Hugging Face's logo

Ben10x
/
bert-base-medmentions

Token Classification
Transformers
Safetensors
bert
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Community
Ben10x commited on
Commit
f56accb
·
verified ·
1 Parent(s): f2fef2a

Model save

Browse files
Files changed (2) hide show
  1. README.md +26 -72
  2. model.safetensors +1 -1
README.md CHANGED
@@ -4,8 +4,6 @@ license: apache-2.0
4
  base_model: bert-base-uncased
5
  tags:
6
  - generated_from_trainer
7
- datasets:
8
- - Ben10x/MedMentions-NER
9
  metrics:
10
  - precision
11
  - recall
@@ -13,26 +11,7 @@ metrics:
13
  - accuracy
14
  model-index:
15
  - name: bert-base-medmentions
16
- results:
17
- - task:
18
- name: Token Classification
19
- type: token-classification
20
- dataset:
21
- name: Ben10x/MedMentions-NER
22
- type: Ben10x/MedMentions-NER
23
- metrics:
24
- - name: Precision
25
- type: precision
26
- value: 0.5765780071456927
27
- - name: Recall
28
- type: recall
29
- value: 0.6334612700628053
30
- - name: F1
31
- type: f1
32
- value: 0.6036826135749616
33
- - name: Accuracy
34
- type: accuracy
35
- value: 0.865718137671959
36
  ---
37
 
38
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -40,13 +19,13 @@ should probably proofread and complete it, then remove this comment. -->
40
 
41
  # bert-base-medmentions
42
 
43
- This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the Ben10x/MedMentions-NER dataset.
44
  It achieves the following results on the evaluation set:
45
- - Loss: 1.9495
46
- - Precision: 0.5766
47
- - Recall: 0.6335
48
- - F1: 0.6037
49
- - Accuracy: 0.8657
50
 
51
  ## Model description
52
 
@@ -72,53 +51,28 @@ The following hyperparameters were used during training:
72
  - optimizer: Use OptimizerNames.ADAFACTOR and the args are:
73
  No additional optimizer arguments
74
  - lr_scheduler_type: linear
75
- - num_epochs: 40.0
76
- - label_smoothing_factor: 0.3
77
 
78
  ### Training results
79
 
80
- | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
- |:-------------:|:-----:|:------:|:---------------:|:---------:|:------:|:------:|:--------:|
82
- | 1.9885 | 1.0 | 2911 | 1.9655 | 0.5352 | 0.6006 | 0.5660 | 0.8572 |
83
- | 1.9172 | 2.0 | 5822 | 1.9495 | 0.5766 | 0.6335 | 0.6037 | 0.8657 |
84
- | 1.8613 | 3.0 | 8733 | 1.9503 | 0.5823 | 0.6559 | 0.6169 | 0.8701 |
85
- | 1.8187 | 4.0 | 11644 | 1.9549 | 0.6169 | 0.6359 | 0.6263 | 0.8757 |
86
- | 1.7887 | 5.0 | 14555 | 1.9619 | 0.6254 | 0.6413 | 0.6333 | 0.8771 |
87
- | 1.7659 | 6.0 | 17466 | 1.9772 | 0.6189 | 0.6600 | 0.6388 | 0.8766 |
88
- | 1.7536 | 7.0 | 20377 | 1.9870 | 0.6279 | 0.6554 | 0.6413 | 0.8790 |
89
- | 1.7473 | 8.0 | 23288 | 1.9854 | 0.6435 | 0.6523 | 0.6479 | 0.8807 |
90
- | 1.7393 | 9.0 | 26199 | 1.9975 | 0.6267 | 0.6713 | 0.6482 | 0.8796 |
91
- | 1.7315 | 10.0 | 29110 | 2.0025 | 0.6374 | 0.6572 | 0.6472 | 0.8808 |
92
- | 1.7277 | 11.0 | 32021 | 2.0055 | 0.6311 | 0.6752 | 0.6524 | 0.8817 |
93
- | 1.7231 | 12.0 | 34932 | 2.0042 | 0.6491 | 0.6622 | 0.6556 | 0.8825 |
94
- | 1.7225 | 13.0 | 37843 | 2.0097 | 0.6317 | 0.6762 | 0.6532 | 0.8817 |
95
- | 1.717 | 14.0 | 40754 | 2.0131 | 0.6488 | 0.6627 | 0.6556 | 0.8814 |
96
- | 1.7152 | 15.0 | 43665 | 2.0191 | 0.6348 | 0.6751 | 0.6543 | 0.8815 |
97
- | 1.7154 | 16.0 | 46576 | 2.0230 | 0.6456 | 0.6666 | 0.6559 | 0.8818 |
98
- | 1.7121 | 17.0 | 49487 | 2.0243 | 0.6422 | 0.6710 | 0.6563 | 0.8831 |
99
- | 1.7114 | 18.0 | 52398 | 2.0195 | 0.6516 | 0.6621 | 0.6568 | 0.8838 |
100
- | 1.7105 | 19.0 | 55309 | 2.0255 | 0.6354 | 0.6810 | 0.6574 | 0.8828 |
101
- | 1.7086 | 20.0 | 58220 | 2.0267 | 0.6514 | 0.6733 | 0.6622 | 0.8841 |
102
- | 1.7077 | 21.0 | 61131 | 2.0343 | 0.6404 | 0.6789 | 0.6591 | 0.8828 |
103
- | 1.7075 | 22.0 | 64042 | 2.0259 | 0.6589 | 0.6706 | 0.6647 | 0.8860 |
104
- | 1.706 | 23.0 | 66953 | 2.0299 | 0.6497 | 0.6752 | 0.6622 | 0.8845 |
105
- | 1.7062 | 24.0 | 69864 | 2.0291 | 0.6585 | 0.6725 | 0.6654 | 0.8856 |
106
- | 1.7051 | 25.0 | 72775 | 2.0327 | 0.6571 | 0.6762 | 0.6665 | 0.8850 |
107
- | 1.7044 | 26.0 | 75686 | 2.0348 | 0.6505 | 0.6838 | 0.6668 | 0.8851 |
108
- | 1.704 | 27.0 | 78597 | 2.0347 | 0.6556 | 0.6729 | 0.6641 | 0.8855 |
109
- | 1.7041 | 28.0 | 81508 | 2.0391 | 0.6542 | 0.6778 | 0.6658 | 0.8848 |
110
- | 1.7044 | 29.0 | 84419 | 2.0384 | 0.6607 | 0.6761 | 0.6683 | 0.8850 |
111
- | 1.7038 | 30.0 | 87330 | 2.0361 | 0.6617 | 0.6765 | 0.6690 | 0.8862 |
112
- | 1.7043 | 31.0 | 90241 | 2.0370 | 0.6584 | 0.6792 | 0.6686 | 0.8862 |
113
- | 1.7027 | 32.0 | 93152 | 2.0346 | 0.6602 | 0.6844 | 0.6721 | 0.8875 |
114
- | 1.7026 | 33.0 | 96063 | 2.0374 | 0.6629 | 0.6813 | 0.6720 | 0.8871 |
115
- | 1.7025 | 34.0 | 98974 | 2.0388 | 0.6572 | 0.6849 | 0.6708 | 0.8862 |
116
- | 1.7024 | 35.0 | 101885 | 2.0370 | 0.6648 | 0.6800 | 0.6723 | 0.8873 |
117
- | 1.703 | 36.0 | 104796 | 2.0410 | 0.6660 | 0.6778 | 0.6719 | 0.8868 |
118
- | 1.7023 | 37.0 | 107707 | 2.0392 | 0.6653 | 0.6810 | 0.6730 | 0.8871 |
119
- | 1.7022 | 38.0 | 110618 | 2.0391 | 0.6627 | 0.6830 | 0.6727 | 0.8874 |
120
- | 1.7022 | 39.0 | 113529 | 2.0394 | 0.6614 | 0.6823 | 0.6717 | 0.8869 |
121
- | 1.7023 | 40.0 | 116440 | 2.0384 | 0.6641 | 0.6819 | 0.6729 | 0.8874 |
122
 
123
 
124
  ### Framework versions
 
4
  base_model: bert-base-uncased
5
  tags:
6
  - generated_from_trainer
 
 
7
  metrics:
8
  - precision
9
  - recall
 
11
  - accuracy
12
  model-index:
13
  - name: bert-base-medmentions
14
+ results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  ---
16
 
17
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
19
 
20
  # bert-base-medmentions
21
 
22
+ This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 1.6247
25
+ - Precision: 0.6473
26
+ - Recall: 0.6735
27
+ - F1: 0.6601
28
+ - Accuracy: 0.8847
29
 
30
  ## Model description
31
 
 
51
  - optimizer: Use OptimizerNames.ADAFACTOR and the args are:
52
  No additional optimizer arguments
53
  - lr_scheduler_type: linear
54
+ - num_epochs: 15.0
55
+ - label_smoothing_factor: 0.2
56
 
57
  ### Training results
58
 
59
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
60
+ |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
61
+ | 1.5686 | 1.0 | 2911 | 1.5440 | 0.5246 | 0.6123 | 0.5650 | 0.8550 |
62
+ | 1.4792 | 2.0 | 5822 | 1.5156 | 0.5821 | 0.6344 | 0.6071 | 0.8689 |
63
+ | 1.4111 | 3.0 | 8733 | 1.5191 | 0.5865 | 0.6494 | 0.6163 | 0.8714 |
64
+ | 1.356 | 4.0 | 11644 | 1.5293 | 0.6236 | 0.6403 | 0.6318 | 0.8777 |
65
+ | 1.3182 | 5.0 | 14555 | 1.5433 | 0.6283 | 0.6426 | 0.6354 | 0.8789 |
66
+ | 1.2919 | 6.0 | 17466 | 1.5671 | 0.6242 | 0.6628 | 0.6429 | 0.8794 |
67
+ | 1.2743 | 7.0 | 20377 | 1.5697 | 0.6356 | 0.6574 | 0.6463 | 0.8809 |
68
+ | 1.2633 | 8.0 | 23288 | 1.5806 | 0.6364 | 0.6699 | 0.6528 | 0.8813 |
69
+ | 1.2542 | 9.0 | 26199 | 1.5942 | 0.6278 | 0.6734 | 0.6498 | 0.8808 |
70
+ | 1.2457 | 10.0 | 29110 | 1.6076 | 0.6372 | 0.6634 | 0.6500 | 0.8814 |
71
+ | 1.2398 | 11.0 | 32021 | 1.6077 | 0.6414 | 0.6696 | 0.6552 | 0.8835 |
72
+ | 1.2377 | 12.0 | 34932 | 1.6135 | 0.6478 | 0.6759 | 0.6615 | 0.8847 |
73
+ | 1.2349 | 13.0 | 37843 | 1.6195 | 0.6433 | 0.6756 | 0.6590 | 0.8839 |
74
+ | 1.2328 | 14.0 | 40754 | 1.6228 | 0.6462 | 0.6726 | 0.6592 | 0.8845 |
75
+ | 1.231 | 15.0 | 43665 | 1.6247 | 0.6473 | 0.6735 | 0.6601 | 0.8847 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
 
77
 
78
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d69423b3f04d3ae9ab27ccc1197ed731b958fc2c28064fe0bcfe3d716a22b946
3
  size 435722204
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a251d4c76fd8b56560460a0ced994d5bbfe48cf3297749da1d18e276010b999c
3
  size 435722204