_model of <class 'allennlp.models.model.Model'>
2021-01-15 16:27:42,548 - INFO - allennlp.common.params - vocabulary.type = default
2021-01-15 16:27:42,548 - INFO - allennlp.common.registrable - instantiating registered subclass default of <class 'allennlp.data.vocabulary.Vocabulary'>
2021-01-15 16:27:42,548 - INFO - allennlp.data.vocabulary - Loading token dictionary from /home/fran/source/udify/vocabulary.
2021-01-15 16:27:44,391 - INFO - allennlp.common.from_params - instantiating class <class 'allennlp.models.model.Model'> from params {'decoders': {'deps': {'arc_representation_dim': 768, 'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'pos_embed_dim': None, 'tag_representation_dim': 256, 'type': 'udify_dependency_decoder'}, 'feats': {'adaptive': True, 'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'label_smoothing': 0.03, 'task': 'feats', 'type': 'udify_tag_decoder'}, 'lemmas': {'adaptive': True, 'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'label_smoothing': 0.03, 'task': 'lemmas', 'type': 'udify_tag_decoder'}, 'upos': {'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'label_smoothing': 0.03, 'task': 'upos', 'type': 'udify_tag_decoder'}}, 'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'layer_dropout': 0.08, 'mix_embedding': 12, 'tasks': ['upos', 'feats', 'lemmas', 'deps'], 'text_field_embedder': {'allow_unmatched_keys': True, 'dropout': 0.4, 'embedder_to_indexer_map': {'bert': ['bert', 'bert-offsets']}, 'token_embedders': {'bert': {'bert_config': 'config/archive/bert-base-multilingual-cased/bert_config.json', 'combine_layers': 'all', 'dropout': 0.1, 'layer_dropout': 0.08, 'requires_grad': True, 'type': 'udify-bert-predictor'}}, 'type': 'udify_embedder'}, 'type': 'udify_model', 'word_dropout': 0.1} and extras {'vocab'}
2021-01-15 16:27:44,391 - INFO - allennlp.common.params - model.type = udify_model
2021-01-15 16:27:44,392 - INFO - allennlp.common.from_params - instantiating class <class 'udify.models.udify_model.UdifyModel'> from params {'decoders': {'deps': {'arc_representation_dim': 768, 'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'pos_embed_dim': None, 'tag_representation_dim': 256, 'type': 'udify_dependency_decoder'}, 'feats': {'adaptive': True, 'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'label_smoothing': 0.03, 'task': 'feats', 'type': 'udify_tag_decoder'}, 'lemmas': {'adaptive': True, 'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'label_smoothing': 0.03, 'task': 'lemmas', 'type': 'udify_tag_decoder'}, 'upos': {'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'label_smoothing': 0.03, 'task': 'upos', 'type': 'udify_tag_decoder'}}, 'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'layer_dropout': 0.08, 'mix_embedding': 12, 'tasks': ['upos', 'feats', 'lemmas', 'deps'], 'text_field_embedder': {'allow_unmatched_keys': True, 'dropout': 0.4, 'embedder_to_indexer_map': {'bert': ['bert', 'bert-offsets']}, 'token_embedders': {'bert': {'bert_config': 'config/archive/bert-base-multilingual-cased/bert_config.json', 'combine_layers': 'all', 'dropout': 0.1, 'layer_dropout': 0.08, 'requires_grad': True, 'type': 'udify-bert-predictor'}}, 'type': 'udify_embedder'}, 'word_dropout': 0.1} and extras {'vocab'}
2021-01-15 16:27:44,392 - INFO - allennlp.common.params - model.tasks = ['upos', 'feats', 'lemmas', 'deps']
2021-01-15 16:27:44,392 - INFO - allennlp.common.from_params - instantiating class <class 'allennlp.modules.text_field_embedders.text_field_embedder.TextFieldEmbedder'> from params {'allow_unmatched_keys': True, 'dropout': 0.4, 'embedder_to_indexer_map': {'bert': ['bert', 'bert-offsets']}, 'token_embedders': {'bert': {'bert_config': 'config/archive/bert-base-multilingual-cased/bert_config.json', 'combine_layers': 'all', 'dropout': 0.1, 'layer_dropout': 0.08, 'requires_grad': True, 'type': 'udify-bert-predictor'}}, 'type': 'udify_embedder'} and extras {'vocab'}
2021-01-15 16:27:44,392 - INFO - allennlp.common.params - model.text_field_embedder.type = udify_embedder
2021-01-15 16:27:44,392 - INFO - allennlp.common.params - model.text_field_embedder.allow_unmatched_keys = True
2021-01-15 16:27:44,392 - INFO - allennlp.common.params - model.text_field_embedder.dropout = 0.4
2021-01-15 16:27:44,392 - INFO - allennlp.common.params - model.text_field_embedder.output_dim = None
2021-01-15 16:27:44,392 - INFO - allennlp.common.params - model.text_field_embedder.sum_embeddings = None
2021-01-15 16:27:44,392 - INFO - allennlp.common.from_params - instantiating class <class 'allennlp.modules.token_embedders.token_embedder.TokenEmbedder'> from params {'bert_config': 'config/archive/bert-base-multilingual-cased/bert_config.json', 'combine_layers': 'all', 'dropout': 0.1, 'layer_dropout': 0.08, 'requires_grad': True, 'type': 'udify-bert-predictor'} and extras {'vocab'}
2021-01-15 16:27:44,393 - INFO - allennlp.common.params - model.text_field_embedder.token_embedders.bert.type = udify-bert-predictor
2021-01-15 16:27:44,393 - INFO - allennlp.common.from_params - instantiating class <class 'udify.modules.bert_pretrained.UdifyPredictionBertEmbedder'> from params {'bert_config': 'config/archive/bert-base-multilingual-cased/bert_config.json', 'combine_layers': 'all', 'dropout': 0.1, 'layer_dropout': 0.08, 'requires_grad': True} and extras {'vocab'}
2021-01-15 16:27:44,393 - INFO - allennlp.common.params - model.text_field_embedder.token_embedders.bert.bert_config = config/archive/bert-base-multilingual-cased/bert_config.json
2021-01-15 16:27:44,393 - INFO - allennlp.common.params - model.text_field_embedder.token_embedders.bert.requires_grad = True
2021-01-15 16:27:44,393 - INFO - allennlp.common.params - model.text_field_embedder.token_embedders.bert.dropout = 0.1
2021-01-15 16:27:44,393 - INFO - allennlp.common.params - model.text_field_embedder.token_embedders.bert.layer_dropout = 0.08
2021-01-15 16:27:44,393 - INFO - allennlp.common.params - model.text_field_embedder.token_embedders.bert.combine_layers = all
2021-01-15 16:27:46,710 - INFO - allennlp.common.from_params - instantiating class <class 'allennlp.modules.seq2seq_encoders.seq2seq_encoder.Seq2SeqEncoder'> from params {'input_dim': 768, 'type': 'pass_through'} and extras {'vocab'}
2021-01-15 16:27:46,710 - INFO - allennlp.common.params - model.encoder.type = pass_through
2021-01-15 16:27:46,711 - INFO - allennlp.common.from_params - instantiating class <class 'allennlp.modules.seq2seq_encoders.pass_through_encoder.PassThroughEncoder'> from params {'input_dim': 768} and extras {'vocab'}
2021-01-15 16:27:46,711 - INFO - allennlp.common.params - model.encoder.input_dim = 768
2021-01-15 16:27:46,711 - INFO - allennlp.common.from_params - instantiating class <class 'allennlp.models.model.Model'> from params {'arc_representation_dim': 768, 'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'pos_embed_dim': None, 'tag_representation_dim': 256, 'type': 'udify_dependency_decoder'} and extras {'vocab'}
2021-01-15 16:27:46,711 - INFO - allennlp.common.params - model.decoders.deps.type = udify_dependency_decoder
2021-01-15 16:27:46,711 - INFO - allennlp.common.from_params - instantiating class <class 'udify.models.dependency_decoder.DependencyDecoder'> from params {'arc_representation_dim': 768, 'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'pos_embed_dim': None, 'tag_representation_dim': 256} and extras {'vocab'}
2021-01-15 16:27:46,711 - INFO - allennlp.common.from_params - instantiating class <class 'allennlp.modules.seq2seq_encoders.seq2seq_encoder.Seq2SeqEncoder'> from params {'input_dim': 768, 'type': 'pass_through'} and extras {'vocab'}
2021-01-15 16:27:46,711 - INFO - allennlp.common.params - model.decoders.deps.encoder.type = pass_through
2021-01-15 16:27:46,711 - INFO - allennlp.common.from_params - instantiating class <class 'allennlp.modules.seq2seq_encoders.pass_through_encoder.PassThroughEncoder'> from params {'input_dim': 768} and extras {'vocab'}
2021-01-15 16:27:46,711 - INFO - allennlp.common.params - model.decoders.deps.encoder.input_dim = 768
2021-01-15 16:27:46,712 - INFO - allennlp.common.params - model.decoders.deps.tag_representation_dim = 256
2021-01-15 16:27:46,712 - INFO - allennlp.common.params - model.decoders.deps.arc_representation_dim = 768
2021-01-15 16:27:46,712 - INFO - allennlp.common.params - model.decoders.deps.pos_embed_dim = None
2021-01-15 16:27:46,712 - INFO - allennlp.common.params - model.decoders.deps.use_mst_decoding_for_validation = True
2021-01-15 16:27:46,712 - INFO - allennlp.common.params - model.decoders.deps.dropout = 0.5
2021-01-15 16:27:46,712 - INFO - allennlp.common.registrable - instantiating registered subclass elu of <class 'allennlp.nn.activations.Activation'>
2021-01-15 16:27:46,718 - INFO - allennlp.common.registrable - instantiating registered subclass linear of <class 'allennlp.nn.activations.Activation'>
2021-01-15 16:27:46,722 - INFO - allennlp.common.registrable - instantiating registered subclass elu of <class 'allennlp.nn.activations.Activation'>
2021-01-15 16:27:46,867 - INFO - udify.models.dependency_decoder - Found POS tags corresponding to the following punctuation : {}. Ignoring words with these POS tags for evaluation.
2021-01-15 16:27:46,867 - INFO - allennlp.nn.initializers - Initializing parameters
2021-01-15 16:27:46,867 - INFO - allennlp.nn.initializers - Done initializing parameters; the following parameters are using their default initialization from their code
2021-01-15 16:27:46,868 - INFO - allennlp.nn.initializers -    _head_sentinel
2021-01-15 16:27:46,868 - INFO - allennlp.nn.initializers -    arc_attention._bias
2021-01-15 16:27:46,868 - INFO - allennlp.nn.initializers -    arc_attention._weight_matrix
2021-01-15 16:27:46,868 - INFO - allennlp.nn.initializers -    child_arc_feedforward._linear_layers.0.bias
2021-01-15 16:27:46,868 - INFO - allennlp.nn.initializers -    child_arc_feedforward._linear_layers.0.weight
2021-01-15 16:27:46,868 - INFO - allennlp.nn.initializers -    child_tag_feedforward._linear_layers.0.bias
2021-01-15 16:27:46,868 - INFO - allennlp.nn.initializers -    child_tag_feedforward._linear_layers.0.weight
2021-01-15 16:27:46,868 - INFO - allennlp.nn.initializers -    head_arc_feedforward._linear_layers.0.bias
2021-01-15 16:27:46,868 - INFO - allennlp.nn.initializers -    head_arc_feedforward._linear_layers.0.weight
2021-01-15 16:27:46,868 - INFO - allennlp.nn.initializers -    head_tag_feedforward._linear_layers.0.bias
2021-01-15 16:27:46,868 - INFO - allennlp.nn.initializers -    head_tag_feedforward._linear_layers.0.weight
2021-01-15 16:27:46,868 - INFO - allennlp.nn.initializers -    tag_bilinear.bias
2021-01-15 16:27:46,868 - INFO - allennlp.nn.initializers -    tag_bilinear.weight
2021-01-15 16:27:46,869 - INFO - allennlp.common.from_params - instantiating class <class 'allennlp.models.model.Model'> from params {'adaptive': True, 'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'label_smoothing': 0.03, 'task': 'feats', 'type': 'udify_tag_decoder'} and extras {'vocab'}
2021-01-15 16:27:46,869 - INFO - allennlp.common.params - model.decoders.feats.type = udify_tag_decoder
2021-01-15 16:27:46,869 - INFO - allennlp.common.from_params - instantiating class <class 'udify.models.tag_decoder.TagDecoder'> from params {'adaptive': True, 'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'label_smoothing': 0.03, 'task': 'feats'} and extras {'vocab'}
2021-01-15 16:27:46,869 - INFO - allennlp.common.params - model.decoders.feats.task = feats
2021-01-15 16:27:46,869 - INFO - allennlp.common.from_params - instantiating class <class 'allennlp.modules.seq2seq_encoders.seq2seq_encoder.Seq2SeqEncoder'> from params {'input_dim': 768, 'type': 'pass_through'} and extras {'vocab'}
2021-01-15 16:27:46,870 - INFO - allennlp.common.params - model.decoders.feats.encoder.type = pass_through
2021-01-15 16:27:46,870 - INFO - allennlp.common.from_params - instantiating class <class 'allennlp.modules.seq2seq_encoders.pass_through_encoder.PassThroughEncoder'> from params {'input_dim': 768} and extras {'vocab'}
2021-01-15 16:27:46,870 - INFO - allennlp.common.params - model.decoders.feats.encoder.input_dim = 768
2021-01-15 16:27:46,870 - INFO - allennlp.common.params - model.decoders.feats.label_smoothing = 0.03
2021-01-15 16:27:46,870 - INFO - allennlp.common.params - model.decoders.feats.dropout = 0.5
2021-01-15 16:27:46,871 - INFO - allennlp.common.params - model.decoders.feats.adaptive = True
2021-01-15 16:27:46,871 - INFO - allennlp.common.params - model.decoders.feats.features = None
2021-01-15 16:27:46,895 - INFO - allennlp.nn.initializers - Initializing parameters
2021-01-15 16:27:46,895 - INFO - allennlp.nn.initializers - Done initializing parameters; the following parameters are using their default initialization from their code
2021-01-15 16:27:46,895 - INFO - allennlp.nn.initializers -    task_output.head.weight
2021-01-15 16:27:46,895 - INFO - allennlp.nn.initializers -    task_output.tail.0.0.weight
2021-01-15 16:27:46,895 - INFO - allennlp.nn.initializers -    task_output.tail.0.1.weight
2021-01-15 16:27:46,895 - INFO - allennlp.nn.initializers -    task_output.tail.1.0.weight
2021-01-15 16:27:46,896 - INFO - allennlp.nn.initializers -    task_output.tail.1.1.weight
2021-01-15 16:27:46,896 - INFO - allennlp.common.from_params - instantiating class <class 'allennlp.models.model.Model'> from params {'adaptive': True, 'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'label_smoothing': 0.03, 'task': 'lemmas', 'type': 'udify_tag_decoder'} and extras {'vocab'}
2021-01-15 16:27:46,896 - INFO - allennlp.common.params - model.decoders.lemmas.type = udify_tag_decoder
2021-01-15 16:27:46,896 - INFO - allennlp.common.from_params - instantiating class <class 'udify.models.tag_decoder.TagDecoder'> from params {'adaptive': True, 'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'label_smoothing': 0.03, 'task': 'lemmas'} and extras {'vocab'}
2021-01-15 16:27:46,897 - INFO - allennlp.common.params - model.decoders.lemmas.task = lemmas
2021-01-15 16:27:46,898 - INFO - allennlp.common.from_params - instantiating class <class 'allennlp.modules.seq2seq_encoders.seq2seq_encoder.Seq2SeqEncoder'> from params {'input_dim': 768, 'type': 'pass_through'} and extras {'vocab'}
2021-01-15 16:27:46,898 - INFO - allennlp.common.params - model.decoders.lemmas.encoder.type = pass_through
2021-01-15 16:27:46,898 - INFO - allennlp.common.from_params - instantiating class <class 'allennlp.modules.seq2seq_encoders.pass_through_encoder.PassThroughEncoder'> from params {'input_dim': 768} and extras {'vocab'}
2021-01-15 16:27:46,899 - INFO - allennlp.common.params - model.decoders.lemmas.encoder.input_dim = 768
2021-01-15 16:27:46,899 - INFO - allennlp.common.params - model.decoders.lemmas.label_smoothing = 0.03
2021-01-15 16:27:46,900 - INFO - allennlp.common.params - model.decoders.lemmas.dropout = 0.5
2021-01-15 16:27:46,900 - INFO - allennlp.common.params - model.decoders.lemmas.adaptive = True
2021-01-15 16:27:46,900 - INFO - allennlp.common.params - model.decoders.lemmas.features = None
2021-01-15 16:27:47,014 - INFO - allennlp.nn.initializers - Initializing parameters
2021-01-15 16:27:47,014 - INFO - allennlp.nn.initializers - Done initializing parameters; the following parameters are using their default initialization from their code
2021-01-15 16:27:47,014 - INFO - allennlp.nn.initializers -    task_output.head.weight
2021-01-15 16:27:47,015 - INFO - allennlp.nn.initializers -    task_output.tail.0.0.weight
2021-01-15 16:27:47,015 - INFO - allennlp.nn.initializers -    task_output.tail.0.1.weight
2021-01-15 16:27:47,015 - INFO - allennlp.nn.initializers -    task_output.tail.1.0.weight
2021-01-15 16:27:47,015 - INFO - allennlp.nn.initializers -    task_output.tail.1.1.weight
2021-01-15 16:27:47,015 - INFO - allennlp.common.from_params - instantiating class <class 'allennlp.models.model.Model'> from params {'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'label_smoothing': 0.03, 'task': 'upos', 'type': 'udify_tag_decoder'} and extras {'vocab'}
2021-01-15 16:27:47,015 - INFO - allennlp.common.params - model.decoders.upos.type = udify_tag_decoder
2021-01-15 16:27:47,015 - INFO - allennlp.common.from_params - instantiating class <class 'udify.models.tag_decoder.TagDecoder'> from params {'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'label_smoothing': 0.03, 'task': 'upos'} and extras {'vocab'}
2021-01-15 16:27:47,015 - INFO - allennlp.common.params - model.decoders.upos.task = upos
2021-01-15 16:27:47,015 - INFO - allennlp.common.from_params - instantiating class <class 'allennlp.modules.seq2seq_encoders.seq2seq_encoder.Seq2SeqEncoder'> from params {'input_dim': 768, 'type': 'pass_through'} and extras {'vocab'}
2021-01-15 16:27:47,015 - INFO - allennlp.common.params - model.decoders.upos.encoder.type = pass_through
2021-01-15 16:27:47,015 - INFO - allennlp.common.from_params - instantiating class <class 'allennlp.modules.seq2seq_encoders.pass_through_encoder.PassThroughEncoder'> from params {'input_dim': 768} and extras {'vocab'}
2021-01-15 16:27:47,015 - INFO - allennlp.common.params - model.decoders.upos.encoder.input_dim = 768
2021-01-15 16:27:47,016 - INFO - allennlp.common.params - model.decoders.upos.label_smoothing = 0.03
2021-01-15 16:27:47,016 - INFO - allennlp.common.params - model.decoders.upos.dropout = 0.5
2021-01-15 16:27:47,016 - INFO - allennlp.common.params - model.decoders.upos.adaptive = False
2021-01-15 16:27:47,016 - INFO - allennlp.common.params - model.decoders.upos.features = None
2021-01-15 16:27:47,016 - INFO - allennlp.nn.initializers - Initializing parameters
2021-01-15 16:27:47,016 - INFO - allennlp.nn.initializers - Done initializing parameters; the following parameters are using their default initialization from their code
2021-01-15 16:27:47,016 - INFO - allennlp.nn.initializers -    task_output._module.bias
2021-01-15 16:27:47,016 - INFO - allennlp.nn.initializers -    task_output._module.weight
2021-01-15 16:27:47,017 - INFO - allennlp.common.params - model.dropout = 0.5
2021-01-15 16:27:47,017 - INFO - allennlp.common.params - model.word_dropout = 0.1
2021-01-15 16:27:47,017 - INFO - allennlp.common.params - model.mix_embedding = 12
2021-01-15 16:27:47,017 - INFO - allennlp.common.params - model.layer_dropout = 0.08
2021-01-15 16:27:47,017 - INFO - pytorch_pretrained_bert.tokenization - loading vocabulary file config/archive/bert-base-multilingual-cased/vocab.txt
2021-01-15 16:27:47,258 - INFO - allennlp.nn.initializers - Initializing parameters
2021-01-15 16:27:47,259 - INFO - allennlp.nn.initializers - Done initializing parameters; the following parameters are using their default initialization from their code
2021-01-15 16:27:47,259 - INFO - allennlp.nn.initializers -    decoders.deps._head_sentinel
2021-01-15 16:27:47,259 - INFO - allennlp.nn.initializers -    decoders.deps.arc_attention._bias
2021-01-15 16:27:47,259 - INFO - allennlp.nn.initializers -    decoders.deps.arc_attention._weight_matrix
2021-01-15 16:27:47,259 - INFO - allennlp.nn.initializers -    decoders.deps.child_arc_feedforward._linear_layers.0.bias
2021-01-15 16:27:47,259 - INFO - allennlp.nn.initializers -    decoders.deps.child_arc_feedforward._linear_layers.0.weight
2021-01-15 16:27:47,259 - INFO - allennlp.nn.initializers -    decoders.deps.child_tag_feedforward._linear_layers.0.bias
2021-01-15 16:27:47,259 - INFO - allennlp.nn.initializers -    decoders.deps.child_tag_feedforward._linear_layers.0.weight
2021-01-15 16:27:47,259 - INFO - allennlp.nn.initializers -    decoders.deps.head_arc_feedforward._linear_layers.0.bias
2021-01-15 16:27:47,259 - INFO - allennlp.nn.initializers -    decoders.deps.head_arc_feedforward._linear_layers.0.weight
2021-01-15 16:27:47,259 - INFO - allennlp.nn.initializers -    decoders.deps.head_tag_feedforward._linear_layers.0.bias
2021-01-15 16:27:47,259 - INFO - allennlp.nn.initializers -    decoders.deps.head_tag_feedforward._linear_layers.0.weight
2021-01-15 16:27:47,259 - INFO - allennlp.nn.initializers -    decoders.deps.tag_bilinear.bias
2021-01-15 16:27:47,259 - INFO - allennlp.nn.initializers -    decoders.deps.tag_bilinear.weight
2021-01-15 16:27:47,259 - INFO - allennlp.nn.initializers -    decoders.feats.task_output.head.weight
2021-01-15 16:27:47,259 - INFO - allennlp.nn.initializers -    decoders.feats.task_output.tail.0.0.weight
2021-01-15 16:27:47,259 - INFO - allennlp.nn.initializers -    decoders.feats.task_output.tail.0.1.weight
2021-01-15 16:27:47,259 - INFO - allennlp.nn.initializers -    decoders.feats.task_output.tail.1.0.weight
2021-01-15 16:27:47,259 - INFO - allennlp.nn.initializers -    decoders.feats.task_output.tail.1.1.weight
2021-01-15 16:27:47,259 - INFO - allennlp.nn.initializers -    decoders.lemmas.task_output.head.weight
2021-01-15 16:27:47,259 - INFO - allennlp.nn.initializers -    decoders.lemmas.task_output.tail.0.0.weight
2021-01-15 16:27:47,259 - INFO - allennlp.nn.initializers -    decoders.lemmas.task_output.tail.0.1.weight
2021-01-15 16:27:47,259 - INFO - allennlp.nn.initializers -    decoders.lemmas.task_output.tail.1.0.weight
2021-01-15 16:27:47,259 - INFO - allennlp.nn.initializers -    decoders.lemmas.task_output.tail.1.1.weight
2021-01-15 16:27:47,259 - INFO - allennlp.nn.initializers -    decoders.upos.task_output._module.bias
2021-01-15 16:27:47,259 - INFO - allennlp.nn.initializers -    decoders.upos.task_output._module.weight
2021-01-15 16:27:47,259 - INFO - allennlp.nn.initializers -    scalar_mix.deps.gamma
2021-01-15 16:27:47,260 - INFO - allennlp.nn.initializers -    scalar_mix.deps.scalar_parameters.0
2021-01-15 16:27:47,260 - INFO - allennlp.nn.initializers -    scalar_mix.deps.scalar_parameters.1
2021-01-15 16:27:47,260 - INFO - allennlp.nn.initializers -    scalar_mix.deps.scalar_parameters.10
2021-01-15 16:27:47,260 - INFO - allennlp.nn.initializers -    scalar_mix.deps.scalar_parameters.11
2021-01-15 16:27:47,260 - INFO - allennlp.nn.initializers -    scalar_mix.deps.scalar_parameters.2
2021-01-15 16:27:47,260 - INFO - allennlp.nn.initializers -    scalar_mix.deps.scalar_parameters.3
2021-01-15 16:27:47,260 - INFO - allennlp.nn.initializers -    scalar_mix.deps.scalar_parameters.4
2021-01-15 16:27:47,260 - INFO - allennlp.nn.initializers -    scalar_mix.deps.scalar_parameters.5
2021-01-15 16:27:47,260 - INFO - allennlp.nn.initializers -    scalar_mix.deps.scalar_parameters.6
2021-01-15 16:27:47,260 - INFO - allennlp.nn.initializers -    scalar_mix.deps.scalar_parameters.7
2021-01-15 16:27:47,260 - INFO - allennlp.nn.initializers -    scalar_mix.deps.scalar_parameters.8
2021-01-15 16:27:47,260 - INFO - allennlp.nn.initializers -    scalar_mix.deps.scalar_parameters.9
2021-01-15 16:27:47,260 - INFO - allennlp.nn.initializers -    scalar_mix.feats.gamma
2021-01-15 16:27:47,260 - INFO - allennlp.nn.initializers -    scalar_mix.feats.scalar_parameters.0
2021-01-15 16:27:47,260 - INFO - allennlp.nn.initializers -    scalar_mix.feats.scalar_parameters.1
2021-01-15 16:27:47,260 - INFO - allennlp.nn.initializers -    scalar_mix.feats.scalar_parameters.10
2021-01-15 16:27:47,260 - INFO - allennlp.nn.initializers -    scalar_mix.feats.scalar_parameters.11
2021-01-15 16:27:47,260 - INFO - allennlp.nn.initializers -    scalar_mix.feats.scalar_parameters.2
2021-01-15 16:27:47,260 - INFO - allennlp.nn.initializers -    scalar_mix.feats.scalar_parameters.3
2021-01-15 16:27:47,260 - INFO - allennlp.nn.initializers -    scalar_mix.feats.scalar_parameters.4
2021-01-15 16:27:47,260 - INFO - allennlp.nn.initializers -    scalar_mix.feats.scalar_parameters.5
2021-01-15 16:27:47,260 - INFO - allennlp.nn.initializers -    scalar_mix.feats.scalar_parameters.6
2021-01-15 16:27:47,260 - INFO - allennlp.nn.initializers -    scalar_mix.feats.scalar_parameters.7
2021-01-15 16:27:47,260 - INFO - allennlp.nn.initializers -    scalar_mix.feats.scalar_parameters.8
2021-01-15 16:27:47,260 - INFO - allennlp.nn.initializers -    scalar_mix.feats.scalar_parameters.9
2021-01-15 16:27:47,260 - INFO - allennlp.nn.initializers -    scalar_mix.lemmas.gamma
2021-01-15 16:27:47,260 - INFO - allennlp.nn.initializers -    scalar_mix.lemmas.scalar_parameters.0
2021-01-15 16:27:47,260 - INFO - allennlp.nn.initializers -    scalar_mix.lemmas.scalar_parameters.1
2021-01-15 16:27:47,260 - INFO - allennlp.nn.initializers -    scalar_mix.lemmas.scalar_parameters.10
2021-01-15 16:27:47,260 - INFO - allennlp.nn.initializers -    scalar_mix.lemmas.scalar_parameters.11
2021-01-15 16:27:47,260 - INFO - allennlp.nn.initializers -    scalar_mix.lemmas.scalar_parameters.2
2021-01-15 16:27:47,260 - INFO - allennlp.nn.initializers -    scalar_mix.lemmas.scalar_parameters.3
2021-01-15 16:27:47,260 - INFO - allennlp.nn.initializers -    scalar_mix.lemmas.scalar_parameters.4
2021-01-15 16:27:47,260 - INFO - allennlp.nn.initializers -    scalar_mix.lemmas.scalar_parameters.5
2021-01-15 16:27:47,260 - INFO - allennlp.nn.initializers -    scalar_mix.lemmas.scalar_parameters.6
2021-01-15 16:27:47,261 - INFO - allennlp.nn.initializers -    scalar_mix.lemmas.scalar_parameters.7
2021-01-15 16:27:47,261 - INFO - allennlp.nn.initializers -    scalar_mix.lemmas.scalar_parameters.8
2021-01-15 16:27:47,261 - INFO - allennlp.nn.initializers -    scalar_mix.lemmas.scalar_parameters.9
2021-01-15 16:27:47,261 - INFO - allennlp.nn.initializers -    scalar_mix.upos.gamma
2021-01-15 16:27:47,261 - INFO - allennlp.nn.initializers -    scalar_mix.upos.scalar_parameters.0
2021-01-15 16:27:47,261 - INFO - allennlp.nn.initializers -    scalar_mix.upos.scalar_parameters.1
2021-01-15 16:27:47,261 - INFO - allennlp.nn.initializers -    scalar_mix.upos.scalar_parameters.10
2021-01-15 16:27:47,261 - INFO - allennlp.nn.initializers -    scalar_mix.upos.scalar_parameters.11
2021-01-15 16:27:47,261 - INFO - allennlp.nn.initializers -    scalar_mix.upos.scalar_parameters.2
2021-01-15 16:27:47,261 - INFO - allennlp.nn.initializers -    scalar_mix.upos.scalar_parameters.3
2021-01-15 16:27:47,261 - INFO - allennlp.nn.initializers -    scalar_mix.upos.scalar_parameters.4
2021-01-15 16:27:47,261 - INFO - allennlp.nn.initializers -    scalar_mix.upos.scalar_parameters.5
2021-01-15 16:27:47,261 - INFO - allennlp.nn.initializers -    scalar_mix.upos.scalar_parameters.6
2021-01-15 16:27:47,261 - INFO - allennlp.nn.initializers -    scalar_mix.upos.scalar_parameters.7
2021-01-15 16:27:47,261 - INFO - allennlp.nn.initializers -    scalar_mix.upos.scalar_parameters.8
2021-01-15 16:27:47,261 - INFO - allennlp.nn.initializers -    scalar_mix.upos.scalar_parameters.9
2021-01-15 16:27:47,261 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.embeddings.LayerNorm.bias
2021-01-15 16:27:47,261 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.embeddings.LayerNorm.weight
2021-01-15 16:27:47,261 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.embeddings.position_embeddings.weight
2021-01-15 16:27:47,261 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.embeddings.token_type_embeddings.weight
2021-01-15 16:27:47,261 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.embeddings.word_embeddings.weight
2021-01-15 16:27:47,261 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.0.attention.output.LayerNorm.bias
2021-01-15 16:27:47,261 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.0.attention.output.LayerNorm.weight
2021-01-15 16:27:47,261 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.0.attention.output.dense.bias
2021-01-15 16:27:47,261 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.0.attention.output.dense.weight
2021-01-15 16:27:47,261 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.0.attention.self.key.bias
2021-01-15 16:27:47,261 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.0.attention.self.key.weight
2021-01-15 16:27:47,261 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.0.attention.self.query.bias
2021-01-15 16:27:47,261 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.0.attention.self.query.weight
2021-01-15 16:27:47,261 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.0.attention.self.value.bias
2021-01-15 16:27:47,261 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.0.attention.self.value.weight
2021-01-15 16:27:47,261 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.0.intermediate.dense.bias
2021-01-15 16:27:47,261 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.0.intermediate.dense.weight
2021-01-15 16:27:47,261 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.0.output.LayerNorm.bias
2021-01-15 16:27:47,261 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.0.output.LayerNorm.weight
2021-01-15 16:27:47,262 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.0.output.dense.bias
2021-01-15 16:27:47,262 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.0.output.dense.weight
2021-01-15 16:27:47,262 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.1.attention.output.LayerNorm.bias
2021-01-15 16:27:47,262 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.1.attention.output.LayerNorm.weight
2021-01-15 16:27:47,262 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.1.attention.output.dense.bias
2021-01-15 16:27:47,262 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.1.attention.output.dense.weight
2021-01-15 16:27:47,262 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.1.attention.self.key.bias
2021-01-15 16:27:47,262 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.1.attention.self.key.weight
2021-01-15 16:27:47,262 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.1.attention.self.query.bias
2021-01-15 16:27:47,262 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.1.attention.self.query.weight
2021-01-15 16:27:47,262 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.1.attention.self.value.bias
2021-01-15 16:27:47,262 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.1.attention.self.value.weight
2021-01-15 16:27:47,262 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.1.intermediate.dense.bias
2021-01-15 16:27:47,262 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.1.intermediate.dense.weight
2021-01-15 16:27:47,262 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.1.output.LayerNorm.bias
2021-01-15 16:27:47,262 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.1.output.LayerNorm.weight
2021-01-15 16:27:47,262 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.1.output.dense.bias
2021-01-15 16:27:47,262 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.1.output.dense.weight
2021-01-15 16:27:47,262 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.10.attention.output.LayerNorm.bias
2021-01-15 16:27:47,262 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.10.attention.output.LayerNorm.weight
2021-01-15 16:27:47,262 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.10.attention.output.dense.bias
2021-01-15 16:27:47,262 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.10.attention.output.dense.weight
2021-01-15 16:27:47,262 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.10.attention.self.key.bias
2021-01-15 16:27:47,262 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.10.attention.self.key.weight
2021-01-15 16:27:47,262 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.10.attention.self.query.bias
2021-01-15 16:27:47,262 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.10.attention.self.query.weight
2021-01-15 16:27:47,262 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.10.attention.self.value.bias
2021-01-15 16:27:47,262 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.10.attention.self.value.weight
2021-01-15 16:27:47,262 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.10.intermediate.dense.bias
2021-01-15 16:27:47,262 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.10.intermediate.dense.weight
2021-01-15 16:27:47,262 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.10.output.LayerNorm.bias
2021-01-15 16:27:47,262 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.10.output.LayerNorm.weight
2021-01-15 16:27:47,262 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.10.output.dense.bias
2021-01-15 16:27:47,262 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.10.output.dense.weight
2021-01-15 16:27:47,262 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.11.attention.output.LayerNorm.bias
2021-01-15 16:27:47,263 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.11.attention.output.LayerNorm.weight
2021-01-15 16:27:47,263 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.11.attention.output.dense.bias
2021-01-15 16:27:47,263 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.11.attention.output.dense.weight
2021-01-15 16:27:47,263 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.11.attention.self.key.bias
2021-01-15 16:27:47,263 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.11.attention.self.key.weight
2021-01-15 16:27:47,263 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.11.attention.self.query.bias
2021-01-15 16:27:47,263 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.11.attention.self.query.weight
2021-01-15 16:27:47,263 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.11.attention.self.value.bias
2021-01-15 16:27:47,263 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.11.attention.self.value.weight
2021-01-15 16:27:47,263 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.11.intermediate.dense.bias
2021-01-15 16:27:47,263 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.11.intermediate.dense.weight
2021-01-15 16:27:47,263 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.11.output.LayerNorm.bias
2021-01-15 16:27:47,263 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.11.output.LayerNorm.weight
2021-01-15 16:27:47,263 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.11.output.dense.bias
2021-01-15 16:27:47,263 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.11.output.dense.weight
2021-01-15 16:27:47,263 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.2.attention.output.LayerNorm.bias
2021-01-15 16:27:47,263 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.2.attention.output.LayerNorm.weight
2021-01-15 16:27:47,263 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.2.attention.output.dense.bias
2021-01-15 16:27:47,263 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.2.attention.output.dense.weight
2021-01-15 16:27:47,263 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.2.attention.self.key.bias
2021-01-15 16:27:47,263 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.2.attention.self.key.weight
2021-01-15 16:27:47,263 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.2.attention.self.query.bias
2021-01-15 16:27:47,263 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.2.attention.self.query.weight
2021-01-15 16:27:47,263 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.2.attention.self.value.bias
2021-01-15 16:27:47,263 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.2.attention.self.value.weight
2021-01-15 16:27:47,263 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.2.intermediate.dense.bias
2021-01-15 16:27:47,263 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.2.intermediate.dense.weight
2021-01-15 16:27:47,263 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.2.output.LayerNorm.bias
2021-01-15 16:27:47,263 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.2.output.LayerNorm.weight
2021-01-15 16:27:47,263 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.2.output.dense.bias
2021-01-15 16:27:47,263 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.2.output.dense.weight
2021-01-15 16:27:47,263 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.3.attention.output.LayerNorm.bias
2021-01-15 16:27:47,263 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.3.attention.output.LayerNorm.weight
2021-01-15 16:27:47,263 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.3.attention.output.dense.bias
2021-01-15 16:27:47,264 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.3.attention.output.dense.weight
2021-01-15 16:27:47,264 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.3.attention.self.key.bias
2021-01-15 16:27:47,264 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.3.attention.self.key.weight
2021-01-15 16:27:47,264 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.3.attention.self.query.bias
2021-01-15 16:27:47,264 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.3.attention.self.query.weight
2021-01-15 16:27:47,264 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.3.attention.self.value.bias
2021-01-15 16:27:47,264 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.3.attention.self.value.weight
2021-01-15 16:27:47,264 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.3.intermediate.dense.bias
2021-01-15 16:27:47,264 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.3.intermediate.dense.weight
2021-01-15 16:27:47,264 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.3.output.LayerNorm.bias
2021-01-15 16:27:47,264 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.3.output.LayerNorm.weight
2021-01-15 16:27:47,264 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.3.output.dense.bias
2021-01-15 16:27:47,264 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.3.output.dense.weight
2021-01-15 16:27:47,264 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.4.attention.output.LayerNorm.bias
2021-01-15 16:27:47,264 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.4.attention.output.LayerNorm.weight
2021-01-15 16:27:47,264 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.4.attention.output.dense.bias
2021-01-15 16:27:47,264 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.4.attention.output.dense.weight
2021-01-15 16:27:47,264 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.4.attention.self.key.bias
2021-01-15 16:27:47,264 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.4.attention.self.key.weight
2021-01-15 16:27:47,264 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.4.attention.self.query.bias
2021-01-15 16:27:47,264 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.4.attention.self.query.weight
2021-01-15 16:27:47,264 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.4.attention.self.value.bias
2021-01-15 16:27:47,264 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.4.attention.self.value.weight
2021-01-15 16:27:47,264 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.4.intermediate.dense.bias
2021-01-15 16:27:47,264 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.4.intermediate.dense.weight
2021-01-15 16:27:47,264 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.4.output.LayerNorm.bias
2021-01-15 16:27:47,264 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.4.output.LayerNorm.weight
2021-01-15 16:27:47,264 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.4.output.dense.bias
2021-01-15 16:27:47,264 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.4.output.dense.weight
2021-01-15 16:27:47,264 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.5.attention.output.LayerNorm.bias
2021-01-15 16:27:47,264 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.5.attention.output.LayerNorm.weight
2021-01-15 16:27:47,264 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.5.attention.output.dense.bias
2021-01-15 16:27:47,264 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.5.attention.output.dense.weight
2021-01-15 16:27:47,264 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.5.attention.self.key.bias
2021-01-15 16:27:47,264 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.5.attention.self.key.weight
2021-01-15 16:27:47,265 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.5.attention.self.query.bias
2021-01-15 16:27:47,265 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.5.attention.self.query.weight
2021-01-15 16:27:47,265 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.5.attention.self.value.bias
2021-01-15 16:27:47,265 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.5.attention.self.value.weight
2021-01-15 16:27:47,265 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.5.intermediate.dense.bias
2021-01-15 16:27:47,265 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.5.intermediate.dense.weight
2021-01-15 16:27:47,265 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.5.output.LayerNorm.bias
2021-01-15 16:27:47,265 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.5.output.LayerNorm.weight
2021-01-15 16:27:47,265 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.5.output.dense.bias
2021-01-15 16:27:47,265 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.5.output.dense.weight
2021-01-15 16:27:47,265 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.6.attention.output.LayerNorm.bias
2021-01-15 16:27:47,265 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.6.attention.output.LayerNorm.weight
2021-01-15 16:27:47,265 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.6.attention.output.dense.bias
2021-01-15 16:27:47,265 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.6.attention.output.dense.weight
2021-01-15 16:27:47,265 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.6.attention.self.key.bias
2021-01-15 16:27:47,265 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.6.attention.self.key.weight
2021-01-15 16:27:47,265 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.6.attention.self.query.bias
2021-01-15 16:27:47,265 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.6.attention.self.query.weight
2021-01-15 16:27:47,265 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.6.attention.self.value.bias
2021-01-15 16:27:47,265 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.6.attention.self.value.weight
2021-01-15 16:27:47,265 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.6.intermediate.dense.bias
2021-01-15 16:27:47,265 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.6.intermediate.dense.weight
2021-01-15 16:27:47,265 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.6.output.LayerNorm.bias
2021-01-15 16:27:47,265 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.6.output.LayerNorm.weight
2021-01-15 16:27:47,265 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.6.output.dense.bias
2021-01-15 16:27:47,265 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.6.output.dense.weight
2021-01-15 16:27:47,265 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.7.attention.output.LayerNorm.bias
2021-01-15 16:27:47,265 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.7.attention.output.LayerNorm.weight
2021-01-15 16:27:47,265 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.7.attention.output.dense.bias
2021-01-15 16:27:47,265 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.7.attention.output.dense.weight
2021-01-15 16:27:47,265 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.7.attention.self.key.bias
2021-01-15 16:27:47,265 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.7.attention.self.key.weight
2021-01-15 16:27:47,265 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.7.attention.self.query.bias
2021-01-15 16:27:47,265 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.7.attention.self.query.weight
2021-01-15 16:27:47,265 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.7.attention.self.value.bias
2021-01-15 16:27:47,266 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.7.attention.self.value.weight
2021-01-15 16:27:47,266 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.7.intermediate.dense.bias
2021-01-15 16:27:47,266 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.7.intermediate.dense.weight
2021-01-15 16:27:47,266 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.7.output.LayerNorm.bias
2021-01-15 16:27:47,266 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.7.output.LayerNorm.weight
2021-01-15 16:27:47,266 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.7.output.dense.bias
2021-01-15 16:27:47,266 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.7.output.dense.weight
2021-01-15 16:27:47,266 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.8.attention.output.LayerNorm.bias
2021-01-15 16:27:47,266 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.8.attention.output.LayerNorm.weight
2021-01-15 16:27:47,266 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.8.attention.output.dense.bias
2021-01-15 16:27:47,266 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.8.attention.output.dense.weight
2021-01-15 16:27:47,266 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.8.attention.self.key.bias
2021-01-15 16:27:47,266 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.8.attention.self.key.weight
2021-01-15 16:27:47,266 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.8.attention.self.query.bias
2021-01-15 16:27:47,266 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.8.attention.self.query.weight
2021-01-15 16:27:47,266 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.8.attention.self.value.bias
2021-01-15 16:27:47,266 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.8.attention.self.value.weight
2021-01-15 16:27:47,266 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.8.intermediate.dense.bias
2021-01-15 16:27:47,266 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.8.intermediate.dense.weight
2021-01-15 16:27:47,266 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.8.output.LayerNorm.bias
2021-01-15 16:27:47,266 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.8.output.LayerNorm.weight
2021-01-15 16:27:47,266 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.8.output.dense.bias
2021-01-15 16:27:47,266 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.8.output.dense.weight
2021-01-15 16:27:47,266 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.9.attention.output.LayerNorm.bias
2021-01-15 16:27:47,266 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.9.attention.output.LayerNorm.weight
2021-01-15 16:27:47,266 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.9.attention.output.dense.bias
2021-01-15 16:27:47,266 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.9.attention.output.dense.weight
2021-01-15 16:27:47,266 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.9.attention.self.key.bias
2021-01-15 16:27:47,266 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.9.attention.self.key.weight
2021-01-15 16:27:47,266 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.9.attention.self.query.bias
2021-01-15 16:27:47,266 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.9.attention.self.query.weight
2021-01-15 16:27:47,267 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.9.attention.self.value.bias
2021-01-15 16:27:47,267 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.9.attention.self.value.weight
2021-01-15 16:27:47,267 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.9.intermediate.dense.bias
2021-01-15 16:27:47,267 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.9.intermediate.dense.weight
2021-01-15 16:27:47,267 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.9.output.LayerNorm.bias
2021-01-15 16:27:47,267 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.9.output.LayerNorm.weight
2021-01-15 16:27:47,267 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.9.output.dense.bias
2021-01-15 16:27:47,267 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.9.output.dense.weight
2021-01-15 16:27:47,267 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.pooler.dense.bias
2021-01-15 16:27:47,267 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.pooler.dense.weight
2021-01-15 16:27:47,268 - INFO - udify.models.udify_model - Total number of parameters: 212246786
2021-01-15 16:27:47,268 - INFO - udify.models.udify_model - Total number of trainable parameters: 212246786
Traceback (most recent call last):
  File "predict.py", line 59, in <module>
    util.predict_and_evaluate_model_with_archive(predictor, params, archive_dir, args.input_file,
  File "/home/fran/source/udify/udify/util.py", line 163, in predict_and_evaluate_model_with_archive
    predict_model_with_archive(predictor, params, archive, segment_file, pred_file, batch_size)
  File "/home/fran/source/udify/udify/util.py", line 142, in predict_model_with_archive
    archive = load_archive(archive,
  File "/home/fran/.local/lib/python3.8/site-packages/allennlp/models/archival.py", line 227, in load_archive
    model = Model.load(config.duplicate(),
  File "/home/fran/.local/lib/python3.8/site-packages/allennlp/models/model.py", line 327, in load
    return cls.by_name(model_type)._load(config, serialization_dir, weights_file, cuda_device)
  File "/home/fran/.local/lib/python3.8/site-packages/allennlp/models/model.py", line 275, in _load
    model_state = torch.load(weights_file, map_location=util.device_mapping(cuda_device))
  File "/home/fran/.local/lib/python3.8/site-packages/torch/serialization.py", line 529, in load
    return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
  File "/home/fran/.local/lib/python3.8/site-packages/torch/serialization.py", line 709, in _legacy_load
    deserialized_objects[key]._set_from_file(f, offset, f_should_read_directly)
RuntimeError: unexpected EOF, expected 316407350 more bytes. The file might be corrupted.
corrupted double-linked list
Avortat
fran@ipek:~/source/udify$

The MD5 sums of the two tarballs are:

$ md5sum *.tar.gz
facd2798e9786636ced131804ac67398  udify-bert.tar.gz
42aacc00e0ed6272b31ca7329055c108  udify-model.tar.gz
ftyers commented 3 years ago

I tried this on another machine and got a slightly different error:

(venv) fran@tlazolteotl /var/lib/home/fran/udify $ python predict.py --device -1 udify-model.tar.gz /home/fran/splits/test.0.conllu test.0.pred --eval_file logs/pred.json
2021-01-19 22:03:30,956 - INFO - allennlp.models.archival - loading archive file /mnt/partuuid-46caa556-c2c4-eb47-907a-5d2092050724/var/lib/home/fran/udify from cache at /mnt/partuuid-46caa556-c2c4-eb47-907a-5d2092050724/var/lib/home/fran/udify
2021-01-19 22:03:30,983 - INFO - allennlp.common.registrable - instantiating registered subclass udify_model of <class 'allennlp.models.model.Model'>
2021-01-19 22:03:30,983 - INFO - allennlp.common.params - vocabulary.type = default
2021-01-19 22:03:30,983 - INFO - allennlp.common.registrable - instantiating registered subclass default of <class 'allennlp.data.vocabulary.Vocabulary'>
2021-01-19 22:03:30,983 - INFO - allennlp.data.vocabulary - Loading token dictionary from /mnt/partuuid-46caa556-c2c4-eb47-907a-5d2092050724/var/lib/home/fran/udify/vocabulary.
2021-01-19 22:03:32,794 - INFO - allennlp.common.from_params - instantiating class <class 'allennlp.models.model.Model'> from params {'decoders': {'deps': {'arc_representation_dim': 768, 'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'pos_embed_dim': None, 'tag_representation_dim': 256, 'type': 'udify_dependency_decoder'}, 'feats': {'adaptive': True, 'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'label_smoothing': 0.03, 'task': 'feats', 'type': 'udify_tag_decoder'}, 'lemmas': {'adaptive': True, 'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'label_smoothing': 0.03, 'task': 'lemmas', 'type': 'udify_tag_decoder'}, 'upos': {'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'label_smoothing': 0.03, 'task': 'upos', 'type': 'udify_tag_decoder'}}, 'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'layer_dropout': 0.08, 'mix_embedding': 12, 'tasks': ['upos', 'feats', 'lemmas', 'deps'], 'text_field_embedder': {'allow_unmatched_keys': True, 'dropout': 0.4, 'embedder_to_indexer_map': {'bert': ['bert', 'bert-offsets']}, 'token_embedders': {'bert': {'bert_config': 'config/archive/bert-base-multilingual-cased/bert_config.json', 'combine_layers': 'all', 'dropout': 0.1, 'layer_dropout': 0.08, 'requires_grad': True, 'type': 'udify-bert-predictor'}}, 'type': 'udify_embedder'}, 'type': 'udify_model', 'word_dropout': 0.1} and extras {'vocab'}
2021-01-19 22:03:32,795 - INFO - allennlp.common.params - model.type = udify_model
2021-01-19 22:03:32,795 - INFO - allennlp.common.from_params - instantiating class <class 'udify.models.udify_model.UdifyModel'> from params {'decoders': {'deps': {'arc_representation_dim': 768, 'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'pos_embed_dim': None, 'tag_representation_dim': 256, 'type': 'udify_dependency_decoder'}, 'feats': {'adaptive': True, 'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'label_smoothing': 0.03, 'task': 'feats', 'type': 'udify_tag_decoder'}, 'lemmas': {'adaptive': True, 'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'label_smoothing': 0.03, 'task': 'lemmas', 'type': 'udify_tag_decoder'}, 'upos': {'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'label_smoothing': 0.03, 'task': 'upos', 'type': 'udify_tag_decoder'}}, 'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'layer_dropout': 0.08, 'mix_embedding': 12, 'tasks': ['upos', 'feats', 'lemmas', 'deps'], 'text_field_embedder': {'allow_unmatched_keys': True, 'dropout': 0.4, 'embedder_to_indexer_map': {'bert': ['bert', 'bert-offsets']}, 'token_embedders': {'bert': {'bert_config': 'config/archive/bert-base-multilingual-cased/bert_config.json', 'combine_layers': 'all', 'dropout': 0.1, 'layer_dropout': 0.08, 'requires_grad': True, 'type': 'udify-bert-predictor'}}, 'type': 'udify_embedder'}, 'word_dropout': 0.1} and extras {'vocab'}
2021-01-19 22:03:32,795 - INFO - allennlp.common.params - model.tasks = ['upos', 'feats', 'lemmas', 'deps']
2021-01-19 22:03:32,795 - INFO - allennlp.common.from_params - instantiating class <class 'allennlp.modules.text_field_embedders.text_field_embedder.TextFieldEmbedder'> from params {'allow_unmatched_keys': True, 'dropout': 0.4, 'embedder_to_indexer_map': {'bert': ['bert', 'bert-offsets']}, 'token_embedders': {'bert': {'bert_config': 'config/archive/bert-base-multilingual-cased/bert_config.json', 'combine_layers': 'all', 'dropout': 0.1, 'layer_dropout': 0.08, 'requires_grad': True, 'type': 'udify-bert-predictor'}}, 'type': 'udify_embedder'} and extras {'vocab'}
2021-01-19 22:03:32,795 - INFO - allennlp.common.params - model.text_field_embedder.type = udify_embedder
2021-01-19 22:03:32,795 - INFO - allennlp.common.params - model.text_field_embedder.allow_unmatched_keys = True
2021-01-19 22:03:32,795 - INFO - allennlp.common.params - model.text_field_embedder.dropout = 0.4
2021-01-19 22:03:32,795 - INFO - allennlp.common.params - model.text_field_embedder.output_dim = None
2021-01-19 22:03:32,795 - INFO - allennlp.common.params - model.text_field_embedder.sum_embeddings = None
2021-01-19 22:03:32,796 - INFO - allennlp.common.from_params - instantiating class <class 'allennlp.modules.token_embedders.token_embedder.TokenEmbedder'> from params {'bert_config': 'config/archive/bert-base-multilingual-cased/bert_config.json', 'combine_layers': 'all', 'dropout': 0.1, 'layer_dropout': 0.08, 'requires_grad': True, 'type': 'udify-bert-predictor'} and extras {'vocab'}
2021-01-19 22:03:32,849 - INFO - allennlp.common.params - model.text_field_embedder.token_embedders.bert.type = udify-bert-predictor
2021-01-19 22:03:32,850 - INFO - allennlp.common.from_params - instantiating class <class 'udify.modules.bert_pretrained.UdifyPredictionBertEmbedder'> from params {'bert_config': 'config/archive/bert-base-multilingual-cased/bert_config.json', 'combine_layers': 'all', 'dropout': 0.1, 'layer_dropout': 0.08, 'requires_grad': True} and extras {'vocab'}
2021-01-19 22:03:32,850 - INFO - allennlp.common.params - model.text_field_embedder.token_embedders.bert.bert_config = config/archive/bert-base-multilingual-cased/bert_config.json
2021-01-19 22:03:32,850 - INFO - allennlp.common.params - model.text_field_embedder.token_embedders.bert.requires_grad = True
2021-01-19 22:03:32,850 - INFO - allennlp.common.params - model.text_field_embedder.token_embedders.bert.dropout = 0.1
2021-01-19 22:03:32,850 - INFO - allennlp.common.params - model.text_field_embedder.token_embedders.bert.layer_dropout = 0.08
2021-01-19 22:03:32,850 - INFO - allennlp.common.params - model.text_field_embedder.token_embedders.bert.combine_layers = all
2021-01-19 22:03:34,489 - INFO - allennlp.common.from_params - instantiating class <class 'allennlp.modules.seq2seq_encoders.seq2seq_encoder.Seq2SeqEncoder'> from params {'input_dim': 768, 'type': 'pass_through'} and extras {'vocab'}
2021-01-19 22:03:34,489 - INFO - allennlp.common.params - model.encoder.type = pass_through
2021-01-19 22:03:34,489 - INFO - allennlp.common.from_params - instantiating class <class 'allennlp.modules.seq2seq_encoders.pass_through_encoder.PassThroughEncoder'> from params {'input_dim': 768} and extras {'vocab'}
2021-01-19 22:03:34,490 - INFO - allennlp.common.params - model.encoder.input_dim = 768
2021-01-19 22:03:34,490 - INFO - allennlp.common.from_params - instantiating class <class 'allennlp.models.model.Model'> from params {'arc_representation_dim': 768, 'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'pos_embed_dim': None, 'tag_representation_dim': 256, 'type': 'udify_dependency_decoder'} and extras {'vocab'}
2021-01-19 22:03:34,490 - INFO - allennlp.common.params - model.decoders.deps.type = udify_dependency_decoder
2021-01-19 22:03:34,490 - INFO - allennlp.common.from_params - instantiating class <class 'udify.models.dependency_decoder.DependencyDecoder'> from params {'arc_representation_dim': 768, 'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'pos_embed_dim': None, 'tag_representation_dim': 256} and extras {'vocab'}
2021-01-19 22:03:34,490 - INFO - allennlp.common.from_params - instantiating class <class 'allennlp.modules.seq2seq_encoders.seq2seq_encoder.Seq2SeqEncoder'> from params {'input_dim': 768, 'type': 'pass_through'} and extras {'vocab'}
2021-01-19 22:03:34,490 - INFO - allennlp.common.params - model.decoders.deps.encoder.type = pass_through
2021-01-19 22:03:34,490 - INFO - allennlp.common.from_params - instantiating class <class 'allennlp.modules.seq2seq_encoders.pass_through_encoder.PassThroughEncoder'> from params {'input_dim': 768} and extras {'vocab'}
2021-01-19 22:03:34,491 - INFO - allennlp.common.params - model.decoders.deps.encoder.input_dim = 768
2021-01-19 22:03:34,491 - INFO - allennlp.common.params - model.decoders.deps.tag_representation_dim = 256
2021-01-19 22:03:34,491 - INFO - allennlp.common.params - model.decoders.deps.arc_representation_dim = 768
2021-01-19 22:03:34,491 - INFO - allennlp.common.params - model.decoders.deps.pos_embed_dim = None
2021-01-19 22:03:34,491 - INFO - allennlp.common.params - model.decoders.deps.use_mst_decoding_for_validation = True
2021-01-19 22:03:34,491 - INFO - allennlp.common.params - model.decoders.deps.dropout = 0.5
2021-01-19 22:03:34,491 - INFO - allennlp.common.registrable - instantiating registered subclass elu of <class 'allennlp.nn.activations.Activation'>
2021-01-19 22:03:34,495 - INFO - allennlp.common.registrable - instantiating registered subclass linear of <class 'allennlp.nn.activations.Activation'>
2021-01-19 22:03:34,497 - INFO - allennlp.common.registrable - instantiating registered subclass elu of <class 'allennlp.nn.activations.Activation'>
2021-01-19 22:03:34,572 - INFO - udify.models.dependency_decoder - Found POS tags corresponding to the following punctuation : {}. Ignoring words with these POS tags for evaluation.
2021-01-19 22:03:34,573 - INFO - allennlp.nn.initializers - Initializing parameters
2021-01-19 22:03:34,573 - INFO - allennlp.nn.initializers - Done initializing parameters; the following parameters are using their default initialization from their code
2021-01-19 22:03:34,573 - INFO - allennlp.nn.initializers -    _head_sentinel
2021-01-19 22:03:34,573 - INFO - allennlp.nn.initializers -    arc_attention._bias
2021-01-19 22:03:34,573 - INFO - allennlp.nn.initializers -    arc_attention._weight_matrix
2021-01-19 22:03:34,573 - INFO - allennlp.nn.initializers -    child_arc_feedforward._linear_layers.0.bias
2021-01-19 22:03:34,573 - INFO - allennlp.nn.initializers -    child_arc_feedforward._linear_layers.0.weight
2021-01-19 22:03:34,573 - INFO - allennlp.nn.initializers -    child_tag_feedforward._linear_layers.0.bias
2021-01-19 22:03:34,573 - INFO - allennlp.nn.initializers -    child_tag_feedforward._linear_layers.0.weight
2021-01-19 22:03:34,573 - INFO - allennlp.nn.initializers -    head_arc_feedforward._linear_layers.0.bias
2021-01-19 22:03:34,573 - INFO - allennlp.nn.initializers -    head_arc_feedforward._linear_layers.0.weight
2021-01-19 22:03:34,573 - INFO - allennlp.nn.initializers -    head_tag_feedforward._linear_layers.0.bias
2021-01-19 22:03:34,573 - INFO - allennlp.nn.initializers -    head_tag_feedforward._linear_layers.0.weight
2021-01-19 22:03:34,573 - INFO - allennlp.nn.initializers -    tag_bilinear.bias
2021-01-19 22:03:34,573 - INFO - allennlp.nn.initializers -    tag_bilinear.weight
2021-01-19 22:03:34,574 - INFO - allennlp.common.from_params - instantiating class <class 'allennlp.models.model.Model'> from params {'adaptive': True, 'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'label_smoothing': 0.03, 'task': 'feats', 'type': 'udify_tag_decoder'} and extras {'vocab'}
2021-01-19 22:03:34,574 - INFO - allennlp.common.params - model.decoders.feats.type = udify_tag_decoder
2021-01-19 22:03:34,574 - INFO - allennlp.common.from_params - instantiating class <class 'udify.models.tag_decoder.TagDecoder'> from params {'adaptive': True, 'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'label_smoothing': 0.03, 'task': 'feats'} and extras {'vocab'}
2021-01-19 22:03:34,574 - INFO - allennlp.common.params - model.decoders.feats.task = feats
2021-01-19 22:03:34,574 - INFO - allennlp.common.from_params - instantiating class <class 'allennlp.modules.seq2seq_encoders.seq2seq_encoder.Seq2SeqEncoder'> from params {'input_dim': 768, 'type': 'pass_through'} and extras {'vocab'}
2021-01-19 22:03:34,574 - INFO - allennlp.common.params - model.decoders.feats.encoder.type = pass_through
2021-01-19 22:03:34,574 - INFO - allennlp.common.from_params - instantiating class <class 'allennlp.modules.seq2seq_encoders.pass_through_encoder.PassThroughEncoder'> from params {'input_dim': 768} and extras {'vocab'}
2021-01-19 22:03:34,574 - INFO - allennlp.common.params - model.decoders.feats.encoder.input_dim = 768
2021-01-19 22:03:34,575 - INFO - allennlp.common.params - model.decoders.feats.label_smoothing = 0.03
2021-01-19 22:03:34,575 - INFO - allennlp.common.params - model.decoders.feats.dropout = 0.5
2021-01-19 22:03:34,575 - INFO - allennlp.common.params - model.decoders.feats.adaptive = True
2021-01-19 22:03:34,575 - INFO - allennlp.common.params - model.decoders.feats.features = None
2021-01-19 22:03:34,588 - INFO - allennlp.nn.initializers - Initializing parameters
2021-01-19 22:03:34,588 - INFO - allennlp.nn.initializers - Done initializing parameters; the following parameters are using their default initialization from their code
2021-01-19 22:03:34,588 - INFO - allennlp.nn.initializers -    task_output.head.weight
2021-01-19 22:03:34,588 - INFO - allennlp.nn.initializers -    task_output.tail.0.0.weight
2021-01-19 22:03:34,588 - INFO - allennlp.nn.initializers -    task_output.tail.0.1.weight
2021-01-19 22:03:34,588 - INFO - allennlp.nn.initializers -    task_output.tail.1.0.weight
2021-01-19 22:03:34,588 - INFO - allennlp.nn.initializers -    task_output.tail.1.1.weight
2021-01-19 22:03:34,588 - INFO - allennlp.common.from_params - instantiating class <class 'allennlp.models.model.Model'> from params {'adaptive': True, 'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'label_smoothing': 0.03, 'task': 'lemmas', 'type': 'udify_tag_decoder'} and extras {'vocab'}
2021-01-19 22:03:34,588 - INFO - allennlp.common.params - model.decoders.lemmas.type = udify_tag_decoder
2021-01-19 22:03:34,589 - INFO - allennlp.common.from_params - instantiating class <class 'udify.models.tag_decoder.TagDecoder'> from params {'adaptive': True, 'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'label_smoothing': 0.03, 'task': 'lemmas'} and extras {'vocab'}
2021-01-19 22:03:34,589 - INFO - allennlp.common.params - model.decoders.lemmas.task = lemmas
2021-01-19 22:03:34,589 - INFO - allennlp.common.from_params - instantiating class <class 'allennlp.modules.seq2seq_encoders.seq2seq_encoder.Seq2SeqEncoder'> from params {'input_dim': 768, 'type': 'pass_through'} and extras {'vocab'}
2021-01-19 22:03:34,589 - INFO - allennlp.common.params - model.decoders.lemmas.encoder.type = pass_through
2021-01-19 22:03:34,589 - INFO - allennlp.common.from_params - instantiating class <class 'allennlp.modules.seq2seq_encoders.pass_through_encoder.PassThroughEncoder'> from params {'input_dim': 768} and extras {'vocab'}
2021-01-19 22:03:34,589 - INFO - allennlp.common.params - model.decoders.lemmas.encoder.input_dim = 768
2021-01-19 22:03:34,589 - INFO - allennlp.common.params - model.decoders.lemmas.label_smoothing = 0.03
2021-01-19 22:03:34,589 - INFO - allennlp.common.params - model.decoders.lemmas.dropout = 0.5
2021-01-19 22:03:34,589 - INFO - allennlp.common.params - model.decoders.lemmas.adaptive = True
2021-01-19 22:03:34,590 - INFO - allennlp.common.params - model.decoders.lemmas.features = None
2021-01-19 22:03:34,647 - INFO - allennlp.nn.initializers - Initializing parameters
2021-01-19 22:03:34,647 - INFO - allennlp.nn.initializers - Done initializing parameters; the following parameters are using their default initialization from their code
2021-01-19 22:03:34,647 - INFO - allennlp.nn.initializers -    task_output.head.weight
2021-01-19 22:03:34,648 - INFO - allennlp.nn.initializers -    task_output.tail.0.0.weight
2021-01-19 22:03:34,648 - INFO - allennlp.nn.initializers -    task_output.tail.0.1.weight
2021-01-19 22:03:34,648 - INFO - allennlp.nn.initializers -    task_output.tail.1.0.weight
2021-01-19 22:03:34,648 - INFO - allennlp.nn.initializers -    task_output.tail.1.1.weight
2021-01-19 22:03:34,648 - INFO - allennlp.common.from_params - instantiating class <class 'allennlp.models.model.Model'> from params {'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'label_smoothing': 0.03, 'task': 'upos', 'type': 'udify_tag_decoder'} and extras {'vocab'}
2021-01-19 22:03:34,648 - INFO - allennlp.common.params - model.decoders.upos.type = udify_tag_decoder
2021-01-19 22:03:34,648 - INFO - allennlp.common.from_params - instantiating class <class 'udify.models.tag_decoder.TagDecoder'> from params {'dropout': 0.5, 'encoder': {'input_dim': 768, 'type': 'pass_through'}, 'label_smoothing': 0.03, 'task': 'upos'} and extras {'vocab'}
2021-01-19 22:03:34,648 - INFO - allennlp.common.params - model.decoders.upos.task = upos
2021-01-19 22:03:34,648 - INFO - allennlp.common.from_params - instantiating class <class 'allennlp.modules.seq2seq_encoders.seq2seq_encoder.Seq2SeqEncoder'> from params {'input_dim': 768, 'type': 'pass_through'} and extras {'vocab'}
2021-01-19 22:03:34,648 - INFO - allennlp.common.params - model.decoders.upos.encoder.type = pass_through
2021-01-19 22:03:34,649 - INFO - allennlp.common.from_params - instantiating class <class 'allennlp.modules.seq2seq_encoders.pass_through_encoder.PassThroughEncoder'> from params {'input_dim': 768} and extras {'vocab'}
2021-01-19 22:03:34,649 - INFO - allennlp.common.params - model.decoders.upos.encoder.input_dim = 768
2021-01-19 22:03:34,649 - INFO - allennlp.common.params - model.decoders.upos.label_smoothing = 0.03
2021-01-19 22:03:34,649 - INFO - allennlp.common.params - model.decoders.upos.dropout = 0.5
2021-01-19 22:03:34,649 - INFO - allennlp.common.params - model.decoders.upos.adaptive = False
2021-01-19 22:03:34,649 - INFO - allennlp.common.params - model.decoders.upos.features = None
2021-01-19 22:03:34,650 - INFO - allennlp.nn.initializers - Initializing parameters
2021-01-19 22:03:34,650 - INFO - allennlp.nn.initializers - Done initializing parameters; the following parameters are using their default initialization from their code
2021-01-19 22:03:34,650 - INFO - allennlp.nn.initializers -    task_output._module.bias
2021-01-19 22:03:34,650 - INFO - allennlp.nn.initializers -    task_output._module.weight
2021-01-19 22:03:34,650 - INFO - allennlp.common.params - model.dropout = 0.5
2021-01-19 22:03:34,650 - INFO - allennlp.common.params - model.word_dropout = 0.1
2021-01-19 22:03:34,650 - INFO - allennlp.common.params - model.mix_embedding = 12
2021-01-19 22:03:34,650 - INFO - allennlp.common.params - model.layer_dropout = 0.08
2021-01-19 22:03:34,650 - INFO - pytorch_pretrained_bert.tokenization - loading vocabulary file config/archive/bert-base-multilingual-cased/vocab.txt
2021-01-19 22:03:34,799 - INFO - allennlp.nn.initializers - Initializing parameters
2021-01-19 22:03:34,800 - INFO - allennlp.nn.initializers - Done initializing parameters; the following parameters are using their default initialization from their code
2021-01-19 22:03:34,800 - INFO - allennlp.nn.initializers -    decoders.deps._head_sentinel
2021-01-19 22:03:34,800 - INFO - allennlp.nn.initializers -    decoders.deps.arc_attention._bias
2021-01-19 22:03:34,800 - INFO - allennlp.nn.initializers -    decoders.deps.arc_attention._weight_matrix
2021-01-19 22:03:34,801 - INFO - allennlp.nn.initializers -    decoders.deps.child_arc_feedforward._linear_layers.0.bias
2021-01-19 22:03:34,801 - INFO - allennlp.nn.initializers -    decoders.deps.child_arc_feedforward._linear_layers.0.weight
2021-01-19 22:03:34,801 - INFO - allennlp.nn.initializers -    decoders.deps.child_tag_feedforward._linear_layers.0.bias
2021-01-19 22:03:34,801 - INFO - allennlp.nn.initializers -    decoders.deps.child_tag_feedforward._linear_layers.0.weight
2021-01-19 22:03:34,801 - INFO - allennlp.nn.initializers -    decoders.deps.head_arc_feedforward._linear_layers.0.bias
2021-01-19 22:03:34,801 - INFO - allennlp.nn.initializers -    decoders.deps.head_arc_feedforward._linear_layers.0.weight
2021-01-19 22:03:34,801 - INFO - allennlp.nn.initializers -    decoders.deps.head_tag_feedforward._linear_layers.0.bias
2021-01-19 22:03:34,801 - INFO - allennlp.nn.initializers -    decoders.deps.head_tag_feedforward._linear_layers.0.weight
2021-01-19 22:03:34,801 - INFO - allennlp.nn.initializers -    decoders.deps.tag_bilinear.bias
2021-01-19 22:03:34,801 - INFO - allennlp.nn.initializers -    decoders.deps.tag_bilinear.weight
2021-01-19 22:03:34,801 - INFO - allennlp.nn.initializers -    decoders.feats.task_output.head.weight
2021-01-19 22:03:34,801 - INFO - allennlp.nn.initializers -    decoders.feats.task_output.tail.0.0.weight
2021-01-19 22:03:34,801 - INFO - allennlp.nn.initializers -    decoders.feats.task_output.tail.0.1.weight
2021-01-19 22:03:34,801 - INFO - allennlp.nn.initializers -    decoders.feats.task_output.tail.1.0.weight
2021-01-19 22:03:34,801 - INFO - allennlp.nn.initializers -    decoders.feats.task_output.tail.1.1.weight
2021-01-19 22:03:34,801 - INFO - allennlp.nn.initializers -    decoders.lemmas.task_output.head.weight
2021-01-19 22:03:34,801 - INFO - allennlp.nn.initializers -    decoders.lemmas.task_output.tail.0.0.weight
2021-01-19 22:03:34,801 - INFO - allennlp.nn.initializers -    decoders.lemmas.task_output.tail.0.1.weight
2021-01-19 22:03:34,801 - INFO - allennlp.nn.initializers -    decoders.lemmas.task_output.tail.1.0.weight
2021-01-19 22:03:34,801 - INFO - allennlp.nn.initializers -    decoders.lemmas.task_output.tail.1.1.weight
2021-01-19 22:03:34,801 - INFO - allennlp.nn.initializers -    decoders.upos.task_output._module.bias
2021-01-19 22:03:34,802 - INFO - allennlp.nn.initializers -    decoders.upos.task_output._module.weight
2021-01-19 22:03:34,802 - INFO - allennlp.nn.initializers -    scalar_mix.deps.gamma
2021-01-19 22:03:34,802 - INFO - allennlp.nn.initializers -    scalar_mix.deps.scalar_parameters.0
2021-01-19 22:03:34,802 - INFO - allennlp.nn.initializers -    scalar_mix.deps.scalar_parameters.1
2021-01-19 22:03:34,802 - INFO - allennlp.nn.initializers -    scalar_mix.deps.scalar_parameters.10
2021-01-19 22:03:34,802 - INFO - allennlp.nn.initializers -    scalar_mix.deps.scalar_parameters.11
2021-01-19 22:03:34,802 - INFO - allennlp.nn.initializers -    scalar_mix.deps.scalar_parameters.2
2021-01-19 22:03:34,802 - INFO - allennlp.nn.initializers -    scalar_mix.deps.scalar_parameters.3
2021-01-19 22:03:34,802 - INFO - allennlp.nn.initializers -    scalar_mix.deps.scalar_parameters.4
2021-01-19 22:03:34,802 - INFO - allennlp.nn.initializers -    scalar_mix.deps.scalar_parameters.5
2021-01-19 22:03:34,802 - INFO - allennlp.nn.initializers -    scalar_mix.deps.scalar_parameters.6
2021-01-19 22:03:34,802 - INFO - allennlp.nn.initializers -    scalar_mix.deps.scalar_parameters.7
2021-01-19 22:03:34,802 - INFO - allennlp.nn.initializers -    scalar_mix.deps.scalar_parameters.8
2021-01-19 22:03:34,802 - INFO - allennlp.nn.initializers -    scalar_mix.deps.scalar_parameters.9
2021-01-19 22:03:34,802 - INFO - allennlp.nn.initializers -    scalar_mix.feats.gamma
2021-01-19 22:03:34,802 - INFO - allennlp.nn.initializers -    scalar_mix.feats.scalar_parameters.0
2021-01-19 22:03:34,802 - INFO - allennlp.nn.initializers -    scalar_mix.feats.scalar_parameters.1
2021-01-19 22:03:34,802 - INFO - allennlp.nn.initializers -    scalar_mix.feats.scalar_parameters.10
2021-01-19 22:03:34,802 - INFO - allennlp.nn.initializers -    scalar_mix.feats.scalar_parameters.11
2021-01-19 22:03:34,802 - INFO - allennlp.nn.initializers -    scalar_mix.feats.scalar_parameters.2
2021-01-19 22:03:34,803 - INFO - allennlp.nn.initializers -    scalar_mix.feats.scalar_parameters.3
2021-01-19 22:03:34,803 - INFO - allennlp.nn.initializers -    scalar_mix.feats.scalar_parameters.4
2021-01-19 22:03:34,803 - INFO - allennlp.nn.initializers -    scalar_mix.feats.scalar_parameters.5
2021-01-19 22:03:34,803 - INFO - allennlp.nn.initializers -    scalar_mix.feats.scalar_parameters.6
2021-01-19 22:03:34,803 - INFO - allennlp.nn.initializers -    scalar_mix.feats.scalar_parameters.7
2021-01-19 22:03:34,803 - INFO - allennlp.nn.initializers -    scalar_mix.feats.scalar_parameters.8
2021-01-19 22:03:34,803 - INFO - allennlp.nn.initializers -    scalar_mix.feats.scalar_parameters.9
2021-01-19 22:03:34,803 - INFO - allennlp.nn.initializers -    scalar_mix.lemmas.gamma
2021-01-19 22:03:34,803 - INFO - allennlp.nn.initializers -    scalar_mix.lemmas.scalar_parameters.0
2021-01-19 22:03:34,803 - INFO - allennlp.nn.initializers -    scalar_mix.lemmas.scalar_parameters.1
2021-01-19 22:03:34,803 - INFO - allennlp.nn.initializers -    scalar_mix.lemmas.scalar_parameters.10
2021-01-19 22:03:34,803 - INFO - allennlp.nn.initializers -    scalar_mix.lemmas.scalar_parameters.11
2021-01-19 22:03:34,803 - INFO - allennlp.nn.initializers -    scalar_mix.lemmas.scalar_parameters.2
2021-01-19 22:03:34,803 - INFO - allennlp.nn.initializers -    scalar_mix.lemmas.scalar_parameters.3
2021-01-19 22:03:34,803 - INFO - allennlp.nn.initializers -    scalar_mix.lemmas.scalar_parameters.4
2021-01-19 22:03:34,803 - INFO - allennlp.nn.initializers -    scalar_mix.lemmas.scalar_parameters.5
2021-01-19 22:03:34,803 - INFO - allennlp.nn.initializers -    scalar_mix.lemmas.scalar_parameters.6
2021-01-19 22:03:34,803 - INFO - allennlp.nn.initializers -    scalar_mix.lemmas.scalar_parameters.7
2021-01-19 22:03:34,803 - INFO - allennlp.nn.initializers -    scalar_mix.lemmas.scalar_parameters.8
2021-01-19 22:03:34,803 - INFO - allennlp.nn.initializers -    scalar_mix.lemmas.scalar_parameters.9
2021-01-19 22:03:34,804 - INFO - allennlp.nn.initializers -    scalar_mix.upos.gamma
2021-01-19 22:03:34,804 - INFO - allennlp.nn.initializers -    scalar_mix.upos.scalar_parameters.0
2021-01-19 22:03:34,804 - INFO - allennlp.nn.initializers -    scalar_mix.upos.scalar_parameters.1
2021-01-19 22:03:34,804 - INFO - allennlp.nn.initializers -    scalar_mix.upos.scalar_parameters.10
2021-01-19 22:03:34,804 - INFO - allennlp.nn.initializers -    scalar_mix.upos.scalar_parameters.11
2021-01-19 22:03:34,804 - INFO - allennlp.nn.initializers -    scalar_mix.upos.scalar_parameters.2
2021-01-19 22:03:34,804 - INFO - allennlp.nn.initializers -    scalar_mix.upos.scalar_parameters.3
2021-01-19 22:03:34,804 - INFO - allennlp.nn.initializers -    scalar_mix.upos.scalar_parameters.4
2021-01-19 22:03:34,804 - INFO - allennlp.nn.initializers -    scalar_mix.upos.scalar_parameters.5
2021-01-19 22:03:34,804 - INFO - allennlp.nn.initializers -    scalar_mix.upos.scalar_parameters.6
2021-01-19 22:03:34,804 - INFO - allennlp.nn.initializers -    scalar_mix.upos.scalar_parameters.7
2021-01-19 22:03:34,804 - INFO - allennlp.nn.initializers -    scalar_mix.upos.scalar_parameters.8
2021-01-19 22:03:34,804 - INFO - allennlp.nn.initializers -    scalar_mix.upos.scalar_parameters.9
2021-01-19 22:03:34,804 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.embeddings.LayerNorm.bias
2021-01-19 22:03:34,804 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.embeddings.LayerNorm.weight
2021-01-19 22:03:34,804 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.embeddings.position_embeddings.weight
2021-01-19 22:03:34,804 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.embeddings.token_type_embeddings.weight
2021-01-19 22:03:34,804 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.embeddings.word_embeddings.weight
2021-01-19 22:03:34,804 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.0.attention.output.LayerNorm.bias
2021-01-19 22:03:34,804 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.0.attention.output.LayerNorm.weight
2021-01-19 22:03:34,804 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.0.attention.output.dense.bias
2021-01-19 22:03:34,805 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.0.attention.output.dense.weight
2021-01-19 22:03:34,805 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.0.attention.self.key.bias
2021-01-19 22:03:34,805 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.0.attention.self.key.weight
2021-01-19 22:03:34,805 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.0.attention.self.query.bias
2021-01-19 22:03:34,805 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.0.attention.self.query.weight
2021-01-19 22:03:34,805 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.0.attention.self.value.bias
2021-01-19 22:03:34,805 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.0.attention.self.value.weight
2021-01-19 22:03:34,805 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.0.intermediate.dense.bias
2021-01-19 22:03:34,805 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.0.intermediate.dense.weight
2021-01-19 22:03:34,805 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.0.output.LayerNorm.bias
2021-01-19 22:03:34,805 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.0.output.LayerNorm.weight
2021-01-19 22:03:34,805 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.0.output.dense.bias
2021-01-19 22:03:34,805 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.0.output.dense.weight
2021-01-19 22:03:34,805 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.1.attention.output.LayerNorm.bias
2021-01-19 22:03:34,805 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.1.attention.output.LayerNorm.weight
2021-01-19 22:03:34,805 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.1.attention.output.dense.bias
2021-01-19 22:03:34,805 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.1.attention.output.dense.weight
2021-01-19 22:03:34,805 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.1.attention.self.key.bias
2021-01-19 22:03:34,805 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.1.attention.self.key.weight
2021-01-19 22:03:34,805 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.1.attention.self.query.bias
2021-01-19 22:03:34,805 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.1.attention.self.query.weight
2021-01-19 22:03:34,806 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.1.attention.self.value.bias
2021-01-19 22:03:34,806 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.1.attention.self.value.weight
2021-01-19 22:03:34,806 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.1.intermediate.dense.bias
2021-01-19 22:03:34,806 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.1.intermediate.dense.weight
2021-01-19 22:03:34,806 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.1.output.LayerNorm.bias
2021-01-19 22:03:34,806 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.1.output.LayerNorm.weight
2021-01-19 22:03:34,806 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.1.output.dense.bias
2021-01-19 22:03:34,806 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.1.output.dense.weight
2021-01-19 22:03:34,806 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.10.attention.output.LayerNorm.bias
2021-01-19 22:03:34,806 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.10.attention.output.LayerNorm.weight
2021-01-19 22:03:34,806 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.10.attention.output.dense.bias
2021-01-19 22:03:34,806 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.10.attention.output.dense.weight
2021-01-19 22:03:34,806 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.10.attention.self.key.bias
2021-01-19 22:03:34,806 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.10.attention.self.key.weight
2021-01-19 22:03:34,806 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.10.attention.self.query.bias
2021-01-19 22:03:34,806 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.10.attention.self.query.weight
2021-01-19 22:03:34,806 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.10.attention.self.value.bias
2021-01-19 22:03:34,806 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.10.attention.self.value.weight
2021-01-19 22:03:34,806 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.10.intermediate.dense.bias
2021-01-19 22:03:34,806 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.10.intermediate.dense.weight
2021-01-19 22:03:34,807 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.10.output.LayerNorm.bias
2021-01-19 22:03:34,807 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.10.output.LayerNorm.weight
2021-01-19 22:03:34,807 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.10.output.dense.bias
2021-01-19 22:03:34,807 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.10.output.dense.weight
2021-01-19 22:03:34,807 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.11.attention.output.LayerNorm.bias
2021-01-19 22:03:34,807 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.11.attention.output.LayerNorm.weight
2021-01-19 22:03:34,807 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.11.attention.output.dense.bias
2021-01-19 22:03:34,807 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.11.attention.output.dense.weight
2021-01-19 22:03:34,807 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.11.attention.self.key.bias
2021-01-19 22:03:34,807 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.11.attention.self.key.weight
2021-01-19 22:03:34,807 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.11.attention.self.query.bias
2021-01-19 22:03:34,807 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.11.attention.self.query.weight
2021-01-19 22:03:34,807 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.11.attention.self.value.bias
2021-01-19 22:03:34,807 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.11.attention.self.value.weight
2021-01-19 22:03:34,807 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.11.intermediate.dense.bias
2021-01-19 22:03:34,807 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.11.intermediate.dense.weight
2021-01-19 22:03:34,807 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.11.output.LayerNorm.bias
2021-01-19 22:03:34,807 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.11.output.LayerNorm.weight
2021-01-19 22:03:34,807 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.11.output.dense.bias
2021-01-19 22:03:34,807 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.11.output.dense.weight
2021-01-19 22:03:34,807 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.2.attention.output.LayerNorm.bias
2021-01-19 22:03:34,808 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.2.attention.output.LayerNorm.weight
2021-01-19 22:03:34,808 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.2.attention.output.dense.bias
2021-01-19 22:03:34,808 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.2.attention.output.dense.weight
2021-01-19 22:03:34,808 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.2.attention.self.key.bias
2021-01-19 22:03:34,808 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.2.attention.self.key.weight
2021-01-19 22:03:34,808 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.2.attention.self.query.bias
2021-01-19 22:03:34,808 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.2.attention.self.query.weight
2021-01-19 22:03:34,808 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.2.attention.self.value.bias
2021-01-19 22:03:34,808 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.2.attention.self.value.weight
2021-01-19 22:03:34,808 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.2.intermediate.dense.bias
2021-01-19 22:03:34,808 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.2.intermediate.dense.weight
2021-01-19 22:03:34,808 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.2.output.LayerNorm.bias
2021-01-19 22:03:34,808 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.2.output.LayerNorm.weight
2021-01-19 22:03:34,808 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.2.output.dense.bias
2021-01-19 22:03:34,808 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.2.output.dense.weight
2021-01-19 22:03:34,808 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.3.attention.output.LayerNorm.bias
2021-01-19 22:03:34,808 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.3.attention.output.LayerNorm.weight
2021-01-19 22:03:34,808 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.3.attention.output.dense.bias
2021-01-19 22:03:34,808 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.3.attention.output.dense.weight
2021-01-19 22:03:34,808 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.3.attention.self.key.bias
2021-01-19 22:03:34,808 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.3.attention.self.key.weight
2021-01-19 22:03:34,809 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.3.attention.self.query.bias
2021-01-19 22:03:34,809 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.3.attention.self.query.weight
2021-01-19 22:03:34,809 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.3.attention.self.value.bias
2021-01-19 22:03:34,809 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.3.attention.self.value.weight
2021-01-19 22:03:34,809 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.3.intermediate.dense.bias
2021-01-19 22:03:34,809 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.3.intermediate.dense.weight
2021-01-19 22:03:34,809 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.3.output.LayerNorm.bias
2021-01-19 22:03:34,809 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.3.output.LayerNorm.weight
2021-01-19 22:03:34,809 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.3.output.dense.bias
2021-01-19 22:03:34,809 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.3.output.dense.weight
2021-01-19 22:03:34,809 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.4.attention.output.LayerNorm.bias
2021-01-19 22:03:34,809 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.4.attention.output.LayerNorm.weight
2021-01-19 22:03:34,809 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.4.attention.output.dense.bias
2021-01-19 22:03:34,809 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.4.attention.output.dense.weight
2021-01-19 22:03:34,809 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.4.attention.self.key.bias
2021-01-19 22:03:34,809 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.4.attention.self.key.weight
2021-01-19 22:03:34,809 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.4.attention.self.query.bias
2021-01-19 22:03:34,809 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.4.attention.self.query.weight
2021-01-19 22:03:34,809 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.4.attention.self.value.bias
2021-01-19 22:03:34,809 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.4.attention.self.value.weight
2021-01-19 22:03:34,809 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.4.intermediate.dense.bias
2021-01-19 22:03:34,810 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.4.intermediate.dense.weight
2021-01-19 22:03:34,810 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.4.output.LayerNorm.bias
2021-01-19 22:03:34,810 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.4.output.LayerNorm.weight
2021-01-19 22:03:34,810 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.4.output.dense.bias
2021-01-19 22:03:34,810 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.4.output.dense.weight
2021-01-19 22:03:34,810 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.5.attention.output.LayerNorm.bias
2021-01-19 22:03:34,810 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.5.attention.output.LayerNorm.weight
2021-01-19 22:03:34,810 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.5.attention.output.dense.bias
2021-01-19 22:03:34,810 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.5.attention.output.dense.weight
2021-01-19 22:03:34,810 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.5.attention.self.key.bias
2021-01-19 22:03:34,810 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.5.attention.self.key.weight
2021-01-19 22:03:34,810 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.5.attention.self.query.bias
2021-01-19 22:03:34,810 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.5.attention.self.query.weight
2021-01-19 22:03:34,810 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.5.attention.self.value.bias
2021-01-19 22:03:34,810 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.5.attention.self.value.weight
2021-01-19 22:03:34,810 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.5.intermediate.dense.bias
2021-01-19 22:03:34,810 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.5.intermediate.dense.weight
2021-01-19 22:03:34,810 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.5.output.LayerNorm.bias
2021-01-19 22:03:34,810 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.5.output.LayerNorm.weight
2021-01-19 22:03:34,810 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.5.output.dense.bias
2021-01-19 22:03:34,810 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.5.output.dense.weight
2021-01-19 22:03:34,811 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.6.attention.output.LayerNorm.bias
2021-01-19 22:03:34,811 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.6.attention.output.LayerNorm.weight
2021-01-19 22:03:34,811 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.6.attention.output.dense.bias
2021-01-19 22:03:34,811 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.6.attention.output.dense.weight
2021-01-19 22:03:34,811 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.6.attention.self.key.bias
2021-01-19 22:03:34,811 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.6.attention.self.key.weight
2021-01-19 22:03:34,811 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.6.attention.self.query.bias
2021-01-19 22:03:34,811 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.6.attention.self.query.weight
2021-01-19 22:03:34,811 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.6.attention.self.value.bias
2021-01-19 22:03:34,811 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.6.attention.self.value.weight
2021-01-19 22:03:34,811 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.6.intermediate.dense.bias
2021-01-19 22:03:34,811 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.6.intermediate.dense.weight
2021-01-19 22:03:34,811 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.6.output.LayerNorm.bias
2021-01-19 22:03:34,811 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.6.output.LayerNorm.weight
2021-01-19 22:03:34,811 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.6.output.dense.bias
2021-01-19 22:03:34,811 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.6.output.dense.weight
2021-01-19 22:03:34,811 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.7.attention.output.LayerNorm.bias
2021-01-19 22:03:34,811 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.7.attention.output.LayerNorm.weight
2021-01-19 22:03:34,811 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.7.attention.output.dense.bias
2021-01-19 22:03:34,811 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.7.attention.output.dense.weight
2021-01-19 22:03:34,811 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.7.attention.self.key.bias
2021-01-19 22:03:34,812 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.7.attention.self.key.weight
2021-01-19 22:03:34,812 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.7.attention.self.query.bias
2021-01-19 22:03:34,812 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.7.attention.self.query.weight
2021-01-19 22:03:34,812 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.7.attention.self.value.bias
2021-01-19 22:03:34,812 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.7.attention.self.value.weight
2021-01-19 22:03:34,812 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.7.intermediate.dense.bias
2021-01-19 22:03:34,812 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.7.intermediate.dense.weight
2021-01-19 22:03:34,812 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.7.output.LayerNorm.bias
2021-01-19 22:03:34,812 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.7.output.LayerNorm.weight
2021-01-19 22:03:34,812 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.7.output.dense.bias
2021-01-19 22:03:34,812 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.7.output.dense.weight
2021-01-19 22:03:34,812 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.8.attention.output.LayerNorm.bias
2021-01-19 22:03:34,812 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.8.attention.output.LayerNorm.weight
2021-01-19 22:03:34,812 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.8.attention.output.dense.bias
2021-01-19 22:03:34,812 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.8.attention.output.dense.weight
2021-01-19 22:03:34,812 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.8.attention.self.key.bias
2021-01-19 22:03:34,812 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.8.attention.self.key.weight
2021-01-19 22:03:34,812 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.8.attention.self.query.bias
2021-01-19 22:03:34,812 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.8.attention.self.query.weight
2021-01-19 22:03:34,812 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.8.attention.self.value.bias
2021-01-19 22:03:34,813 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.8.attention.self.value.weight
2021-01-19 22:03:34,813 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.8.intermediate.dense.bias
2021-01-19 22:03:34,813 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.8.intermediate.dense.weight
2021-01-19 22:03:34,813 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.8.output.LayerNorm.bias
2021-01-19 22:03:34,813 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.8.output.LayerNorm.weight
2021-01-19 22:03:34,813 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.8.output.dense.bias
2021-01-19 22:03:34,813 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.8.output.dense.weight
2021-01-19 22:03:34,813 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.9.attention.output.LayerNorm.bias
2021-01-19 22:03:34,813 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.9.attention.output.LayerNorm.weight
2021-01-19 22:03:34,813 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.9.attention.output.dense.bias
2021-01-19 22:03:34,813 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.9.attention.output.dense.weight
2021-01-19 22:03:34,813 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.9.attention.self.key.bias
2021-01-19 22:03:34,813 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.9.attention.self.key.weight
2021-01-19 22:03:34,813 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.9.attention.self.query.bias
2021-01-19 22:03:34,813 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.9.attention.self.query.weight
2021-01-19 22:03:34,813 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.9.attention.self.value.bias
2021-01-19 22:03:34,813 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.9.attention.self.value.weight
2021-01-19 22:03:34,813 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.9.intermediate.dense.bias
2021-01-19 22:03:34,813 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.9.intermediate.dense.weight
2021-01-19 22:03:34,813 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.9.output.LayerNorm.bias
2021-01-19 22:03:34,813 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.9.output.LayerNorm.weight
2021-01-19 22:03:34,814 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.9.output.dense.bias
2021-01-19 22:03:34,814 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.encoder.layer.9.output.dense.weight
2021-01-19 22:03:34,814 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.pooler.dense.bias
2021-01-19 22:03:34,814 - INFO - allennlp.nn.initializers -    text_field_embedder.token_embedder_bert.bert_model.pooler.dense.weight
2021-01-19 22:03:34,816 - INFO - udify.models.udify_model - Total number of parameters: 212246786
2021-01-19 22:03:34,816 - INFO - udify.models.udify_model - Total number of trainable parameters: 212246786
Traceback (most recent call last):
  File "predict.py", line 60, in <module>
    args.pred_file, args.eval_file, batch_size=args.batch_size)
  File "/mnt/partuuid-46caa556-c2c4-eb47-907a-5d2092050724/var/lib/home/fran/udify/udify/util.py", line 163, in predict_and_evaluate_model_with_archive
    predict_model_with_archive(predictor, params, archive, segment_file, pred_file, batch_size)
  File "/mnt/partuuid-46caa556-c2c4-eb47-907a-5d2092050724/var/lib/home/fran/udify/udify/util.py", line 143, in predict_model_with_archive
    cuda_device=cuda_device)
  File "/mnt/partuuid-46caa556-c2c4-eb47-907a-5d2092050724/var/lib/home/fran/venv/lib/python3.7/site-packages/allennlp/models/archival.py", line 230, in load_archive
    cuda_device=cuda_device)
  File "/mnt/partuuid-46caa556-c2c4-eb47-907a-5d2092050724/var/lib/home/fran/venv/lib/python3.7/site-packages/allennlp/models/model.py", line 327, in load
    return cls.by_name(model_type)._load(config, serialization_dir, weights_file, cuda_device)
  File "/mnt/partuuid-46caa556-c2c4-eb47-907a-5d2092050724/var/lib/home/fran/venv/lib/python3.7/site-packages/allennlp/models/model.py", line 275, in _load
    model_state = torch.load(weights_file, map_location=util.device_mapping(cuda_device))
  File "/mnt/partuuid-46caa556-c2c4-eb47-907a-5d2092050724/var/lib/home/fran/venv/lib/python3.7/site-packages/torch/serialization.py", line 529, in load
    return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
  File "/mnt/partuuid-46caa556-c2c4-eb47-907a-5d2092050724/var/lib/home/fran/venv/lib/python3.7/site-packages/torch/serialization.py", line 709, in _legacy_load
    deserialized_objects[key]._set_from_file(f, offset, f_should_read_directly)
RuntimeError: unexpected EOF, expected 240172598 more bytes. The file might be corrupted.
free(): corrupted unsorted chunks
Aborted (core dumped)
(venv) fran@tlazolteotl /var/lib/home/fran/udify $ md5sum udify*.tar.gz
facd2798e9786636ced131804ac67398  udify-bert.tar.gz
42aacc00e0ed6272b31ca7329055c108  udify-model.tar.gz
Hyperparticle commented 3 years ago

This seems to me like a newer version of PyTorch made an incompatible change torch.load, which leads to it saying that the file might be corrupted. It seems unlikely that the file format is corrupted, considering nothing has changed in the code and the MD5 sum matches.

I have the version pinned to 1.4.0. What version of PyTorch are you running? That might give us a start.

ftyers commented 3 years ago

Yep, I think that it is unlikely that it is anything to do with the file format.

I'm running 1.4.0 too:

$ pip3 show torch
Name: torch
Version: 1.4.0
Summary: Tensors and Dynamic neural networks in Python with strong GPU acceleration
Home-page: https://pytorch.org/
Author: PyTorch Team
Author-email: packages@pytorch.org
License: BSD-3
Location: /home/fran/.local/lib/python3.8/site-packages
Requires: 
Required-by: torchvision, torchaudio, pytorch-transformers, pytorch-pretrained-bert, fairseq, allennlp

And I don't have any other versions lying around:

$ find /home/fran/.local/lib/ /home/fran/local/lib /usr/lib/python* | grep torch-
/home/fran/.local/lib/python3.8/site-packages/torch-1.4.0.dist-info
/home/fran/.local/lib/python3.8/site-packages/torch-1.4.0.dist-info/WHEEL
/home/fran/.local/lib/python3.8/site-packages/torch-1.4.0.dist-info/NOTICE
/home/fran/.local/lib/python3.8/site-packages/torch-1.4.0.dist-info/INSTALLER
/home/fran/.local/lib/python3.8/site-packages/torch-1.4.0.dist-info/top_level.txt
/home/fran/.local/lib/python3.8/site-packages/torch-1.4.0.dist-info/RECORD
/home/fran/.local/lib/python3.8/site-packages/torch-1.4.0.dist-info/METADATA
/home/fran/.local/lib/python3.8/site-packages/torch-1.4.0.dist-info/LICENSE
/home/fran/.local/lib/python3.8/site-packages/torch-1.4.0.dist-info/entry_points.txt
Hyperparticle commented 3 years ago

Hmm, this seems tricky.

Looks like some others report issues with the main HuggingFace library: https://github.com/huggingface/transformers/issues/6620 https://github.com/huggingface/transformers/issues/1491

There are a few solutions posed, but I'm not sure how applicable they might be.

Hyperparticle commented 3 years ago

Seems like it stops at deserialized_objects[key]._set_from_file(f, offset, f_should_read_directly).

Can you set a breakpoint/print statement and list out what the input variables are? Maybe it could give a clue.

Or maybe _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args) might be better.

huberemanuel commented 3 years ago

I am having the same behavior.

MD5: 

42aacc00e0ed6272b31ca7329055c108  udify-model.tar.gz

Stacktrace:

Traceback (most recent call last):
  File "predict.py", line 57, in <module>
    batch_size=args.batch_size)
  File "/content/udify/udify/util.py", line 143, in predict_model_with_archive
    cuda_device=cuda_device)
  File "/usr/local/lib/python3.7/dist-packages/allennlp/models/archival.py", line 230, in load_archive
    cuda_device=cuda_device)
  File "/usr/local/lib/python3.7/dist-packages/allennlp/models/model.py", line 327, in load
    return cls.by_name(model_type)._load(config, serialization_dir, weights_file, cuda_device)
  File "/usr/local/lib/python3.7/dist-packages/allennlp/models/model.py", line 275, in _load
    model_state = torch.load(weights_file, map_location=util.device_mapping(cuda_device))
  File "/usr/local/lib/python3.7/dist-packages/torch/serialization.py", line 529, in load
    return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
  File "/usr/local/lib/python3.7/dist-packages/torch/serialization.py", line 709, in _legacy_load
    deserialized_objects[key]._set_from_file(f, offset, f_should_read_directly)
RuntimeError: unexpected EOF, expected 245923382 more bytes. The file might be corrupted.
terminate called after throwing an instance of 'c10::Error'
  what():  owning_ptr == NullType::singleton() || owning_ptr->refcount_.load() > 0 INTERNAL ASSERT FAILED at /pytorch/c10/util/intrusive_ptr.h:348, please report a bug to PyTorch. intrusive_ptr: Can only intrusive_ptr::reclaim() owning pointers that were created using intrusive_ptr::release(). (reclaim at /pytorch/c10/util/intrusive_ptr.h:348)
frame #0: c10::Error::Error(c10::SourceLocation, std::string const&) + 0x33 (0x7f865f5d5193 in /usr/local/lib/python3.7/dist-packages/torch/lib/libc10.so)
frame #1: <unknown function> + 0x18cd59f (0x7f86612f559f in /usr/local/lib/python3.7/dist-packages/torch/lib/libtorch.so)
frame #2: THStorage_free + 0x17 (0x7f8661abdba7 in /usr/local/lib/python3.7/dist-packages/torch/lib/libtorch.so)
frame #3: <unknown function> + 0x939a17 (0x7f86aa902a17 in /usr/local/lib/python3.7/dist-packages/torch/lib/libtorch_python.so)
<omitting python frames>
frame #21: __libc_start_main + 0xe7 (0x7f870e4cdbf7 in /lib/x86_64-linux-gnu/libc.so.6)
Lguyogiro commented 2 years ago

any solution to this? I've also run into it just now.