-
Notifications
You must be signed in to change notification settings - Fork 1.1k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Showing
104 changed files
with
12,847 additions
and
535 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,72 @@ | ||
| { | ||
| "dataset_reader": { | ||
| "class_name": "boolqa_reader", | ||
| "data_path": "{DOWNLOADS_PATH}/boolqa_data", | ||
| "language": "ru" | ||
| }, | ||
| "dataset_iterator": { | ||
| "class_name": "basic_classification_iterator", | ||
| "seed": 243 | ||
| }, | ||
| "chainer": { | ||
| "in": ["text_a", "text_b"], | ||
| "in_y": ["y"], | ||
| "pipe": [ | ||
| { | ||
| "class_name": "bert_preprocessor", | ||
| "vocab_file": "{DOWNLOADS_PATH}/bert_models/rubert_cased_L-12_H-768_A-12_v1/vocab.txt", | ||
| "do_lower_case": false, | ||
| "max_seq_length": 128, | ||
| "in": ["text_a", "text_b"], | ||
| "out": ["bert_features"] | ||
| }, | ||
| { | ||
| "class_name": "bert_classifier", | ||
| "n_classes": 2, | ||
| "one_hot_labels": false, | ||
| "bert_config_file": "{DOWNLOADS_PATH}/bert_models/rubert_cased_L-12_H-768_A-12_v1/bert_config.json", | ||
| "pretrained_bert": "{DOWNLOADS_PATH}/bert_models/rubert_cased_L-12_H-768_A-12_v1/bert_model.ckpt", | ||
| "save_path": "{MODELS_PATH}/boolqa_rubert/model_rubert", | ||
| "load_path": "{MODELS_PATH}/boolqa_rubert/model_rubert", | ||
| "keep_prob": 0.5, | ||
| "optimizer": "tf.train:AdamOptimizer", | ||
| "learning_rate": 2e-05, | ||
| "learning_rate_drop_patience": 3, | ||
| "learning_rate_drop_div": 2.0, | ||
| "in": ["bert_features"], | ||
| "in_y": ["y"], | ||
| "out": ["predictions"] | ||
| } | ||
| ], | ||
| "out": ["predictions"] | ||
| }, | ||
| "train": { | ||
| "epochs": 50, | ||
| "batch_size": 32, | ||
| "train_metrics": ["f1", "acc"], | ||
| "metrics": ["f1", "acc"], | ||
| "validation_patience": 5, | ||
| "val_every_n_epochs": 1, | ||
| "log_every_n_epochs": 1, | ||
| "evaluation_targets": ["valid", "train"], | ||
| "show_examples": false, | ||
| "tensorboard_log_dir": "{MODELS_PATH}/boolqa_rubert/logs" | ||
| }, | ||
| "metadata": { | ||
| "variables": { | ||
| "ROOT_PATH": "~/.deeppavlov", | ||
| "DOWNLOADS_PATH": "{ROOT_PATH}/downloads", | ||
| "MODELS_PATH": "{ROOT_PATH}/models" | ||
| }, | ||
| "requirements": [ | ||
| "{DEEPPAVLOV_PATH}/requirements/tf.txt", | ||
| "{DEEPPAVLOV_PATH}/requirements/bert_dp.txt" | ||
| ], | ||
| "download": [ | ||
| { | ||
| "url": "http://files.deeppavlov.ai/deeppavlov_data/bert/rubert_cased_L-12_H-768_A-12_v1.tar.gz", | ||
| "subdir": "{DOWNLOADS_PATH}/bert_models" | ||
| } | ||
| ] | ||
| } | ||
| } |
80 changes: 80 additions & 0 deletions
80
deeppavlov/configs/classifiers/entity_ranking_bert_rus_no_mention.json
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,80 @@ | ||
| { | ||
| "dataset_reader": { | ||
| "class_name": "paraphraser_reader", | ||
| "data_path": "{DOWNLOADS_PATH}/entity_ranking_bert_rus_no_mention", | ||
| "do_lower_case": false | ||
| }, | ||
| "dataset_iterator": { | ||
| "class_name": "siamese_iterator", | ||
| "seed": 243, | ||
| "len_valid": 500 | ||
| }, | ||
| "chainer": { | ||
| "in": ["text_a", "text_b"], | ||
| "in_y": ["y"], | ||
| "pipe": [ | ||
| { | ||
| "class_name": "bert_preprocessor", | ||
| "vocab_file": "{DOWNLOADS_PATH}/bert_models/multi_cased_L-12_H-768_A-12/vocab.txt", | ||
| "do_lower_case": false, | ||
| "max_seq_length": 64, | ||
| "in": ["text_a", "text_b"], | ||
| "out": ["bert_features"] | ||
| }, | ||
| { | ||
| "class_name": "bert_classifier", | ||
| "n_classes": 2, | ||
| "return_probas": true, | ||
| "one_hot_labels": false, | ||
| "bert_config_file": "{DOWNLOADS_PATH}/bert_models/multi_cased_L-12_H-768_A-12/bert_config.json", | ||
| "pretrained_bert": "{DOWNLOADS_PATH}/bert_models/multi_cased_L-12_H-768_A-12/bert_model.ckpt", | ||
| "save_path": "{MODEL_PATH}/model", | ||
| "load_path": "{MODEL_PATH}/model", | ||
| "keep_prob": 0.5, | ||
| "learning_rate": 2e-05, | ||
| "learning_rate_drop_patience": 2, | ||
| "learning_rate_drop_div": 2.0, | ||
| "in": ["bert_features"], | ||
| "in_y": ["y"], | ||
| "out": ["predictions"] | ||
| } | ||
| ], | ||
| "out": ["predictions"] | ||
| }, | ||
| "train": { | ||
| "batch_size": 32, | ||
| "pytest_max_batches": 2, | ||
| "metrics": ["f1", "acc"], | ||
| "validation_patience": 10, | ||
| "val_every_n_batches": 100, | ||
| "log_every_n_batches": 100, | ||
| "evaluation_targets": ["train", "valid", "test"], | ||
| "tensorboard_log_dir": "{MODEL_PATH}/" | ||
| }, | ||
| "metadata": { | ||
| "variables": { | ||
| "ROOT_PATH": "~/.deeppavlov", | ||
| "DOWNLOADS_PATH": "{ROOT_PATH}/downloads", | ||
| "MODELS_PATH": "{ROOT_PATH}/models", | ||
| "MODEL_PATH": "{MODELS_PATH}/entity_ranking_bert_rus_no_mention" | ||
| }, | ||
| "requirements": [ | ||
| "{DEEPPAVLOV_PATH}/requirements/tf.txt", | ||
| "{DEEPPAVLOV_PATH}/requirements/bert_dp.txt" | ||
| ], | ||
| "download": [ | ||
| { | ||
| "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/kbqa/datasets/rel_ranking_bert_rus.tar.gz", | ||
| "subdir": "{DOWNLOADS_PATH}/rel_ranking_rus" | ||
| }, | ||
| { | ||
| "url": "http://files.deeppavlov.ai/kbqa/models/rel_ranking_bert_rus.tar.gz", | ||
| "subdir": "{MODELS_PATH}/rel_ranking_bert_rus" | ||
| } | ||
| ] | ||
| } | ||
| } |
153 changes: 153 additions & 0 deletions
153
deeppavlov/configs/classifiers/insults_kaggle_bert_torch.json
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,153 @@ | ||
| { | ||
| "dataset_reader": { | ||
| "class_name": "basic_classification_reader", | ||
| "x": "Comment", | ||
| "y": "Class", | ||
| "data_path": "{DOWNLOADS_PATH}/insults_data" | ||
| }, | ||
| "dataset_iterator": { | ||
| "class_name": "basic_classification_iterator", | ||
| "seed": 42 | ||
| }, | ||
| "chainer": { | ||
| "in": [ | ||
| "x" | ||
| ], | ||
| "in_y": [ | ||
| "y" | ||
| ], | ||
| "pipe": [ | ||
| { | ||
| "class_name": "torch_bert_preprocessor", | ||
| "vocab_file": "bert-base-uncased", | ||
| "do_lower_case": true, | ||
| "max_seq_length": 64, | ||
| "in": [ | ||
| "x" | ||
| ], | ||
| "out": [ | ||
| "bert_features" | ||
| ] | ||
| }, | ||
| { | ||
| "id": "classes_vocab", | ||
| "class_name": "simple_vocab", | ||
| "fit_on": [ | ||
| "y" | ||
| ], | ||
| "save_path": "{MODEL_PATH}/classes.dict", | ||
| "load_path": "{MODEL_PATH}/classes.dict", | ||
| "in": [ | ||
| "y" | ||
| ], | ||
| "out": [ | ||
| "y_ids" | ||
| ] | ||
| }, | ||
| { | ||
| "in": [ | ||
| "y_ids" | ||
| ], | ||
| "out": [ | ||
| "y_onehot" | ||
| ], | ||
| "class_name": "one_hotter", | ||
| "depth": "#classes_vocab.len", | ||
| "single_vector": true | ||
| }, | ||
| { | ||
| "class_name": "torch_bert_classifier", | ||
| "n_classes": "#classes_vocab.len", | ||
| "return_probas": true, | ||
| "pretrained_bert": "bert-base-uncased", | ||
| "save_path": "{MODEL_PATH}/model", | ||
| "load_path": "{MODEL_PATH}/model", | ||
| "optimizer": "AdamW", | ||
| "optimizer_parameters": { | ||
| "lr": 1e-05 | ||
| }, | ||
| "learning_rate_drop_patience": 5, | ||
| "learning_rate_drop_div": 2.0, | ||
| "in": [ | ||
| "bert_features" | ||
| ], | ||
| "in_y": [ | ||
| "y_ids" | ||
| ], | ||
| "out": [ | ||
| "y_pred_probas" | ||
| ] | ||
| }, | ||
| { | ||
| "in": [ | ||
| "y_pred_probas" | ||
| ], | ||
| "out": [ | ||
| "y_pred_ids" | ||
| ], | ||
| "class_name": "proba2labels", | ||
| "max_proba": true | ||
| }, | ||
| { | ||
| "in": [ | ||
| "y_pred_ids" | ||
| ], | ||
| "out": [ | ||
| "y_pred_labels" | ||
| ], | ||
| "ref": "classes_vocab" | ||
| } | ||
| ], | ||
| "out": [ | ||
| "y_pred_labels" | ||
| ] | ||
| }, | ||
| "train": { | ||
| "epochs": 100, | ||
| "batch_size": 64, | ||
| "metrics": [ | ||
| { | ||
| "name": "roc_auc", | ||
| "inputs": [ | ||
| "y_onehot", | ||
| "y_pred_probas" | ||
| ] | ||
| }, | ||
| "accuracy", | ||
| "f1_macro" | ||
| ], | ||
| "validation_patience": 5, | ||
| "val_every_n_epochs": 1, | ||
| "log_every_n_epochs": 1, | ||
| "show_examples": false, | ||
| "evaluation_targets": [ | ||
| "train", | ||
| "valid", | ||
| "test" | ||
| ], | ||
| "class_name": "torch_trainer", | ||
| "tensorboard_log_dir": "{MODEL_PATH}/" | ||
| }, | ||
| "metadata": { | ||
| "variables": { | ||
| "ROOT_PATH": "~/.deeppavlov", | ||
| "DOWNLOADS_PATH": "{ROOT_PATH}/downloads", | ||
| "MODELS_PATH": "{ROOT_PATH}/models", | ||
| "MODEL_PATH": "{MODELS_PATH}/classifiers/insults_kaggle_torch_bert" | ||
| }, | ||
| "requirements": [ | ||
| "{DEEPPAVLOV_PATH}/requirements/pytorch.txt", | ||
| "{DEEPPAVLOV_PATH}/requirements/transformers.txt" | ||
| ], | ||
| "download": [ | ||
| { | ||
| "url": "http://files.deeppavlov.ai/datasets/insults_data.tar.gz", | ||
| "subdir": "{DOWNLOADS_PATH}" | ||
| }, | ||
| { | ||
| "url": "http://files.deeppavlov.ai/deeppavlov_data/classifiers/insults_kaggle_torch_bert_v0.tar.gz", | ||
| "subdir": "{MODELS_PATH}/classifiers" | ||
| } | ||
| ] | ||
| } | ||
| } |
Oops, something went wrong.