adigo commited on
Commit
3d99b87
1 Parent(s): 121659b

Training complete

Browse files
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
  library_name: transformers
3
- license: mit
4
- base_model: emilyalsentzer/Bio_ClinicalBERT
5
  tags:
6
  - generated_from_trainer
7
  datasets:
@@ -26,16 +26,16 @@ model-index:
26
  metrics:
27
  - name: Precision
28
  type: precision
29
- value: 0.8098676293622142
30
  - name: Recall
31
  type: recall
32
- value: 0.855146124523507
33
  - name: F1
34
  type: f1
35
- value: 0.8318912237330038
36
  - name: Accuracy
37
  type: accuracy
38
- value: 0.9839353700436438
39
  ---
40
 
41
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -43,13 +43,13 @@ should probably proofread and complete it, then remove this comment. -->
43
 
44
  # bert-finetuned-ner
45
 
46
- This model is a fine-tuned version of [emilyalsentzer/Bio_ClinicalBERT](https://huggingface.co/emilyalsentzer/Bio_ClinicalBERT) on the ncbi_disease dataset.
47
  It achieves the following results on the evaluation set:
48
- - Loss: 0.0627
49
- - Precision: 0.8099
50
- - Recall: 0.8551
51
- - F1: 0.8319
52
- - Accuracy: 0.9839
53
 
54
  ## Model description
55
 
@@ -80,9 +80,9 @@ The following hyperparameters were used during training:
80
 
81
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
82
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
83
- | 0.1222 | 1.0 | 680 | 0.0522 | 0.7460 | 0.8247 | 0.7833 | 0.9828 |
84
- | 0.0392 | 2.0 | 1360 | 0.0542 | 0.7956 | 0.8361 | 0.8154 | 0.9837 |
85
- | 0.0149 | 3.0 | 2040 | 0.0627 | 0.8099 | 0.8551 | 0.8319 | 0.9839 |
86
 
87
 
88
  ### Framework versions
 
1
  ---
2
  library_name: transformers
3
+ license: apache-2.0
4
+ base_model: bert-base-cased
5
  tags:
6
  - generated_from_trainer
7
  datasets:
 
26
  metrics:
27
  - name: Precision
28
  type: precision
29
+ value: 0.7791907514450868
30
  - name: Recall
31
  type: recall
32
+ value: 0.8564167725540025
33
  - name: F1
34
  type: f1
35
+ value: 0.8159806295399515
36
  - name: Accuracy
37
  type: accuracy
38
+ value: 0.9823540395867049
39
  ---
40
 
41
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
43
 
44
  # bert-finetuned-ner
45
 
46
+ This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the ncbi_disease dataset.
47
  It achieves the following results on the evaluation set:
48
+ - Loss: 0.0713
49
+ - Precision: 0.7792
50
+ - Recall: 0.8564
51
+ - F1: 0.8160
52
+ - Accuracy: 0.9824
53
 
54
  ## Model description
55
 
 
80
 
81
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
82
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
83
+ | 0.1175 | 1.0 | 680 | 0.0609 | 0.7252 | 0.8183 | 0.7690 | 0.9815 |
84
+ | 0.0437 | 2.0 | 1360 | 0.0603 | 0.7489 | 0.8450 | 0.7940 | 0.9821 |
85
+ | 0.016 | 3.0 | 2040 | 0.0713 | 0.7792 | 0.8564 | 0.8160 | 0.9824 |
86
 
87
 
88
  ### Framework versions
runs/Sep12_06-49-10_0f6714f4ef72/events.out.tfevents.1726123751.0f6714f4ef72.625.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3af2daf6fca186618e4ab0416d7e0aaa3508672af3633d2466cb458f623b35d
3
- size 6837
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:723e9a081aa5278d38717a274c9814f7598afd826b1bcaa98851a962812e029d
3
+ size 7663