Skip to content

Commit

Permalink
refactor: ner_ontonotes_bert[_mult]_torch -> ner_ontonotes_bert[_mult]
Browse files Browse the repository at this point in the history
  • Loading branch information
@IgnatovFedor
IgnatovFedor committed Feb 1, 2022
1 parent a902cbe commit bb41a58
Show file tree
Hide file tree
Showing 7 changed files with 66 additions and 294 deletions.
63 changes: 28 additions & 35 deletions deeppavlov/configs/ner/ner_ontonotes_bert.json
View file
Original file line number Diff line number Diff line change
Expand Up @@ -13,8 +13,8 @@
"in_y": ["y"],
"pipe": [
{
"class_name": "bert_ner_preprocessor",
"vocab_file": "{BERT_PATH}/vocab.txt",
"class_name": "torch_transformers_ner_preprocessor",
"vocab_file": "{TRANSFORMER}",
"do_lower_case": false,
"max_seq_length": 512,
"max_subword_length": 15,
Expand All @@ -27,33 +27,33 @@
"class_name": "simple_vocab",
"unk_token": ["O"],
"pad_with_zeros": true,
"save_path": "{NER_PATH}/tag.dict",
"load_path": "{NER_PATH}/tag.dict",
"save_path": "{MODEL_PATH}/tag.dict",
"load_path": "{MODEL_PATH}/tag.dict",
"fit_on": ["y"],
"in": ["y"],
"out": ["y_ind"]
},
{
"class_name": "bert_sequence_tagger",
"class_name": "torch_transformers_sequence_tagger",
"n_tags": "#tag_vocab.len",
"keep_prob": 0.1,
"bert_config_file": "{BERT_PATH}/bert_config.json",
"pretrained_bert": "{BERT_PATH}/bert_model.ckpt",
"pretrained_bert": "{TRANSFORMER}",
"attention_probs_keep_prob": 0.5,
"use_crf": true,
"return_probas": false,
"ema_decay": 0.9,
"encoder_layer_ids": [-1],
"weight_decay_rate": 1e-6,
"learning_rate": 1e-2,
"bert_learning_rate": 2e-5,
"min_learning_rate": 1e-7,
"learning_rate_drop_patience": 30,
"learning_rate_drop_div": 2,
"load_before_drop": false,
"optimizer": "AdamW",
"optimizer_parameters": {
"lr": 2e-05,
"weight_decay": 1e-06,
"betas": [0.9, 0.999],
"eps": 1e-06
},
"clip_norm": 1.0,
"save_path": "{NER_PATH}/model",
"load_path": "{NER_PATH}/model",
"min_learning_rate": 1e-07,
"learning_rate_drop_patience": 30,
"learning_rate_drop_div": 1.5,
"load_before_drop": true,
"save_path": "{MODEL_PATH}/model",
"load_path": "{MODEL_PATH}/model",
"in": ["x_subword_tok_ids", "attention_mask", "startofword_markers"],
"in_y": ["y_ind"],
"out": ["y_pred_ind"]
Expand All @@ -68,7 +68,7 @@
},
"train": {
"epochs": 30,
"batch_size": 16,
"batch_size": 10,
"metrics": [
{
"name": "ner_f1",
Expand All @@ -80,34 +80,27 @@
}
],
"validation_patience": 100,
"val_every_n_batches": 40,

"log_every_n_batches": 40,
"tensorboard_log_dir": "{NER_PATH}/logs",
"val_every_n_batches": 20,
"log_every_n_batches": 20,
"show_examples": false,
"pytest_max_batches": 2,
"pytest_batch_size": 8,
"evaluation_targets": ["valid", "test"],
"class_name": "nn_trainer"
"class_name": "torch_trainer"
},
"metadata": {
"variables": {
"ROOT_PATH": "~/.deeppavlov",
"DOWNLOADS_PATH": "{ROOT_PATH}/downloads",
"MODELS_PATH": "{ROOT_PATH}/models",
"BERT_PATH": "{DOWNLOADS_PATH}/bert_models/cased_L-12_H-768_A-12",
"NER_PATH": "{MODELS_PATH}/ner_ontonotes_bert"
"TRANSFORMER": "bert-base-cased",
"MODEL_PATH": "{MODELS_PATH}/ner_ontonotes_bert_torch/{TRANSFORMER}"
},
"download": [

{
"url": "http://files.deeppavlov.ai/deeppavlov_data/ner_ontonotes_bert_v1.tar.gz",
"subdir": "{MODELS_PATH}"
},
{
"url": "http://files.deeppavlov.ai/deeppavlov_data/bert/cased_L-12_H-768_A-12.zip",
"subdir": "{DOWNLOADS_PATH}/bert_models"
"url": "http://files.deeppavlov.ai/v1/ner/ner_ontonotes_bert_torch.tar.gz",
"subdir": "{ROOT_PATH}/models"
}
]
}
}
}
57 changes: 25 additions & 32 deletions deeppavlov/configs/ner/ner_ontonotes_bert_mult.json
View file
Original file line number Diff line number Diff line change
Expand Up @@ -13,8 +13,8 @@
"in_y": ["y"],
"pipe": [
{
"class_name": "bert_ner_preprocessor",
"vocab_file": "{BERT_PATH}/vocab.txt",
"class_name": "torch_transformers_ner_preprocessor",
"vocab_file": "{TRANSFORMER}",
"do_lower_case": false,
"max_seq_length": 512,
"max_subword_length": 15,
Expand All @@ -27,33 +27,33 @@
"class_name": "simple_vocab",
"unk_token": ["O"],
"pad_with_zeros": true,
"save_path": "{NER_PATH}/tag.dict",
"load_path": "{NER_PATH}/tag.dict",
"save_path": "{MODEL_PATH}/tag.dict",
"load_path": "{MODEL_PATH}/tag.dict",
"fit_on": ["y"],
"in": ["y"],
"out": ["y_ind"]
},
{
"class_name": "bert_sequence_tagger",
"class_name": "torch_transformers_sequence_tagger",
"n_tags": "#tag_vocab.len",
"keep_prob": 0.1,
"bert_config_file": "{BERT_PATH}/bert_config.json",
"pretrained_bert": "{BERT_PATH}/bert_model.ckpt",
"pretrained_bert": "{TRANSFORMER}",
"attention_probs_keep_prob": 0.5,
"use_crf": true,
"return_probas": false,
"ema_decay": 0.9,
"encoder_layer_ids": [-1],
"weight_decay_rate": 1e-6,
"learning_rate": 1e-2,
"bert_learning_rate": 2e-5,
"min_learning_rate": 1e-7,
"optimizer": "AdamW",
"optimizer_parameters": {
"lr": 2e-05,
"weight_decay": 1e-06,
"betas": [0.9, 0.999],
"eps": 1e-06
},
"clip_norm": 1.0,
"min_learning_rate": 1e-07,
"learning_rate_drop_patience": 30,
"learning_rate_drop_div": 1.5,
"load_before_drop": false,
"clip_norm": 1.0,
"save_path": "{NER_PATH}/model",
"load_path": "{NER_PATH}/model",
"load_before_drop": true,
"save_path": "{MODEL_PATH}/model",
"load_path": "{MODEL_PATH}/model",
"in": ["x_subword_tok_ids", "attention_mask", "startofword_markers"],
"in_y": ["y_ind"],
"out": ["y_pred_ind"]
Expand All @@ -68,7 +68,7 @@
},
"train": {
"epochs": 30,
"batch_size": 16,
"batch_size": 10,
"metrics": [
{
"name": "ner_f1",
Expand All @@ -81,32 +81,25 @@
],
"validation_patience": 100,
"val_every_n_batches": 20,

"log_every_n_batches": 20,
"tensorboard_log_dir": "{NER_PATH}/logs",
"show_examples": false,
"pytest_max_batches": 2,
"pytest_batch_size": 8,
"show_examples": false,
"evaluation_targets": ["valid", "test"],
"class_name": "nn_trainer"
"class_name": "torch_trainer"
},
"metadata": {
"variables": {
"ROOT_PATH": "~/.deeppavlov",
"DOWNLOADS_PATH": "{ROOT_PATH}/downloads",
"MODELS_PATH": "{ROOT_PATH}/models",
"BERT_PATH": "{DOWNLOADS_PATH}/bert_models/multi_cased_L-12_H-768_A-12",
"NER_PATH": "{MODELS_PATH}/ner_ontonotes_bert_mult"
"TRANSFORMER": "bert-base-multilingual-cased",
"MODEL_PATH": "{MODELS_PATH}/ner_ontonotes_bert_mult_torch/{TRANSFORMER}"
},
"download": [

{
"url": "http://files.deeppavlov.ai/deeppavlov_data/ner_ontonotes_bert_mult_v1.tar.gz",
"subdir": "{MODELS_PATH}"
},
{
"url": "http://files.deeppavlov.ai/deeppavlov_data/bert/multi_cased_L-12_H-768_A-12.zip",
"subdir": "{DOWNLOADS_PATH}/bert_models"
"url": "http://files.deeppavlov.ai/v1/ner/ner_ontonotes_bert_mult_torch.tar.gz",
"subdir": "{ROOT_PATH}/models"
}
]
}
Expand Down
106 changes: 0 additions & 106 deletions deeppavlov/configs/ner/ner_ontonotes_bert_mult_torch.json
View file

This file was deleted.

Loading

0 comments on commit bb41a58

Please sign in to comment.