Hugging Face's logo

vineetsharma
/
BioMedical_NER-maccrobat-distilbert

Token Classification
Transformers
PyTorch
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Community
1
vineetsharma commited on
Commit
2df0641
•
1 Parent(s): ef9f75d

Training complete

Browse files
Files changed (2) hide show
  1. README.md +69 -15
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -3,22 +3,14 @@ license: apache-2.0
3
  base_model: distilbert-base-uncased
4
  tags:
5
  - generated_from_trainer
 
 
 
 
 
6
  model-index:
7
  - name: BioMedical_NER-maccrobat-distilbert
8
  results: []
9
- widget:
10
- - text: "CASE: A 28-year-old previously healthy man presented with a 6-week history of palpitations.
11
- The symptoms occurred during rest, 2–3 times per week, lasted up to 30 minutes at a time and were associated with dyspnea.
12
- Except for a grade 2/6 holosystolic tricuspid regurgitation murmur (best heard at the left sternal border with inspiratory accentuation), physical examination yielded unremarkable findings."
13
- example_title: "example 1"
14
- - text: "A 63-year-old woman with no known cardiac history presented with a sudden onset of dyspnea requiring intubation and ventilatory support out of hospital.
15
- She denied preceding symptoms of chest discomfort, palpitations, syncope or infection.
16
- The patient was afebrile and normotensive, with a sinus tachycardia of 140 beats/min."
17
- example_title: "example 2"
18
- - text: "A 48 year-old female presented with vaginal bleeding and abnormal Pap smears.
19
- Upon diagnosis of invasive non-keratinizing SCC of the cervix, she underwent a radical hysterectomy with salpingo-oophorectomy which demonstrated positive spread to the pelvic lymph nodes and the parametrium.
20
- Pathological examination revealed that the tumour also extensively involved the lower uterine segment."
21
- example_title: "example 3"
22
  ---
23
 
24
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -27,6 +19,12 @@ should probably proofread and complete it, then remove this comment. -->
27
  # BioMedical_NER-maccrobat-distilbert
28
 
29
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 
 
 
 
 
 
30
 
31
  ## Model description
32
 
@@ -51,11 +49,67 @@ The following hyperparameters were used during training:
51
  - seed: 42
52
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
  - lr_scheduler_type: linear
54
- - num_epochs: 30
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
 
56
  ### Framework versions
57
 
58
  - Transformers 4.32.1
59
- - Pytorch 2.0.1+cu117
60
  - Datasets 2.14.4
61
  - Tokenizers 0.13.3
 
3
  base_model: distilbert-base-uncased
4
  tags:
5
  - generated_from_trainer
6
+ metrics:
7
+ - precision
8
+ - recall
9
+ - f1
10
+ - accuracy
11
  model-index:
12
  - name: BioMedical_NER-maccrobat-distilbert
13
  results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  ---
15
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
19
  # BioMedical_NER-maccrobat-distilbert
20
 
21
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.3622
24
+ - Precision: 0.8525
25
+ - Recall: 0.9225
26
+ - F1: 0.8861
27
+ - Accuracy: 0.9419
28
 
29
  ## Model description
30
 
 
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
+ - num_epochs: 50
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
+ | No log | 1.0 | 45 | 1.7742 | 0.6341 | 0.0055 | 0.0109 | 0.6272 |
59
+ | No log | 2.0 | 90 | 1.4622 | 0.3671 | 0.1659 | 0.2286 | 0.6546 |
60
+ | No log | 3.0 | 135 | 1.2643 | 0.3409 | 0.2941 | 0.3158 | 0.6742 |
61
+ | No log | 4.0 | 180 | 1.1501 | 0.4039 | 0.4283 | 0.4157 | 0.7028 |
62
+ | No log | 5.0 | 225 | 1.0938 | 0.4145 | 0.5229 | 0.4624 | 0.7098 |
63
+ | No log | 6.0 | 270 | 1.0439 | 0.4371 | 0.5780 | 0.4978 | 0.7257 |
64
+ | No log | 7.0 | 315 | 0.9442 | 0.4997 | 0.6147 | 0.5513 | 0.7583 |
65
+ | No log | 8.0 | 360 | 0.9376 | 0.5126 | 0.6591 | 0.5767 | 0.7629 |
66
+ | No log | 9.0 | 405 | 0.8024 | 0.5512 | 0.6753 | 0.6070 | 0.7921 |
67
+ | No log | 10.0 | 450 | 0.7367 | 0.5949 | 0.6842 | 0.6364 | 0.8121 |
68
+ | No log | 11.0 | 495 | 0.7276 | 0.5959 | 0.7209 | 0.6525 | 0.8222 |
69
+ | 1.0374 | 12.0 | 540 | 0.6606 | 0.6329 | 0.7289 | 0.6775 | 0.8369 |
70
+ | 1.0374 | 13.0 | 585 | 0.6466 | 0.6335 | 0.7530 | 0.6881 | 0.8423 |
71
+ | 1.0374 | 14.0 | 630 | 0.6825 | 0.6200 | 0.7716 | 0.6875 | 0.8397 |
72
+ | 1.0374 | 15.0 | 675 | 0.5721 | 0.6767 | 0.7777 | 0.7237 | 0.8657 |
73
+ | 1.0374 | 16.0 | 720 | 0.5446 | 0.6965 | 0.7876 | 0.7393 | 0.8771 |
74
+ | 1.0374 | 17.0 | 765 | 0.5136 | 0.7475 | 0.7881 | 0.7672 | 0.8872 |
75
+ | 1.0374 | 18.0 | 810 | 0.5248 | 0.7185 | 0.8218 | 0.7667 | 0.8866 |
76
+ | 1.0374 | 19.0 | 855 | 0.4944 | 0.7494 | 0.8284 | 0.7869 | 0.8961 |
77
+ | 1.0374 | 20.0 | 900 | 0.5092 | 0.7299 | 0.8391 | 0.7807 | 0.8920 |
78
+ | 1.0374 | 21.0 | 945 | 0.4491 | 0.7775 | 0.8393 | 0.8072 | 0.9083 |
79
+ | 1.0374 | 22.0 | 990 | 0.4400 | 0.7744 | 0.8537 | 0.8121 | 0.9104 |
80
+ | 0.3072 | 23.0 | 1035 | 0.4593 | 0.7689 | 0.8619 | 0.8128 | 0.9091 |
81
+ | 0.3072 | 24.0 | 1080 | 0.4547 | 0.7726 | 0.8670 | 0.8171 | 0.9094 |
82
+ | 0.3072 | 25.0 | 1125 | 0.4425 | 0.7825 | 0.8689 | 0.8234 | 0.9141 |
83
+ | 0.3072 | 26.0 | 1170 | 0.4229 | 0.7949 | 0.8712 | 0.8313 | 0.9184 |
84
+ | 0.3072 | 27.0 | 1215 | 0.4015 | 0.8192 | 0.8731 | 0.8453 | 0.9241 |
85
+ | 0.3072 | 28.0 | 1260 | 0.4222 | 0.7995 | 0.8771 | 0.8365 | 0.9197 |
86
+ | 0.3072 | 29.0 | 1305 | 0.4119 | 0.8017 | 0.8849 | 0.8413 | 0.9217 |
87
+ | 0.3072 | 30.0 | 1350 | 0.3960 | 0.8217 | 0.8864 | 0.8528 | 0.9276 |
88
+ | 0.3072 | 31.0 | 1395 | 0.3965 | 0.8204 | 0.8919 | 0.8547 | 0.9278 |
89
+ | 0.3072 | 32.0 | 1440 | 0.3936 | 0.8222 | 0.8972 | 0.8581 | 0.9282 |
90
+ | 0.3072 | 33.0 | 1485 | 0.3979 | 0.8263 | 0.8991 | 0.8612 | 0.9299 |
91
+ | 0.1369 | 34.0 | 1530 | 0.3799 | 0.8352 | 0.8989 | 0.8659 | 0.9333 |
92
+ | 0.1369 | 35.0 | 1575 | 0.3712 | 0.8407 | 0.9054 | 0.8718 | 0.9356 |
93
+ | 0.1369 | 36.0 | 1620 | 0.3648 | 0.8443 | 0.9046 | 0.8734 | 0.9368 |
94
+ | 0.1369 | 37.0 | 1665 | 0.3640 | 0.8414 | 0.9048 | 0.8719 | 0.9368 |
95
+ | 0.1369 | 38.0 | 1710 | 0.3632 | 0.8473 | 0.9088 | 0.8770 | 0.9385 |
96
+ | 0.1369 | 39.0 | 1755 | 0.3765 | 0.8369 | 0.9118 | 0.8727 | 0.9363 |
97
+ | 0.1369 | 40.0 | 1800 | 0.3686 | 0.8465 | 0.9107 | 0.8775 | 0.9382 |
98
+ | 0.1369 | 41.0 | 1845 | 0.3644 | 0.8461 | 0.9158 | 0.8796 | 0.9389 |
99
+ | 0.1369 | 42.0 | 1890 | 0.3676 | 0.8446 | 0.9156 | 0.8786 | 0.9390 |
100
+ | 0.1369 | 43.0 | 1935 | 0.3667 | 0.8451 | 0.9177 | 0.8799 | 0.9397 |
101
+ | 0.1369 | 44.0 | 1980 | 0.3622 | 0.8502 | 0.9189 | 0.8832 | 0.9407 |
102
+ | 0.0844 | 45.0 | 2025 | 0.3628 | 0.8535 | 0.9187 | 0.8849 | 0.9410 |
103
+ | 0.0844 | 46.0 | 2070 | 0.3677 | 0.8510 | 0.9198 | 0.8840 | 0.9406 |
104
+ | 0.0844 | 47.0 | 2115 | 0.3670 | 0.8521 | 0.9229 | 0.8861 | 0.9410 |
105
+ | 0.0844 | 48.0 | 2160 | 0.3627 | 0.8532 | 0.9227 | 0.8866 | 0.9417 |
106
+ | 0.0844 | 49.0 | 2205 | 0.3640 | 0.8511 | 0.9232 | 0.8857 | 0.9417 |
107
+ | 0.0844 | 50.0 | 2250 | 0.3622 | 0.8525 | 0.9225 | 0.8861 | 0.9419 |
108
+
109
 
110
  ### Framework versions
111
 
112
  - Transformers 4.32.1
113
+ - Pytorch 2.0.1+cu118
114
  - Datasets 2.14.4
115
  - Tokenizers 0.13.3
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc152553d6a8cac49c252b71105c59478970f0a8c247318a37211e59f1e17918
3
  size 265738597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be5deb7ea71545e7a7d23e66ce3b05eefa38ba0d5b84c19a8b1a6571e03e7c51
3
  size 265738597