damand2061
commited on
Commit
•
ff0319d
1
Parent(s):
2e54381
End of training
Browse files- README.md +72 -0
- config.json +70 -0
- special_tokens_map.json +7 -0
- tf_model.h5 +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: indobenchmark/indobert-base-p1
|
4 |
+
tags:
|
5 |
+
- generated_from_keras_callback
|
6 |
+
model-index:
|
7 |
+
- name: damand2061/innermore-x-indobert-base-p1
|
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 |
+
# damand2061/innermore-x-indobert-base-p1
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [indobenchmark/indobert-base-p1](https://huggingface.co/indobenchmark/indobert-base-p1) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 0.0013
|
19 |
+
- Validation Loss: 0.1945
|
20 |
+
- Train Precision: 0.8199
|
21 |
+
- Train Recall: 0.7425
|
22 |
+
- Train F1: 0.7793
|
23 |
+
- Train Accuracy: 0.9614
|
24 |
+
- Epoch: 14
|
25 |
+
|
26 |
+
## Model description
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Intended uses & limitations
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training and evaluation data
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training procedure
|
39 |
+
|
40 |
+
### Training hyperparameters
|
41 |
+
|
42 |
+
The following hyperparameters were used during training:
|
43 |
+
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.0002, 'decay_steps': 420, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
|
44 |
+
- training_precision: float32
|
45 |
+
|
46 |
+
### Training results
|
47 |
+
|
48 |
+
| Train Loss | Validation Loss | Train Precision | Train Recall | Train F1 | Train Accuracy | Epoch |
|
49 |
+
|:----------:|:---------------:|:---------------:|:------------:|:--------:|:--------------:|:-----:|
|
50 |
+
| 0.7385 | 0.3395 | 0.2826 | 0.2232 | 0.2494 | 0.9016 | 0 |
|
51 |
+
| 0.2565 | 0.2143 | 0.6564 | 0.5494 | 0.5981 | 0.9360 | 1 |
|
52 |
+
| 0.1188 | 0.2212 | 0.6146 | 0.5064 | 0.5553 | 0.9317 | 2 |
|
53 |
+
| 0.0631 | 0.1887 | 0.7321 | 0.7039 | 0.7177 | 0.9524 | 3 |
|
54 |
+
| 0.0358 | 0.1894 | 0.7210 | 0.7210 | 0.7210 | 0.9496 | 4 |
|
55 |
+
| 0.0161 | 0.1829 | 0.8301 | 0.7339 | 0.7790 | 0.9605 | 5 |
|
56 |
+
| 0.0092 | 0.1609 | 0.7982 | 0.7811 | 0.7896 | 0.9590 | 6 |
|
57 |
+
| 0.0060 | 0.1885 | 0.8269 | 0.7382 | 0.7800 | 0.9619 | 7 |
|
58 |
+
| 0.0035 | 0.1838 | 0.8261 | 0.7339 | 0.7773 | 0.9614 | 8 |
|
59 |
+
| 0.0022 | 0.1852 | 0.8182 | 0.7339 | 0.7738 | 0.9609 | 9 |
|
60 |
+
| 0.0026 | 0.1900 | 0.7991 | 0.7339 | 0.7651 | 0.9590 | 10 |
|
61 |
+
| 0.0012 | 0.1923 | 0.7907 | 0.7296 | 0.7589 | 0.9595 | 11 |
|
62 |
+
| 0.0010 | 0.1927 | 0.8199 | 0.7425 | 0.7793 | 0.9614 | 12 |
|
63 |
+
| 0.0014 | 0.1942 | 0.8199 | 0.7425 | 0.7793 | 0.9614 | 13 |
|
64 |
+
| 0.0013 | 0.1945 | 0.8199 | 0.7425 | 0.7793 | 0.9614 | 14 |
|
65 |
+
|
66 |
+
|
67 |
+
### Framework versions
|
68 |
+
|
69 |
+
- Transformers 4.38.2
|
70 |
+
- TensorFlow 2.15.0
|
71 |
+
- Datasets 2.18.0
|
72 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "indobenchmark/indobert-base-p1",
|
3 |
+
"_num_labels": 5,
|
4 |
+
"architectures": [
|
5 |
+
"BertForTokenClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"directionality": "bidi",
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "O",
|
15 |
+
"1": "B-MVT",
|
16 |
+
"2": "B-GEN",
|
17 |
+
"3": "B-ACT",
|
18 |
+
"4": "B-DIR",
|
19 |
+
"5": "B-LOC",
|
20 |
+
"6": "B-CHAR",
|
21 |
+
"7": "B-YEAR",
|
22 |
+
"8": "B-STUD",
|
23 |
+
"9": "I-MVT",
|
24 |
+
"10": "I-GEN",
|
25 |
+
"11": "I-ACT",
|
26 |
+
"12": "I-DIR",
|
27 |
+
"13": "I-LOC",
|
28 |
+
"14": "I-CHAR",
|
29 |
+
"15": "I-YEAR",
|
30 |
+
"16": "I-STUD"
|
31 |
+
},
|
32 |
+
"initializer_range": 0.02,
|
33 |
+
"intermediate_size": 3072,
|
34 |
+
"label2id": {
|
35 |
+
"B-ACT": 3,
|
36 |
+
"B-CHAR": 6,
|
37 |
+
"B-DIR": 4,
|
38 |
+
"B-GEN": 2,
|
39 |
+
"B-LOC": 5,
|
40 |
+
"B-MVT": 1,
|
41 |
+
"B-STUD": 8,
|
42 |
+
"B-YEAR": 7,
|
43 |
+
"I-ACT": 11,
|
44 |
+
"I-CHAR": 14,
|
45 |
+
"I-DIR": 12,
|
46 |
+
"I-GEN": 10,
|
47 |
+
"I-LOC": 13,
|
48 |
+
"I-MVT": 9,
|
49 |
+
"I-STUD": 16,
|
50 |
+
"I-YEAR": 15,
|
51 |
+
"O": 0
|
52 |
+
},
|
53 |
+
"layer_norm_eps": 1e-12,
|
54 |
+
"max_position_embeddings": 512,
|
55 |
+
"model_type": "bert",
|
56 |
+
"num_attention_heads": 12,
|
57 |
+
"num_hidden_layers": 12,
|
58 |
+
"output_past": true,
|
59 |
+
"pad_token_id": 0,
|
60 |
+
"pooler_fc_size": 768,
|
61 |
+
"pooler_num_attention_heads": 12,
|
62 |
+
"pooler_num_fc_layers": 3,
|
63 |
+
"pooler_size_per_head": 128,
|
64 |
+
"pooler_type": "first_token_transform",
|
65 |
+
"position_embedding_type": "absolute",
|
66 |
+
"transformers_version": "4.38.2",
|
67 |
+
"type_vocab_size": 2,
|
68 |
+
"use_cache": true,
|
69 |
+
"vocab_size": 50000
|
70 |
+
}
|
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 sha256:680ab066e72832f620d289c233c382603ddd1c25c15248ac79cd1f4fb1a96d99
|
3 |
+
size 495728652
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 1000000000000000019884624838656,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "BertTokenizer",
|
56 |
+
"unk_token": "[UNK]"
|
57 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|