Hugging Face's logo

hebashakeel
/
bert-wellness-classifier

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
Metrics Community
hebashakeel commited on
Commit
cd48d82
·
verified ·
1 Parent(s): 493161f

End of training

Browse files
Files changed (6) hide show
  1. README.md +31 -27
  2. config.json +12 -8
  3. model.safetensors +2 -2
  4. runs/Feb17_03-54-50_8dab684b9a4e/events.out.tfevents.1739764492.8dab684b9a4e.30.0 +3 -0
  5. runs/Feb17_03-54-50_8dab684b9a4e/events.out.tfevents.1739764616.8dab684b9a4e.30.1 +3 -0
  6. training_args.bin +1 -1
README.md CHANGED
@@ -18,17 +18,21 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.7555
22
- - Accuracy: 0.714
23
- - Auc: 0.894
24
- - Precision Class 0: 0.771
25
- - Precision Class 1: 0.789
26
- - Precision Class 2: 0.78
27
- - Precision Class 3: 0.653
28
- - Recall Class 0: 0.698
29
- - Recall Class 1: 0.556
30
- - Recall Class 2: 0.619
31
- - Recall Class 3: 0.827
 
 
 
 
32
 
33
  ## Model description
34
 
@@ -47,9 +51,9 @@ More information needed
47
  ### Training hyperparameters
48
 
49
  The following hyperparameters were used during training:
50
- - learning_rate: 0.0002
51
- - train_batch_size: 8
52
- - eval_batch_size: 8
53
  - seed: 42
54
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
55
  - lr_scheduler_type: linear
@@ -57,23 +61,23 @@ The following hyperparameters were used during training:
57
 
58
  ### Training results
59
 
60
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | Auc | Precision Class 0 | Precision Class 1 | Precision Class 2 | Precision Class 3 | Recall Class 0 | Recall Class 1 | Recall Class 2 | Recall Class 3 |
61
- |:-------------:|:-----:|:----:|:---------------:|:--------:|:-----:|:-----------------:|:-----------------:|:-----------------:|:-----------------:|:--------------:|:--------------:|:--------------:|:--------------:|
62
- | 1.1543 | 1.0 | 140 | 1.0293 | 0.568 | 0.835 | 0.767 | 1.0 | 0.447 | 0.587 | 0.434 | 0.296 | 0.667 | 0.653 |
63
- | 0.9519 | 2.0 | 280 | 0.9149 | 0.585 | 0.86 | 0.738 | 1.0 | 0.613 | 0.528 | 0.585 | 0.185 | 0.302 | 0.878 |
64
- | 0.8294 | 3.0 | 420 | 0.7950 | 0.676 | 0.88 | 0.74 | 0.824 | 0.606 | 0.67 | 0.698 | 0.519 | 0.683 | 0.704 |
65
- | 0.7821 | 4.0 | 560 | 0.8809 | 0.598 | 0.882 | 0.87 | 0.727 | 0.604 | 0.545 | 0.377 | 0.296 | 0.508 | 0.857 |
66
- | 0.7349 | 5.0 | 700 | 0.7576 | 0.701 | 0.892 | 0.809 | 0.789 | 0.714 | 0.639 | 0.717 | 0.556 | 0.635 | 0.776 |
67
- | 0.7173 | 6.0 | 840 | 0.7700 | 0.689 | 0.89 | 0.76 | 0.824 | 0.744 | 0.626 | 0.717 | 0.519 | 0.508 | 0.837 |
68
- | 0.7048 | 7.0 | 980 | 0.7977 | 0.68 | 0.892 | 0.822 | 0.842 | 0.793 | 0.595 | 0.698 | 0.593 | 0.365 | 0.898 |
69
- | 0.6776 | 8.0 | 1120 | 0.7654 | 0.705 | 0.892 | 0.745 | 0.8 | 0.778 | 0.648 | 0.717 | 0.593 | 0.556 | 0.827 |
70
- | 0.6649 | 9.0 | 1260 | 0.7612 | 0.718 | 0.895 | 0.837 | 0.789 | 0.78 | 0.643 | 0.679 | 0.556 | 0.619 | 0.847 |
71
- | 0.676 | 10.0 | 1400 | 0.7555 | 0.714 | 0.894 | 0.771 | 0.789 | 0.78 | 0.653 | 0.698 | 0.556 | 0.619 | 0.827 |
72
 
73
 
74
  ### Framework versions
75
 
76
  - Transformers 4.45.1
77
- - Pytorch 2.4.0+cpu
78
  - Datasets 3.0.1
79
  - Tokenizers 0.20.0
 
18
 
19
  This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.9911
22
+ - Accuracy: 0.634
23
+ - Auc: 0.886
24
+ - Precision Class 0: 0.368
25
+ - Precision Class 1: 0.76
26
+ - Precision Class 2: 0.394
27
+ - Precision Class 3: 0.706
28
+ - Precision Class 4: 0.794
29
+ - Precision Class 5: 0.455
30
+ - Recall Class 0: 0.368
31
+ - Recall Class 1: 0.826
32
+ - Recall Class 2: 0.481
33
+ - Recall Class 3: 0.766
34
+ - Recall Class 4: 0.781
35
+ - Recall Class 5: 0.303
36
 
37
  ## Model description
38
 
 
51
  ### Training hyperparameters
52
 
53
  The following hyperparameters were used during training:
54
+ - learning_rate: 0.001
55
+ - train_batch_size: 16
56
+ - eval_batch_size: 16
57
  - seed: 42
58
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
  - lr_scheduler_type: linear
 
61
 
62
  ### Training results
63
 
64
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Auc | Precision Class 0 | Precision Class 1 | Precision Class 2 | Precision Class 3 | Precision Class 4 | Precision Class 5 | Recall Class 0 | Recall Class 1 | Recall Class 2 | Recall Class 3 | Recall Class 4 | Recall Class 5 |
65
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:-----:|:-----------------:|:-----------------:|:-----------------:|:-----------------:|:-----------------:|:-----------------:|:--------------:|:--------------:|:--------------:|:--------------:|:--------------:|:--------------:|
66
+ | 1.487 | 1.0 | 62 | 1.1345 | 0.547 | 0.863 | 0.471 | 0.727 | 0.0 | 0.783 | 0.646 | 0.306 | 0.32 | 0.4 | 0.0 | 0.857 | 0.627 | 0.611 |
67
+ | 1.137 | 2.0 | 124 | 1.1035 | 0.561 | 0.871 | 0.667 | 0.593 | 0.417 | 0.853 | 0.722 | 0.329 | 0.16 | 0.8 | 0.227 | 0.69 | 0.582 | 0.722 |
68
+ | 1.0435 | 3.0 | 186 | 0.9909 | 0.608 | 0.88 | 0.361 | 0.75 | 0.435 | 0.795 | 0.676 | 0.474 | 0.52 | 0.6 | 0.455 | 0.833 | 0.746 | 0.25 |
69
+ | 0.9615 | 4.0 | 248 | 1.0186 | 0.623 | 0.884 | 0.667 | 0.917 | 0.385 | 0.796 | 0.554 | 0.455 | 0.4 | 0.55 | 0.227 | 0.929 | 0.925 | 0.139 |
70
+ | 0.8951 | 5.0 | 310 | 0.9772 | 0.613 | 0.884 | 0.692 | 0.68 | 0.429 | 0.791 | 0.712 | 0.345 | 0.36 | 0.85 | 0.136 | 0.81 | 0.701 | 0.556 |
71
+ | 0.8591 | 6.0 | 372 | 0.9818 | 0.642 | 0.879 | 0.483 | 0.923 | 0.6 | 0.892 | 0.655 | 0.389 | 0.56 | 0.6 | 0.273 | 0.786 | 0.851 | 0.389 |
72
+ | 0.8471 | 7.0 | 434 | 0.9825 | 0.646 | 0.885 | 0.5 | 0.923 | 0.474 | 0.8 | 0.671 | 0.409 | 0.56 | 0.6 | 0.409 | 0.857 | 0.851 | 0.25 |
73
+ | 0.8187 | 8.0 | 496 | 0.9950 | 0.637 | 0.884 | 0.471 | 0.652 | 0.556 | 0.833 | 0.688 | 0.333 | 0.64 | 0.75 | 0.455 | 0.833 | 0.791 | 0.167 |
74
+ | 0.772 | 9.0 | 558 | 0.9836 | 0.618 | 0.884 | 0.5 | 0.812 | 0.435 | 0.755 | 0.73 | 0.359 | 0.44 | 0.65 | 0.455 | 0.881 | 0.687 | 0.389 |
75
+ | 0.7256 | 10.0 | 620 | 0.9703 | 0.642 | 0.883 | 0.538 | 0.765 | 0.4 | 0.795 | 0.701 | 0.435 | 0.56 | 0.65 | 0.455 | 0.833 | 0.806 | 0.278 |
76
 
77
 
78
  ### Framework versions
79
 
80
  - Transformers 4.45.1
81
+ - Pytorch 2.4.0
82
  - Datasets 3.0.1
83
  - Tokenizers 0.20.0
config.json CHANGED
@@ -10,18 +10,22 @@
10
  "hidden_dropout_prob": 0.1,
11
  "hidden_size": 768,
12
  "id2label": {
13
- "0": "PA",
14
- "1": "IVA",
15
- "2": "SA",
16
- "3": "SEA"
 
 
17
  },
18
  "initializer_range": 0.02,
19
  "intermediate_size": 3072,
20
  "label2id": {
21
- "IVA": 1,
22
- "PA": 0,
23
- "SA": 2,
24
- "SEA": 3
 
 
25
  },
26
  "layer_norm_eps": 1e-12,
27
  "max_position_embeddings": 512,
 
10
  "hidden_dropout_prob": 0.1,
11
  "hidden_size": 768,
12
  "id2label": {
13
+ "0": "Intellectual Aspect",
14
+ "1": "Vocational Aspect",
15
+ "2": "Spiritual Aspect",
16
+ "3": "Physical Aspect",
17
+ "4": "Social Aspect",
18
+ "5": "Emotional Aspect"
19
  },
20
  "initializer_range": 0.02,
21
  "intermediate_size": 3072,
22
  "label2id": {
23
+ "Emotional Aspect": 5,
24
+ "Intellectual Aspect": 0,
25
+ "Physical Aspect": 3,
26
+ "Social Aspect": 4,
27
+ "Spiritual Aspect": 2,
28
+ "Vocational Aspect": 1
29
  },
30
  "layer_norm_eps": 1e-12,
31
  "max_position_embeddings": 512,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4cf1b12ac4188061a1b95939442a7c108f381568361d53d7ef5a043d7dca0006
3
- size 437964800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8e37f25161ee81184b11fc254236f2fe1378b19c21e9b18dcac4356a24b3f2c
3
+ size 437970952
runs/Feb17_03-54-50_8dab684b9a4e/events.out.tfevents.1739764492.8dab684b9a4e.30.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a71a2722b03a2406ac46808360f3acc10a4d228285f1190c98efee741716231c
3
+ size 18607
runs/Feb17_03-54-50_8dab684b9a4e/events.out.tfevents.1739764616.8dab684b9a4e.30.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6f5d09e0c9936fc368fc7c60d57b17d3e32527c035a9b6e8f776d587cc165c5
3
+ size 1172
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a70b78afccdcdf8177875748299d08ca590587387f997ad402e337418bc7479
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e782049f7b3cb890a3fa6c9e68ca472b303bd795d3a91d42c453a28fc2c059c
3
  size 5240