Shijia commited on
Commit
16c4910
1 Parent(s): b826379

Model save

Browse files
Files changed (1) hide show
  1. README.md +22 -22
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
- license: apache-2.0
3
- base_model: michiyasunaga/BioLinkBERT-base
4
  tags:
5
  - generated_from_trainer
6
  datasets:
@@ -25,16 +25,16 @@ model-index:
25
  metrics:
26
  - name: Accuracy
27
  type: accuracy
28
- value: 0.62
29
  - name: Precision
30
  type: precision
31
- value: 0.6273344651952462
32
  - name: Recall
33
  type: recall
34
- value: 0.62
35
  - name: F1
36
  type: f1
37
- value: 0.614448051948052
38
  ---
39
 
40
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -42,13 +42,13 @@ should probably proofread and complete it, then remove this comment. -->
42
 
43
  # run1
44
 
45
- This model is a fine-tuned version of [michiyasunaga/BioLinkBERT-base](https://huggingface.co/michiyasunaga/BioLinkBERT-base) on the sem_eval_2024_task_2 dataset.
46
  It achieves the following results on the evaluation set:
47
- - Loss: 0.6923
48
- - Accuracy: 0.62
49
- - Precision: 0.6273
50
- - Recall: 0.62
51
- - F1: 0.6144
52
 
53
  ## Model description
54
 
@@ -82,16 +82,16 @@ The following hyperparameters were used during training:
82
 
83
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
84
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
85
- | No log | 0.99 | 53 | 0.6893 | 0.55 | 0.5565 | 0.55 | 0.5366 |
86
- | 0.7034 | 2.0 | 107 | 0.6771 | 0.595 | 0.5986 | 0.595 | 0.5913 |
87
- | 0.7034 | 2.99 | 160 | 0.6680 | 0.585 | 0.5882 | 0.585 | 0.5812 |
88
- | 0.6769 | 4.0 | 214 | 0.6448 | 0.625 | 0.6271 | 0.625 | 0.6234 |
89
- | 0.6769 | 4.99 | 267 | 0.6465 | 0.625 | 0.6503 | 0.625 | 0.6085 |
90
- | 0.5962 | 6.0 | 321 | 0.6457 | 0.635 | 0.6456 | 0.635 | 0.6282 |
91
- | 0.5962 | 6.99 | 374 | 0.6595 | 0.63 | 0.6366 | 0.63 | 0.6255 |
92
- | 0.4977 | 8.0 | 428 | 0.6763 | 0.62 | 0.6273 | 0.62 | 0.6144 |
93
- | 0.4977 | 8.99 | 481 | 0.6831 | 0.63 | 0.6379 | 0.63 | 0.6246 |
94
- | 0.4268 | 9.91 | 530 | 0.6923 | 0.62 | 0.6273 | 0.62 | 0.6144 |
95
 
96
 
97
  ### Framework versions
 
1
  ---
2
+ license: mit
3
+ base_model: emilyalsentzer/Bio_ClinicalBERT
4
  tags:
5
  - generated_from_trainer
6
  datasets:
 
25
  metrics:
26
  - name: Accuracy
27
  type: accuracy
28
+ value: 0.6
29
  - name: Precision
30
  type: precision
31
+ value: 0.6000400160064026
32
  - name: Recall
33
  type: recall
34
+ value: 0.6
35
  - name: F1
36
  type: f1
37
+ value: 0.5999599959995999
38
  ---
39
 
40
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
42
 
43
  # run1
44
 
45
+ This model is a fine-tuned version of [emilyalsentzer/Bio_ClinicalBERT](https://huggingface.co/emilyalsentzer/Bio_ClinicalBERT) on the sem_eval_2024_task_2 dataset.
46
  It achieves the following results on the evaluation set:
47
+ - Loss: 0.6634
48
+ - Accuracy: 0.6
49
+ - Precision: 0.6000
50
+ - Recall: 0.6
51
+ - F1: 0.6000
52
 
53
  ## Model description
54
 
 
82
 
83
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
84
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
85
+ | No log | 0.99 | 53 | 0.6935 | 0.515 | 0.5177 | 0.515 | 0.4958 |
86
+ | 0.7014 | 2.0 | 107 | 0.6895 | 0.535 | 0.5363 | 0.535 | 0.5308 |
87
+ | 0.7014 | 2.99 | 160 | 0.6894 | 0.52 | 0.5267 | 0.52 | 0.488 |
88
+ | 0.6961 | 4.0 | 214 | 0.6846 | 0.575 | 0.5842 | 0.575 | 0.5631 |
89
+ | 0.6961 | 4.99 | 267 | 0.6837 | 0.535 | 0.5931 | 0.535 | 0.4490 |
90
+ | 0.687 | 6.0 | 321 | 0.6762 | 0.585 | 0.5852 | 0.585 | 0.5847 |
91
+ | 0.687 | 6.99 | 374 | 0.6738 | 0.58 | 0.58 | 0.58 | 0.58 |
92
+ | 0.6707 | 8.0 | 428 | 0.6677 | 0.59 | 0.5900 | 0.59 | 0.5900 |
93
+ | 0.6707 | 8.99 | 481 | 0.6670 | 0.575 | 0.5767 | 0.575 | 0.5726 |
94
+ | 0.653 | 9.91 | 530 | 0.6634 | 0.6 | 0.6000 | 0.6 | 0.6000 |
95
 
96
 
97
  ### Framework versions