Model auxiliar files
Browse files- config.json +74 -0
- eval_results.txt +4 -0
- model_args.json +1 -0
- special_tokens_map.json +7 -0
- tokenizer_config.json +16 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "neuralmind/bert-large-portuguese-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"directionality": "bidi",
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 1024,
|
12 |
+
"id2label": {
|
13 |
+
"0": "O",
|
14 |
+
"1": "B-Observacoes",
|
15 |
+
"2": "I-Observacoes",
|
16 |
+
"3": "B-Historico_Paciente",
|
17 |
+
"4": "I-Historico_Paciente",
|
18 |
+
"5": "B-Drogas",
|
19 |
+
"6": "I-Drogas",
|
20 |
+
"7": "B-Historico_Familiar",
|
21 |
+
"8": "I-Historico_Familiar",
|
22 |
+
"9": "B-Funcao_Psiquica",
|
23 |
+
"10": "I-Funcao_Psiquica",
|
24 |
+
"11": "B-Diagnosticos",
|
25 |
+
"12": "I-Diagnosticos",
|
26 |
+
"13": "B-Farmacos",
|
27 |
+
"14": "I-Farmacos",
|
28 |
+
"15": "B-Sintomas_e_Queixas_Ps\u00edquicas",
|
29 |
+
"16": "I-Sintomas_e_Queixas_Ps\u00edquicas",
|
30 |
+
"17": "B-Comportamento_Autodestrutivo",
|
31 |
+
"18": "I-Comportamento_Autodestrutivo"
|
32 |
+
},
|
33 |
+
"initializer_range": 0.02,
|
34 |
+
"intermediate_size": 4096,
|
35 |
+
"label2id": {
|
36 |
+
"B-Comportamento_Autodestrutivo": 17,
|
37 |
+
"B-Diagnosticos": 11,
|
38 |
+
"B-Drogas": 5,
|
39 |
+
"B-Farmacos": 13,
|
40 |
+
"B-Funcao_Psiquica": 9,
|
41 |
+
"B-Historico_Familiar": 7,
|
42 |
+
"B-Historico_Paciente": 3,
|
43 |
+
"B-Observacoes": 1,
|
44 |
+
"B-Sintomas_e_Queixas_Ps\u00edquicas": 15,
|
45 |
+
"I-Comportamento_Autodestrutivo": 18,
|
46 |
+
"I-Diagnosticos": 12,
|
47 |
+
"I-Drogas": 6,
|
48 |
+
"I-Farmacos": 14,
|
49 |
+
"I-Funcao_Psiquica": 10,
|
50 |
+
"I-Historico_Familiar": 8,
|
51 |
+
"I-Historico_Paciente": 4,
|
52 |
+
"I-Observacoes": 2,
|
53 |
+
"I-Sintomas_e_Queixas_Ps\u00edquicas": 16,
|
54 |
+
"O": 0
|
55 |
+
},
|
56 |
+
"layer_norm_eps": 1e-12,
|
57 |
+
"max_position_embeddings": 512,
|
58 |
+
"model_type": "bert",
|
59 |
+
"num_attention_heads": 16,
|
60 |
+
"num_hidden_layers": 24,
|
61 |
+
"output_past": true,
|
62 |
+
"pad_token_id": 0,
|
63 |
+
"pooler_fc_size": 768,
|
64 |
+
"pooler_num_attention_heads": 12,
|
65 |
+
"pooler_num_fc_layers": 3,
|
66 |
+
"pooler_size_per_head": 128,
|
67 |
+
"pooler_type": "first_token_transform",
|
68 |
+
"position_embedding_type": "absolute",
|
69 |
+
"torch_dtype": "float32",
|
70 |
+
"transformers_version": "4.26.0",
|
71 |
+
"type_vocab_size": 2,
|
72 |
+
"use_cache": true,
|
73 |
+
"vocab_size": 29794
|
74 |
+
}
|
eval_results.txt
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
eval_loss = 0.4258968200534582
|
2 |
+
f1_score = 0.6705346042271032
|
3 |
+
precision = 0.648757016840417
|
4 |
+
recall = 0.6938250428816467
|
model_args.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
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
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": false,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"model_max_length": 1000000000000000019884624838656,
|
7 |
+
"name_or_path": "neuralmind/bert-large-portuguese-cased",
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--neuralmind--bert-large-portuguese-cased/snapshots/aa302f6ea73b759f7df9cad58bd272127b67ec28/special_tokens_map.json",
|
12 |
+
"strip_accents": null,
|
13 |
+
"tokenize_chinese_chars": true,
|
14 |
+
"tokenizer_class": "BertTokenizer",
|
15 |
+
"unk_token": "[UNK]"
|
16 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33f25a41afdcaabb10fc4a073d8e05492177000ccf76136f904746cba25a82a8
|
3 |
+
size 3515
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|