Commit
·
1ccfebf
1
Parent(s):
dfcd803
Training in progress epoch 0
Browse files- README.md +54 -0
- config.json +89 -0
- special_tokens_map.json +7 -0
- tf_model.h5 +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +17 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: neuralmind/bert-base-portuguese-cased
|
4 |
+
tags:
|
5 |
+
- generated_from_keras_callback
|
6 |
+
model-index:
|
7 |
+
- name: eloi-goncalves/handsfree-commands-ner2
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
12 |
+
probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# eloi-goncalves/handsfree-commands-ner2
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [neuralmind/bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 0.0399
|
19 |
+
- Validation Loss: 0.0004
|
20 |
+
- Epoch: 0
|
21 |
+
|
22 |
+
## Model description
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training and evaluation data
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training procedure
|
35 |
+
|
36 |
+
### Training hyperparameters
|
37 |
+
|
38 |
+
The following hyperparameters were used during training:
|
39 |
+
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 12693, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
|
40 |
+
- training_precision: mixed_float16
|
41 |
+
|
42 |
+
### Training results
|
43 |
+
|
44 |
+
| Train Loss | Validation Loss | Epoch |
|
45 |
+
|:----------:|:---------------:|:-----:|
|
46 |
+
| 0.0399 | 0.0004 | 0 |
|
47 |
+
|
48 |
+
|
49 |
+
### Framework versions
|
50 |
+
|
51 |
+
- Transformers 4.33.0
|
52 |
+
- TensorFlow 2.12.0
|
53 |
+
- Datasets 2.16.2.dev0
|
54 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "neuralmind/bert-base-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": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "O",
|
14 |
+
"1": "B-UNIT_NAME",
|
15 |
+
"2": "I-UNIT_NAME",
|
16 |
+
"3": "B-TEMPLATE_NAME",
|
17 |
+
"4": "I-TEMPLATE_NAME",
|
18 |
+
"5": "B-PROTOCOL_NAME",
|
19 |
+
"6": "I-PROTOCOL_NAME",
|
20 |
+
"7": "B-MACRO_NAME",
|
21 |
+
"8": "I-MACRO_NAME",
|
22 |
+
"9": "B-PATIENT_NAME",
|
23 |
+
"10": "I-PATIENT_NAME",
|
24 |
+
"11": "B-SHOWME_SPECIFIC_SCORE_MODAL",
|
25 |
+
"12": "I-SHOWME_SPECIFIC_SCORE_MODAL",
|
26 |
+
"13": "B-ROUTINE_NAME",
|
27 |
+
"14": "I-ROUTINE_NAME",
|
28 |
+
"15": "B-SUBMIT_CONTEXT",
|
29 |
+
"16": "I-SUBMIT_CONTEXT",
|
30 |
+
"17": "B-SHOWME_SPECIFIC_VITALS_MODAL",
|
31 |
+
"18": "I-SHOWME_SPECIFIC_VITALS_MODAL",
|
32 |
+
"19": "B-CLINICAL_NOTE",
|
33 |
+
"20": "I-CLINICAL_NOTE",
|
34 |
+
"21": "B-ORDER_ITEM",
|
35 |
+
"22": "I-ORDER_ITEM",
|
36 |
+
"23": "B-SHOWME_SPECIFIC_LABRESULTS_MODAL",
|
37 |
+
"24": "I-SHOWME_SPECIFIC_LABRESULTS_MODAL",
|
38 |
+
"25": "B-GO_TO_LOCATION",
|
39 |
+
"26": "I-GO_TO_LOCATION"
|
40 |
+
},
|
41 |
+
"initializer_range": 0.02,
|
42 |
+
"intermediate_size": 3072,
|
43 |
+
"label2id": {
|
44 |
+
"B-CLINICAL_NOTE": 19,
|
45 |
+
"B-GO_TO_LOCATION": 25,
|
46 |
+
"B-MACRO_NAME": 7,
|
47 |
+
"B-ORDER_ITEM": 21,
|
48 |
+
"B-PATIENT_NAME": 9,
|
49 |
+
"B-PROTOCOL_NAME": 5,
|
50 |
+
"B-ROUTINE_NAME": 13,
|
51 |
+
"B-SHOWME_SPECIFIC_LABRESULTS_MODAL": 23,
|
52 |
+
"B-SHOWME_SPECIFIC_SCORE_MODAL": 11,
|
53 |
+
"B-SHOWME_SPECIFIC_VITALS_MODAL": 17,
|
54 |
+
"B-SUBMIT_CONTEXT": 15,
|
55 |
+
"B-TEMPLATE_NAME": 3,
|
56 |
+
"B-UNIT_NAME": 1,
|
57 |
+
"I-CLINICAL_NOTE": 20,
|
58 |
+
"I-GO_TO_LOCATION": 26,
|
59 |
+
"I-MACRO_NAME": 8,
|
60 |
+
"I-ORDER_ITEM": 22,
|
61 |
+
"I-PATIENT_NAME": 10,
|
62 |
+
"I-PROTOCOL_NAME": 6,
|
63 |
+
"I-ROUTINE_NAME": 14,
|
64 |
+
"I-SHOWME_SPECIFIC_LABRESULTS_MODAL": 24,
|
65 |
+
"I-SHOWME_SPECIFIC_SCORE_MODAL": 12,
|
66 |
+
"I-SHOWME_SPECIFIC_VITALS_MODAL": 18,
|
67 |
+
"I-SUBMIT_CONTEXT": 16,
|
68 |
+
"I-TEMPLATE_NAME": 4,
|
69 |
+
"I-UNIT_NAME": 2,
|
70 |
+
"O": 0
|
71 |
+
},
|
72 |
+
"layer_norm_eps": 1e-12,
|
73 |
+
"max_position_embeddings": 512,
|
74 |
+
"model_type": "bert",
|
75 |
+
"num_attention_heads": 12,
|
76 |
+
"num_hidden_layers": 12,
|
77 |
+
"output_past": true,
|
78 |
+
"pad_token_id": 0,
|
79 |
+
"pooler_fc_size": 768,
|
80 |
+
"pooler_num_attention_heads": 12,
|
81 |
+
"pooler_num_fc_layers": 3,
|
82 |
+
"pooler_size_per_head": 128,
|
83 |
+
"pooler_type": "first_token_transform",
|
84 |
+
"position_embedding_type": "absolute",
|
85 |
+
"transformers_version": "4.33.0",
|
86 |
+
"type_vocab_size": 2,
|
87 |
+
"use_cache": true,
|
88 |
+
"vocab_size": 29794
|
89 |
+
}
|
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 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e457c8f70f9887d8189d17535634bc0d6536e273cd52755319b9ec281fe2477e
|
3 |
+
size 433686580
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_basic_tokenize": true,
|
5 |
+
"do_lower_case": false,
|
6 |
+
"is_split_into_words": true,
|
7 |
+
"mask_token": "[MASK]",
|
8 |
+
"model_max_length": 1000000000000000019884624838656,
|
9 |
+
"never_split": null,
|
10 |
+
"pad_token": "[PAD]",
|
11 |
+
"return_offsets_mapping": true,
|
12 |
+
"sep_token": "[SEP]",
|
13 |
+
"strip_accents": null,
|
14 |
+
"tokenize_chinese_chars": true,
|
15 |
+
"tokenizer_class": "BertTokenizer",
|
16 |
+
"unk_token": "[UNK]"
|
17 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|