khygopole commited on
Commit
7ed27e3
1 Parent(s): 3d07b36

khygopole/NLP_HerbalMultiLabelClassificationModel

Browse files
README.md ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: medicalai/ClinicalBERT
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - f1
7
+ - accuracy
8
+ model-index:
9
+ - name: working
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # working
17
+
18
+ This model is a fine-tuned version of [medicalai/ClinicalBERT](https://huggingface.co/medicalai/ClinicalBERT) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.0108
21
+ - F1: 0.9834
22
+ - Roc Auc: 0.9930
23
+ - Accuracy: 0.9853
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 5e-05
43
+ - train_batch_size: 8
44
+ - eval_batch_size: 8
45
+ - seed: 42
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - num_epochs: 5
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
53
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
54
+ | No log | 1.0 | 136 | 0.0223 | 0.9834 | 0.9930 | 0.9853 |
55
+ | No log | 2.0 | 272 | 0.0163 | 0.9881 | 0.9959 | 0.9926 |
56
+ | No log | 3.0 | 408 | 0.0137 | 0.9834 | 0.9930 | 0.9853 |
57
+ | 0.0216 | 4.0 | 544 | 0.0120 | 0.9834 | 0.9930 | 0.9853 |
58
+ | 0.0216 | 5.0 | 680 | 0.0108 | 0.9834 | 0.9930 | 0.9853 |
59
+
60
+
61
+ ### Framework versions
62
+
63
+ - Transformers 4.37.0
64
+ - Pytorch 2.1.2+cu118
65
+ - Datasets 2.16.1
66
+ - Tokenizers 0.15.0
config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "medicalai/ClinicalBERT",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7",
20
+ "8": "LABEL_8",
21
+ "9": "LABEL_9"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "label2id": {
25
+ "LABEL_0": 0,
26
+ "LABEL_1": 1,
27
+ "LABEL_2": 2,
28
+ "LABEL_3": 3,
29
+ "LABEL_4": 4,
30
+ "LABEL_5": 5,
31
+ "LABEL_6": 6,
32
+ "LABEL_7": 7,
33
+ "LABEL_8": 8,
34
+ "LABEL_9": 9
35
+ },
36
+ "max_position_embeddings": 512,
37
+ "model_type": "distilbert",
38
+ "n_heads": 12,
39
+ "n_layers": 6,
40
+ "output_past": true,
41
+ "pad_token_id": 0,
42
+ "problem_type": "multi_label_classification",
43
+ "qa_dropout": 0.1,
44
+ "seq_classif_dropout": 0.2,
45
+ "sinusoidal_pos_embds": false,
46
+ "tie_weights_": true,
47
+ "torch_dtype": "float32",
48
+ "transformers_version": "4.37.0",
49
+ "vocab_size": 119547
50
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:631735545ea04b16e1c0998dae4432080e6c0b582978d273100a417d55bb42f6
3
+ size 541341984
runs/Feb02_17-40-41_LAPTOP-KMPG041102/events.out.tfevents.1706866949.LAPTOP-KMPG041102.8084.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1e0ec1c153f550c69f6517752b30d48887446dd6724e5a964f61bb73d0c4078
3
+ size 5696
runs/Feb02_20-08-12_LAPTOP-KMPG041102/events.out.tfevents.1706875693.LAPTOP-KMPG041102.944.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f607f2abc77fa135f20eb0d289e67d0d67f6a159935ce93ffc0df1dfa4309dbd
3
+ size 6592
runs/Feb02_20-08-12_LAPTOP-KMPG041102/events.out.tfevents.1706877100.LAPTOP-KMPG041102.944.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e37a89571f929e7437e10b30c980ce3c6f05c8d23a1e2136766ac0df447e2326
3
+ size 359
runs/Feb02_20-08-12_LAPTOP-KMPG041102/events.out.tfevents.1706877101.LAPTOP-KMPG041102.944.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a705700160dd06b8c447ce53215e23efd0786e4c5dc9385d6c19b2d62248616e
3
+ size 7379
runs/Feb02_20-08-12_LAPTOP-KMPG041102/events.out.tfevents.1706879275.LAPTOP-KMPG041102.944.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d05dd0ba3671eee97a5bc3b032fbbc27ba967186f4a6dcb6ccac0a2cd019d85
3
+ size 508
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.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
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
+ "full_tokenizer_file": null,
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "problem_type": "multi-label-classification",
54
+ "sep_token": "[SEP]",
55
+ "strip_accents": null,
56
+ "tokenize_chinese_chars": true,
57
+ "tokenizer_class": "DistilBertTokenizer",
58
+ "unk_token": "[UNK]"
59
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95ad2eee12bcda8026a061008edbe413c6659e8a0ffd4a736dcc812c67a72dde
3
+ size 4728
vocab.txt ADDED
The diff for this file is too large to render. See raw diff