Umesh commited on
Commit
7f094e7
1 Parent(s): 7c15228

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +16 -14
README.md CHANGED
@@ -23,16 +23,16 @@ model-index:
23
  metrics:
24
  - name: Precision
25
  type: precision
26
- value: 0.8241758241758241
27
  - name: Recall
28
  type: recall
29
- value: 0.8576874205844981
30
  - name: F1
31
  type: f1
32
- value: 0.8405977584059776
33
  - name: Accuracy
34
  type: accuracy
35
- value: 0.985111585724456
36
  ---
37
 
38
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -42,11 +42,11 @@ should probably proofread and complete it, then remove this comment. -->
42
 
43
  This model is a fine-tuned version of [dmis-lab/biobert-base-cased-v1.2](https://huggingface.co/dmis-lab/biobert-base-cased-v1.2) on the ncbi_disease dataset.
44
  It achieves the following results on the evaluation set:
45
- - Loss: 0.0621
46
- - Precision: 0.8242
47
- - Recall: 0.8577
48
- - F1: 0.8406
49
- - Accuracy: 0.9851
50
 
51
  ## Model description
52
 
@@ -70,16 +70,18 @@ The following hyperparameters were used during training:
70
  - eval_batch_size: 8
71
  - seed: 42
72
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
73
- - lr_scheduler_type: linear
74
- - num_epochs: 3
75
 
76
  ### Training results
77
 
78
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
79
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
80
- | 0.0982 | 1.0 | 680 | 0.0582 | 0.7792 | 0.7891 | 0.7841 | 0.9818 |
81
- | 0.0426 | 2.0 | 1360 | 0.0564 | 0.8102 | 0.8463 | 0.8278 | 0.9848 |
82
- | 0.0123 | 3.0 | 2040 | 0.0621 | 0.8242 | 0.8577 | 0.8406 | 0.9851 |
 
 
83
 
84
 
85
  ### Framework versions
 
23
  metrics:
24
  - name: Precision
25
  type: precision
26
+ value: 0.8308823529411765
27
  - name: Recall
28
  type: recall
29
+ value: 0.8614993646759848
30
  - name: F1
31
  type: f1
32
+ value: 0.8459139114160948
33
  - name: Accuracy
34
  type: accuracy
35
+ value: 0.9845853839725137
36
  ---
37
 
38
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
42
 
43
  This model is a fine-tuned version of [dmis-lab/biobert-base-cased-v1.2](https://huggingface.co/dmis-lab/biobert-base-cased-v1.2) on the ncbi_disease dataset.
44
  It achieves the following results on the evaluation set:
45
+ - Loss: 0.0816
46
+ - Precision: 0.8309
47
+ - Recall: 0.8615
48
+ - F1: 0.8459
49
+ - Accuracy: 0.9846
50
 
51
  ## Model description
52
 
 
70
  - eval_batch_size: 8
71
  - seed: 42
72
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
73
+ - lr_scheduler_type: cosine_with_restarts
74
+ - num_epochs: 5
75
 
76
  ### Training results
77
 
78
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
79
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
80
+ | 0.0986 | 1.0 | 680 | 0.0657 | 0.7476 | 0.8018 | 0.7738 | 0.9806 |
81
+ | 0.0427 | 2.0 | 1360 | 0.0585 | 0.7726 | 0.8590 | 0.8135 | 0.9830 |
82
+ | 0.0127 | 3.0 | 2040 | 0.0616 | 0.8420 | 0.8602 | 0.8510 | 0.9849 |
83
+ | 0.0051 | 4.0 | 2720 | 0.0800 | 0.8317 | 0.8602 | 0.8457 | 0.9848 |
84
+ | 0.0041 | 5.0 | 3400 | 0.0816 | 0.8309 | 0.8615 | 0.8459 | 0.9846 |
85
 
86
 
87
  ### Framework versions