Hugging Face's logo

racheltong
/
ClinicalBERT-mimic-phi-ner

Token Classification
Transformers
Safetensors
bert
Generated from Trainer
Model card Files
xet
 Community
racheltong commited on
Commit
537bf3c
·
verified ·
1 Parent(s): 8ea6cbc

Model save

Browse files
Files changed (2) hide show
  1. README.md +26 -24
  2. model.safetensors +1 -1
README.md CHANGED
@@ -19,22 +19,22 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [emilyalsentzer/Bio_ClinicalBERT](https://huggingface.co/emilyalsentzer/Bio_ClinicalBERT) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.0075
23
- - F1 Macro: 0.9461
24
- - F1 Weighted: 0.9461
25
- - Precision: 0.9200
26
- - Recall: 0.9737
27
- - F1 Name: 0.96
28
- - F1 Location: 0.93
29
  - F1 Phone: 0.93
30
- - F1 Date: 0.81
31
- - F1 Mrn: 0.78
32
- - F1 Account: 0.84
33
- - F1 Age Over 89: 0.5
34
- - F1 Device Id: 0.89
35
- - F1 Ssn: 0.79
36
- - F1 Url: 0.5
37
- - F1 Email: 1.0
38
 
39
  ## Model description
40
 
@@ -69,15 +69,17 @@ The following hyperparameters were used during training:
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 Weighted | Precision | Recall | F1 Name | F1 Location | F1 Phone | F1 Date | F1 Mrn | F1 Account | F1 Age Over 89 | F1 Device Id | F1 Ssn | F1 Url | F1 Email |
71
  |:-------------:|:------:|:----:|:---------------:|:--------:|:-----------:|:---------:|:------:|:-------:|:-----------:|:--------:|:-------:|:------:|:----------:|:--------------:|:------------:|:------:|:------:|:--------:|
72
- | 0.6574 | 0.2020 | 300 | 0.1811 | 0.5379 | 0.5379 | 0.4319 | 0.7128 | 0.61 | 0.34 | 0.38 | 0.2 | 0.13 | 0.2 | 0.18 | 0.0 | 0.0 | 0.0 | 0.0 |
73
- | 0.0919 | 0.4039 | 600 | 0.0339 | 0.7431 | 0.7431 | 0.6524 | 0.8632 | 0.83 | 0.57 | 0.55 | 0.22 | 0.51 | 0.35 | 0.06 | 0.18 | 0.12 | 0.0 | 0.22 |
74
- | 0.1265 | 0.6059 | 900 | 0.0161 | 0.8535 | 0.8535 | 0.7874 | 0.9316 | 0.92 | 0.7 | 0.77 | 0.35 | 0.63 | 0.33 | 0.09 | 0.1 | 0.21 | 0.0 | 0.57 |
75
- | 0.0502 | 0.8078 | 1200 | 0.0258 | 0.8752 | 0.8752 | 0.8199 | 0.9384 | 0.93 | 0.8 | 0.75 | 0.28 | 0.57 | 0.47 | 0.1 | 0.53 | 0.31 | 0.22 | 0.71 |
76
- | 0.0335 | 1.0094 | 1500 | 0.0105 | 0.9095 | 0.9095 | 0.8734 | 0.9487 | 0.94 | 0.87 | 0.85 | 0.44 | 0.63 | 0.71 | 0.13 | 0.29 | 0.71 | 0.31 | 0.88 |
77
- | 0.0069 | 1.2114 | 1800 | 0.0088 | 0.9424 | 0.9424 | 0.9175 | 0.9686 | 0.95 | 0.92 | 0.94 | 0.8 | 0.79 | 0.82 | 0.5 | 0.89 | 0.79 | 0.5 | 1.0 |
78
- | 0.0140 | 1.4133 | 2100 | 0.0086 | 0.9318 | 0.9318 | 0.8992 | 0.9669 | 0.95 | 0.91 | 0.92 | 0.67 | 0.77 | 0.82 | 0.5 | 0.89 | 0.79 | 0.5 | 1.0 |
79
- | 0.0101 | 1.6153 | 2400 | 0.0080 | 0.9466 | 0.9466 | 0.9211 | 0.9735 | 0.96 | 0.92 | 0.93 | 0.77 | 0.76 | 0.82 | 0.5 | 0.8 | 0.79 | 0.5 | 1.0 |
80
- | 0.0073 | 1.8172 | 2700 | 0.0075 | 0.9461 | 0.9461 | 0.9200 | 0.9737 | 0.96 | 0.93 | 0.93 | 0.81 | 0.78 | 0.84 | 0.5 | 0.89 | 0.79 | 0.5 | 1.0 |
 
 
81
 
82
 
83
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [emilyalsentzer/Bio_ClinicalBERT](https://huggingface.co/emilyalsentzer/Bio_ClinicalBERT) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.0017
23
+ - F1 Macro: 0.9441
24
+ - F1 Weighted: 0.9441
25
+ - Precision: 0.9140
26
+ - Recall: 0.9763
27
+ - F1 Name: 0.94
28
+ - F1 Location: 0.91
29
  - F1 Phone: 0.93
30
+ - F1 Date: 0.84
31
+ - F1 Mrn: 0.96
32
+ - F1 Account: 0.97
33
+ - F1 Age Over 89: 0.98
34
+ - F1 Device Id: 0.99
35
+ - F1 Ssn: 1.0
36
+ - F1 Url: 1.0
37
+ - F1 Email: 0.99
38
 
39
  ## Model description
40
 
 
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 Weighted | Precision | Recall | F1 Name | F1 Location | F1 Phone | F1 Date | F1 Mrn | F1 Account | F1 Age Over 89 | F1 Device Id | F1 Ssn | F1 Url | F1 Email |
71
  |:-------------:|:------:|:----:|:---------------:|:--------:|:-----------:|:---------:|:------:|:-------:|:-----------:|:--------:|:-------:|:------:|:----------:|:--------------:|:------------:|:------:|:------:|:--------:|
72
+ | 0.4470 | 0.1774 | 300 | 0.0868 | 0.3948 | 0.3948 | 0.2935 | 0.6032 | 0.46 | 0.33 | 0.41 | 0.04 | 0.46 | 0.4 | 0.08 | 0.58 | 0.32 | 0.0 | 0.31 |
73
+ | 0.0508 | 0.3547 | 600 | 0.0112 | 0.7449 | 0.7449 | 0.6654 | 0.8461 | 0.82 | 0.57 | 0.8 | 0.21 | 0.64 | 0.85 | 0.04 | 0.89 | 0.86 | 0.56 | 0.95 |
74
+ | 0.0302 | 0.5321 | 900 | 0.0131 | 0.8389 | 0.8389 | 0.7652 | 0.9284 | 0.88 | 0.72 | 0.86 | 0.27 | 0.59 | 0.98 | 0.84 | 0.9 | 0.92 | 0.93 | 0.99 |
75
+ | 0.0244 | 0.7094 | 1200 | 0.0046 | 0.8816 | 0.8816 | 0.8212 | 0.9517 | 0.9 | 0.81 | 0.81 | 0.48 | 0.75 | 0.97 | 0.95 | 0.97 | 0.98 | 1.0 | 1.0 |
76
+ | 0.0187 | 0.8868 | 1500 | 0.0030 | 0.9160 | 0.9160 | 0.8713 | 0.9656 | 0.93 | 0.82 | 0.87 | 0.52 | 0.89 | 0.95 | 0.96 | 0.96 | 1.0 | 1.0 | 1.0 |
77
+ | 0.0055 | 1.0638 | 1800 | 0.0030 | 0.9343 | 0.9343 | 0.8979 | 0.9737 | 0.94 | 0.89 | 0.9 | 0.57 | 0.92 | 0.97 | 0.98 | 0.99 | 1.0 | 1.0 | 1.0 |
78
+ | 0.0037 | 1.2412 | 2100 | 0.0027 | 0.9306 | 0.9306 | 0.8944 | 0.9697 | 0.93 | 0.89 | 0.9 | 0.74 | 0.92 | 0.98 | 0.98 | 0.99 | 1.0 | 1.0 | 1.0 |
79
+ | 0.0117 | 1.4186 | 2400 | 0.0025 | 0.9338 | 0.9338 | 0.8988 | 0.9716 | 0.94 | 0.88 | 0.89 | 0.8 | 0.94 | 0.97 | 0.98 | 0.99 | 1.0 | 1.0 | 0.99 |
80
+ | 0.0066 | 1.5959 | 2700 | 0.0020 | 0.9454 | 0.9454 | 0.9159 | 0.9769 | 0.95 | 0.9 | 0.93 | 0.83 | 0.96 | 0.98 | 0.99 | 0.99 | 1.0 | 1.0 | 0.99 |
81
+ | 0.0043 | 1.7733 | 3000 | 0.0018 | 0.9433 | 0.9433 | 0.9124 | 0.9763 | 0.94 | 0.9 | 0.93 | 0.82 | 0.96 | 0.97 | 0.99 | 0.99 | 1.0 | 1.0 | 0.99 |
82
+ | 0.0030 | 1.9506 | 3300 | 0.0017 | 0.9441 | 0.9441 | 0.9140 | 0.9763 | 0.94 | 0.91 | 0.93 | 0.84 | 0.96 | 0.97 | 0.98 | 0.99 | 1.0 | 1.0 | 0.99 |
83
 
84
 
85
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a54945b3cb288c202b429dcab7595d0a2696e27f7bf18fd9fb01ccd181bca6e7
3
  size 430972780
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f0b357c5000145f0a5384affdf81d3ea4c327c3d458308d4c8f8438e8bc4ee7
3
  size 430972780