Model auxiliar files

config.json

@@ -0,0 +1,74 @@
+{
+  "_name_or_path": "neuralmind/bert-large-portuguese-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "O",
+    "1": "B-Observacoes",
+    "2": "I-Observacoes",
+    "3": "B-Historico_Paciente",
+    "4": "I-Historico_Paciente",
+    "5": "B-Drogas",
+    "6": "I-Drogas",
+    "7": "B-Historico_Familiar",
+    "8": "I-Historico_Familiar",
+    "9": "B-Funcao_Psiquica",
+    "10": "I-Funcao_Psiquica",
+    "11": "B-Diagnosticos",
+    "12": "I-Diagnosticos",
+    "13": "B-Farmacos",
+    "14": "I-Farmacos",
+    "15": "B-Sintomas_e_Queixas_Ps\u00edquicas",
+    "16": "I-Sintomas_e_Queixas_Ps\u00edquicas",
+    "17": "B-Comportamento_Autodestrutivo",
+    "18": "I-Comportamento_Autodestrutivo"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-Comportamento_Autodestrutivo": 17,
+    "B-Diagnosticos": 11,
+    "B-Drogas": 5,
+    "B-Farmacos": 13,
+    "B-Funcao_Psiquica": 9,
+    "B-Historico_Familiar": 7,
+    "B-Historico_Paciente": 3,
+    "B-Observacoes": 1,
+    "B-Sintomas_e_Queixas_Ps\u00edquicas": 15,
+    "I-Comportamento_Autodestrutivo": 18,
+    "I-Diagnosticos": 12,
+    "I-Drogas": 6,
+    "I-Farmacos": 14,
+    "I-Funcao_Psiquica": 10,
+    "I-Historico_Familiar": 8,
+    "I-Historico_Paciente": 4,
+    "I-Observacoes": 2,
+    "I-Sintomas_e_Queixas_Ps\u00edquicas": 16,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 29794
+}

eval_results.txt

@@ -0,0 +1,4 @@
+eval_loss = 0.4258968200534582
+f1_score = 0.6705346042271032
+precision = 0.648757016840417
+recall = 0.6938250428816467

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": "/outputs/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": "UTF-8", "eval_batch_size": 8, "evaluate_during_training": false, "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": 1, "max_grad_norm": 1.0, "max_seq_length": 256, "model_name": "neuralmind/bert-large-portuguese-cased", "model_type": "bert", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": true, "no_save": false, "not_saved_args": [], "num_train_epochs": 4, "optimizer": "AdamW", "output_dir": "/outputs/", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 10, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": false, "save_model_every_epoch": false, "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": 16, "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": "bert-large-cased_fold_4", "warmup_ratio": 0.06, "warmup_steps": 31, "weight_decay": 0.0, "model_class": "NERModel", "classification_report": false, "labels_list": ["O", "B-Observacoes", "I-Observacoes", "B-Historico_Paciente", "I-Historico_Paciente", "B-Drogas", "I-Drogas", "B-Historico_Familiar", "I-Historico_Familiar", "B-Funcao_Psiquica", "I-Funcao_Psiquica", "B-Diagnosticos", "I-Diagnosticos", "B-Farmacos", "I-Farmacos", "B-Sintomas_e_Queixas_Ps\u00edquicas", "I-Sintomas_e_Queixas_Ps\u00edquicas", "B-Comportamento_Autodestrutivo", "I-Comportamento_Autodestrutivo"], "lazy_loading": false, "lazy_loading_start_line": 0, "onnx": false, "special_tokens_list": []}

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 +1,16 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "neuralmind/bert-large-portuguese-cased",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--neuralmind--bert-large-portuguese-cased/snapshots/aa302f6ea73b759f7df9cad58bd272127b67ec28/special_tokens_map.json",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33f25a41afdcaabb10fc4a073d8e05492177000ccf76136f904746cba25a82a8
+size 3515