Initial commit of NER model for legal text

config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "./models/mlm_80_without_bertturk_2g_1epoch_32bathsize",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-LAW",
+    "2": "I-LAW",
+    "3": "B-LOC",
+    "4": "B-COR",
+    "5": "I-COR",
+    "6": "B-PUB",
+    "7": "I-PUB",
+    "8": "B-GOV",
+    "9": "I-GOV",
+    "10": "B-PER",
+    "11": "B-OOR",
+    "12": "I-OOR",
+    "13": "B-DAT",
+    "14": "I-DAT",
+    "15": "B-CRT",
+    "16": "I-CRT",
+    "17": "I-PER",
+    "18": "B-PRO",
+    "19": "I-PRO",
+    "20": "B-MNY",
+    "21": "I-MNY",
+    "22": "I-LOC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-COR": 4,
+    "B-CRT": 15,
+    "B-DAT": 13,
+    "B-GOV": 8,
+    "B-LAW": 1,
+    "B-LOC": 3,
+    "B-MNY": 20,
+    "B-OOR": 11,
+    "B-PER": 10,
+    "B-PRO": 18,
+    "B-PUB": 6,
+    "I-COR": 5,
+    "I-CRT": 16,
+    "I-DAT": 14,
+    "I-GOV": 9,
+    "I-LAW": 2,
+    "I-LOC": 22,
+    "I-MNY": 21,
+    "I-OOR": 12,
+    "I-PER": 17,
+    "I-PRO": 19,
+    "I-PUB": 7,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.32.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.txt

@@ -0,0 +1,4 @@
+eval_loss = 0.02349623791743171
+f1_score = 0.9070149360301706
+precision = 0.8850183043461738
+recall = 0.9301328647123039

model_args.json

@@ -0,0 +1 @@
+{"adafactor_beta1": null, "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_eps": [1e-30, 0.001], "adafactor_relative_step": true, "adafactor_scale_parameter": true, "adafactor_warmup_init": true, "adam_betas": [0.9, 0.999], "adam_epsilon": 1e-08, "best_model_dir": "./models/ner/mlm_80_without_bertturk_2g_1epoch_32bathsize/best_model", "cache_dir": "cache_dir/", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "do_lower_case": false, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 3, "encoding": null, "eval_batch_size": 8, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 2000, "evaluate_during_training_verbose": false, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 4e-05, "local_rank": -1, "logging_steps": 50, "loss_type": null, "loss_args": {}, "manual_seed": null, "max_grad_norm": 1.0, "max_seq_length": 128, "model_name": "./models/mlm_80_without_bertturk_2g_1epoch_32bathsize", "model_type": "bert", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 1, "optimizer": "AdamW", "output_dir": "./models/ner/mlm_80_without_bertturk_2g_1epoch_32bathsize", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 126, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": false, "save_model_every_epoch": true, "save_optimizer_and_scheduler": true, "save_steps": 2000, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_name": null, "tokenizer_type": null, "train_batch_size": 128, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_hf_datasets": false, "use_multiprocessing": true, "use_multiprocessing_for_evaluation": true, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 236, "weight_decay": 0.0, "model_class": "NERModel", "classification_report": false, "labels_list": ["O", "B-LAW", "I-LAW", "B-LOC", "B-COR", "I-COR", "B-PUB", "I-PUB", "B-GOV", "I-GOV", "B-PER", "B-OOR", "I-OOR", "B-DAT", "I-DAT", "B-CRT", "I-CRT", "I-PER", "B-PRO", "I-PRO", "B-MNY", "I-MNY", "I-LOC"], "lazy_loading": false, "lazy_loading_start_line": 0, "onnx": false, "special_tokens_list": []}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d493c77e1f5663082fa6f6b2c807db650caf6183742fc098b2fbba3af6b75d5d
+size 880519895

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7187ecc058843fd7e20b445a3054b1dc29b81703cd870da4e347d54c5ac7a48e
+size 440243763

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1377522ec140c78779cec05e2a884468f8bf077b7fce9be5c075b977f1aeb0b7
+size 623

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "max_length": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "tokenizer_file": null,
+  "truncation": true,
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62e18505a736bb1fe8ed503f0c41e3007bb5718bd4c4dc6863835c179c102897
+size 3375