Upload 7 files
Browse files- config.json +47 -0
- model.safetensors +3 -0
- model_performance_metrics.txt +73 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert/distilbert-base-uncased",
|
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 |
+
},
|
22 |
+
"initializer_range": 0.02,
|
23 |
+
"label2id": {
|
24 |
+
"LABEL_0": 0,
|
25 |
+
"LABEL_1": 1,
|
26 |
+
"LABEL_2": 2,
|
27 |
+
"LABEL_3": 3,
|
28 |
+
"LABEL_4": 4,
|
29 |
+
"LABEL_5": 5,
|
30 |
+
"LABEL_6": 6,
|
31 |
+
"LABEL_7": 7,
|
32 |
+
"LABEL_8": 8
|
33 |
+
},
|
34 |
+
"max_position_embeddings": 512,
|
35 |
+
"model_type": "distilbert",
|
36 |
+
"n_heads": 12,
|
37 |
+
"n_layers": 6,
|
38 |
+
"pad_token_id": 0,
|
39 |
+
"problem_type": "multi_label_classification",
|
40 |
+
"qa_dropout": 0.1,
|
41 |
+
"seq_classif_dropout": 0.2,
|
42 |
+
"sinusoidal_pos_embds": false,
|
43 |
+
"tie_weights_": true,
|
44 |
+
"torch_dtype": "float32",
|
45 |
+
"transformers_version": "4.40.1",
|
46 |
+
"vocab_size": 30522
|
47 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b48e4609bdbe67bb7ee5ba66b5c1a6d14d0156aa2570b1b426803db86c56127
|
3 |
+
size 267854100
|
model_performance_metrics.txt
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Training set class counts after balancing:
|
2 |
+
_Borderline 10398
|
3 |
+
_Anxiety 10393
|
4 |
+
_Depression 10400
|
5 |
+
_Bipolar 10359
|
6 |
+
_OCD 10413
|
7 |
+
_ADHD 10412
|
8 |
+
_Schizophrenia 10447
|
9 |
+
_Asperger 10470
|
10 |
+
_PTSD 10489
|
11 |
+
dtype: object
|
12 |
+
Validation set class counts after balancing:
|
13 |
+
_Borderline 1180
|
14 |
+
_Anxiety 1185
|
15 |
+
_Depression 1178
|
16 |
+
_Bipolar 1219
|
17 |
+
_OCD 1165
|
18 |
+
_ADHD 1166
|
19 |
+
_Schizophrenia 1131
|
20 |
+
_Asperger 1108
|
21 |
+
_PTSD 1089
|
22 |
+
dtype: object
|
23 |
+
Some weights of DistilBertForSequenceClassification were not initialized from the model checkpoint at distilbert/distilbert-base-uncased and are newly initialized: ['classifier.bias', 'classifier.weight', 'pre_classifier.bias', 'pre_classifier.weight']
|
24 |
+
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
|
25 |
+
Epoch 1, Train Loss: 0.2660, Val Loss: 0.2032
|
26 |
+
Epoch 2, Train Loss: 0.1891, Val Loss: 0.1873
|
27 |
+
F1 Score on Validation Set: 0.6356
|
28 |
+
AUC Score on Validation Set: 0.7643
|
29 |
+
|
30 |
+
|
31 |
+
Classification Report, AUC Score, F1 Score, and Losses
|
32 |
+
|
33 |
+
Train Losses: [0.2660091122228647, 0.18910447711386752]
|
34 |
+
Validation Losses: [0.20317846728614503, 0.18728890073445678]
|
35 |
+
F1 Score: [0.6355810277640191]
|
36 |
+
AUC Score: [0.7642971226283637]
|
37 |
+
Classification Report:
|
38 |
+
_Borderline:
|
39 |
+
Precision: 0.7606837606837606
|
40 |
+
Recall: 0.45254237288135596
|
41 |
+
F1-score: 0.5674814027630181
|
42 |
+
_Anxiety:
|
43 |
+
Precision: 0.7063318777292577
|
44 |
+
Recall: 0.5459915611814345
|
45 |
+
F1-score: 0.6158971918134221
|
46 |
+
_Depression:
|
47 |
+
Precision: 0.7286096256684492
|
48 |
+
Recall: 0.4626485568760611
|
49 |
+
F1-score: 0.5659397715472482
|
50 |
+
_Bipolar:
|
51 |
+
Precision: 0.7997076023391813
|
52 |
+
Recall: 0.44872846595570137
|
53 |
+
F1-score: 0.5748817656332107
|
54 |
+
_OCD:
|
55 |
+
Precision: 0.8222748815165877
|
56 |
+
Recall: 0.5957081545064378
|
57 |
+
F1-score: 0.6908909905425585
|
58 |
+
_ADHD:
|
59 |
+
Precision: 0.8856382978723404
|
60 |
+
Recall: 0.5711835334476844
|
61 |
+
F1-score: 0.6944734098018769
|
62 |
+
_Schizophrenia:
|
63 |
+
Precision: 0.7540628385698809
|
64 |
+
Recall: 0.6153846153846154
|
65 |
+
F1-score: 0.6777020447906524
|
66 |
+
_Asperger:
|
67 |
+
Precision: 0.6743515850144092
|
68 |
+
Recall: 0.6335740072202166
|
69 |
+
F1-score: 0.6533271288971615
|
70 |
+
_PTSD:
|
71 |
+
Precision: 0.7724687144482366
|
72 |
+
Recall: 0.6235078053259872
|
73 |
+
F1-score: 0.6900406504065041
|
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 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 1000000000000000019884624838656,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|