elopezlopez commited on
Commit
d393dff
·
1 Parent(s): ea22ef8

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +83 -0
README.md ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - f1
7
+ model-index:
8
+ - name: Bio_ClinicalBERT_fold_2_ternary_v1
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # Bio_ClinicalBERT_fold_2_ternary_v1
16
+
17
+ This model is a fine-tuned version of [emilyalsentzer/Bio_ClinicalBERT](https://huggingface.co/emilyalsentzer/Bio_ClinicalBERT) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 1.8379
20
+ - F1: 0.7970
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 2e-05
40
+ - train_batch_size: 16
41
+ - eval_batch_size: 16
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - num_epochs: 25
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss | F1 |
50
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
51
+ | No log | 1.0 | 294 | 0.5573 | 0.7645 |
52
+ | 0.558 | 2.0 | 588 | 0.4940 | 0.8133 |
53
+ | 0.558 | 3.0 | 882 | 0.6569 | 0.7984 |
54
+ | 0.2332 | 4.0 | 1176 | 0.9006 | 0.7943 |
55
+ | 0.2332 | 5.0 | 1470 | 1.0598 | 0.7943 |
56
+ | 0.1016 | 6.0 | 1764 | 1.2016 | 0.8011 |
57
+ | 0.0374 | 7.0 | 2058 | 1.2670 | 0.7970 |
58
+ | 0.0374 | 8.0 | 2352 | 1.3962 | 0.8065 |
59
+ | 0.0196 | 9.0 | 2646 | 1.3871 | 0.8092 |
60
+ | 0.0196 | 10.0 | 2940 | 1.4636 | 0.8106 |
61
+ | 0.0113 | 11.0 | 3234 | 1.4908 | 0.8065 |
62
+ | 0.008 | 12.0 | 3528 | 1.5714 | 0.7930 |
63
+ | 0.008 | 13.0 | 3822 | 1.5383 | 0.8119 |
64
+ | 0.0056 | 14.0 | 4116 | 1.5784 | 0.8106 |
65
+ | 0.0056 | 15.0 | 4410 | 1.7421 | 0.7957 |
66
+ | 0.0084 | 16.0 | 4704 | 1.7423 | 0.8011 |
67
+ | 0.0084 | 17.0 | 4998 | 1.7502 | 0.7984 |
68
+ | 0.0023 | 18.0 | 5292 | 1.8131 | 0.7943 |
69
+ | 0.0057 | 19.0 | 5586 | 1.7784 | 0.8024 |
70
+ | 0.0057 | 20.0 | 5880 | 1.8324 | 0.8011 |
71
+ | 0.0023 | 21.0 | 6174 | 1.8269 | 0.8051 |
72
+ | 0.0023 | 22.0 | 6468 | 1.8622 | 0.7916 |
73
+ | 0.0018 | 23.0 | 6762 | 1.8553 | 0.7957 |
74
+ | 0.0024 | 24.0 | 7056 | 1.8445 | 0.7943 |
75
+ | 0.0024 | 25.0 | 7350 | 1.8379 | 0.7970 |
76
+
77
+
78
+ ### Framework versions
79
+
80
+ - Transformers 4.21.0
81
+ - Pytorch 1.12.0+cu113
82
+ - Datasets 2.4.0
83
+ - Tokenizers 0.12.1