bryanahusna commited on
Commit
b22651d
1 Parent(s): 0a3056a

bryanahusna/my-nergrit-model

Browse files
Files changed (4) hide show
  1. README.md +91 -0
  2. config.json +110 -0
  3. pytorch_model.bin +3 -0
  4. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: indolem/indobert-base-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - id_nergrit_corpus
8
+ metrics:
9
+ - precision
10
+ - recall
11
+ - f1
12
+ - accuracy
13
+ model-index:
14
+ - name: my-nergrit-model
15
+ results:
16
+ - task:
17
+ name: Token Classification
18
+ type: token-classification
19
+ dataset:
20
+ name: id_nergrit_corpus
21
+ type: id_nergrit_corpus
22
+ config: ner
23
+ split: validation
24
+ args: ner
25
+ metrics:
26
+ - name: Precision
27
+ type: precision
28
+ value: 0.8166034264688973
29
+ - name: Recall
30
+ type: recall
31
+ value: 0.8423674534456174
32
+ - name: F1
33
+ type: f1
34
+ value: 0.8292853806632415
35
+ - name: Accuracy
36
+ type: accuracy
37
+ value: 0.9476005188067445
38
+ ---
39
+
40
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
41
+ should probably proofread and complete it, then remove this comment. -->
42
+
43
+ # my-nergrit-model
44
+
45
+ This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on the id_nergrit_corpus dataset.
46
+ It achieves the following results on the evaluation set:
47
+ - Loss: 0.1792
48
+ - Precision: 0.8166
49
+ - Recall: 0.8424
50
+ - F1: 0.8293
51
+ - Accuracy: 0.9476
52
+
53
+ ## Model description
54
+
55
+ More information needed
56
+
57
+ ## Intended uses & limitations
58
+
59
+ More information needed
60
+
61
+ ## Training and evaluation data
62
+
63
+ More information needed
64
+
65
+ ## Training procedure
66
+
67
+ ### Training hyperparameters
68
+
69
+ The following hyperparameters were used during training:
70
+ - learning_rate: 2e-05
71
+ - train_batch_size: 16
72
+ - eval_batch_size: 16
73
+ - seed: 42
74
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
75
+ - lr_scheduler_type: linear
76
+ - num_epochs: 2
77
+
78
+ ### Training results
79
+
80
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
+ | 0.4887 | 1.0 | 784 | 0.1891 | 0.7908 | 0.8305 | 0.8102 | 0.9427 |
83
+ | 0.1624 | 2.0 | 1568 | 0.1792 | 0.8166 | 0.8424 | 0.8293 | 0.9476 |
84
+
85
+
86
+ ### Framework versions
87
+
88
+ - Transformers 4.33.2
89
+ - Pytorch 2.0.1+cu118
90
+ - Datasets 2.14.5
91
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "indolem/indobert-base-uncased",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_ids": 0,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "B-CRD",
15
+ "1": "B-DAT",
16
+ "2": "B-EVT",
17
+ "3": "B-FAC",
18
+ "4": "B-GPE",
19
+ "5": "B-LAN",
20
+ "6": "B-LAW",
21
+ "7": "B-LOC",
22
+ "8": "B-MON",
23
+ "9": "B-NOR",
24
+ "10": "B-ORD",
25
+ "11": "B-ORG",
26
+ "12": "B-PER",
27
+ "13": "B-PRC",
28
+ "14": "B-PRD",
29
+ "15": "B-QTY",
30
+ "16": "B-REG",
31
+ "17": "B-TIM",
32
+ "18": "B-WOA",
33
+ "19": "I-CRD",
34
+ "20": "I-DAT",
35
+ "21": "I-EVT",
36
+ "22": "I-FAC",
37
+ "23": "I-GPE",
38
+ "24": "I-LAN",
39
+ "25": "I-LAW",
40
+ "26": "I-LOC",
41
+ "27": "I-MON",
42
+ "28": "I-NOR",
43
+ "29": "I-ORD",
44
+ "30": "I-ORG",
45
+ "31": "I-PER",
46
+ "32": "I-PRC",
47
+ "33": "I-PRD",
48
+ "34": "I-QTY",
49
+ "35": "I-REG",
50
+ "36": "I-TIM",
51
+ "37": "I-WOA",
52
+ "38": "O"
53
+ },
54
+ "initializer_range": 0.02,
55
+ "intermediate_size": 3072,
56
+ "label2id": {
57
+ "B-CRD": 0,
58
+ "B-DAT": 1,
59
+ "B-EVT": 2,
60
+ "B-FAC": 3,
61
+ "B-GPE": 4,
62
+ "B-LAN": 5,
63
+ "B-LAW": 6,
64
+ "B-LOC": 7,
65
+ "B-MON": 8,
66
+ "B-NOR": 9,
67
+ "B-ORD": 10,
68
+ "B-ORG": 11,
69
+ "B-PER": 12,
70
+ "B-PRC": 13,
71
+ "B-PRD": 14,
72
+ "B-QTY": 15,
73
+ "B-REG": 16,
74
+ "B-TIM": 17,
75
+ "B-WOA": 18,
76
+ "I-CRD": 19,
77
+ "I-DAT": 20,
78
+ "I-EVT": 21,
79
+ "I-FAC": 22,
80
+ "I-GPE": 23,
81
+ "I-LAN": 24,
82
+ "I-LAW": 25,
83
+ "I-LOC": 26,
84
+ "I-MON": 27,
85
+ "I-NOR": 28,
86
+ "I-ORD": 29,
87
+ "I-ORG": 30,
88
+ "I-PER": 31,
89
+ "I-PRC": 32,
90
+ "I-PRD": 33,
91
+ "I-QTY": 34,
92
+ "I-REG": 35,
93
+ "I-TIM": 36,
94
+ "I-WOA": 37,
95
+ "O": 38
96
+ },
97
+ "layer_norm_eps": 1e-12,
98
+ "max_position_embeddings": 512,
99
+ "model_type": "bert",
100
+ "num_attention_heads": 12,
101
+ "num_hidden_layers": 12,
102
+ "output_past": true,
103
+ "pad_token_id": 0,
104
+ "position_embedding_type": "absolute",
105
+ "torch_dtype": "float32",
106
+ "transformers_version": "4.33.2",
107
+ "type_vocab_size": 2,
108
+ "use_cache": true,
109
+ "vocab_size": 31923
110
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d553ccd1c24b7cd564fcf420ad5bfb20db8ff6f5b0184c0e11dca94089f82e05
3
+ size 440058153
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e7a7d5504180043ab48b98189fb1fed280419d0237b9e4c2ffa07e61064fa98
3
+ size 4027