adigo commited on
Commit
dfd56ba
1 Parent(s): 4471115

Training complete

Browse files
README.md CHANGED
@@ -26,16 +26,16 @@ model-index:
26
  metrics:
27
  - name: Precision
28
  type: precision
29
- value: 0.8066825775656324
30
  - name: Recall
31
  type: recall
32
- value: 0.8589580686149937
33
  - name: F1
34
  type: f1
35
- value: 0.832
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
@@ -45,11 +45,11 @@ should probably proofread and complete it, then remove this comment. -->
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: 0.0612
49
- - Precision: 0.8067
50
- - Recall: 0.8590
51
- - F1: 0.832
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
- | 0.1242 | 1.0 | 680 | 0.0521 | 0.7460 | 0.8399 | 0.7902 | 0.9825 |
84
- | 0.039 | 2.0 | 1360 | 0.0515 | 0.7891 | 0.8463 | 0.8167 | 0.9835 |
85
- | 0.0144 | 3.0 | 2040 | 0.0612 | 0.8067 | 0.8590 | 0.832 | 0.9839 |
86
 
87
 
88
  ### Framework versions
 
26
  metrics:
27
  - name: Precision
28
  type: precision
29
+ value: 0.8116805721096544
30
  - name: Recall
31
  type: recall
32
+ value: 0.8653113087674714
33
  - name: F1
34
  type: f1
35
+ value: 0.8376383763837638
36
  - name: Accuracy
37
  type: accuracy
38
+ value: 0.9840282291763395
39
  ---
40
 
41
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
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: 0.0621
49
+ - Precision: 0.8117
50
+ - Recall: 0.8653
51
+ - F1: 0.8376
52
+ - Accuracy: 0.9840
53
 
54
  ## Model description
55
 
 
80
 
81
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
82
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
83
+ | 0.1181 | 1.0 | 680 | 0.0523 | 0.7339 | 0.8272 | 0.7778 | 0.9824 |
84
+ | 0.0386 | 2.0 | 1360 | 0.0554 | 0.8112 | 0.8463 | 0.8284 | 0.9838 |
85
+ | 0.0145 | 3.0 | 2040 | 0.0621 | 0.8117 | 0.8653 | 0.8376 | 0.9840 |
86
 
87
 
88
  ### Framework versions
runs/Sep17_05-59-50_041092765f38/events.out.tfevents.1726552793.041092765f38.588.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bbe999fe6ed85d88bbee5bef262c5e73cf0baf73c5c595aa7be6efbdda0bd1d
3
- size 6770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4478525fb8c5c15c4e0772fb9c31c82bcee9214bd296db9be1b8b6aff85ccdae
3
+ size 7596