Hugging Face's logo

hung200504
/
CliBert-20

Question Answering
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
hung200504 commited on
Commit
a4df883
•
1 Parent(s): a4781c8

bert-cased

Browse files
Files changed (3) hide show
  1. README.md +35 -35
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [emilyalsentzer/Bio_ClinicalBERT](https://huggingface.co/emilyalsentzer/Bio_ClinicalBERT) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 5.8847
19
 
20
  ## Model description
21
 
@@ -34,7 +34,7 @@ More information needed
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
- - learning_rate: 0.0001
38
  - train_batch_size: 16
39
  - eval_batch_size: 16
40
  - seed: 42
@@ -46,39 +46,39 @@ The following hyperparameters were used during training:
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
- | 5.8842 | 0.09 | 5 | 5.9152 |
50
- | 5.7961 | 0.18 | 10 | 5.9106 |
51
- | 5.7777 | 0.27 | 15 | 5.9060 |
52
- | 5.7638 | 0.36 | 20 | 5.9016 |
53
- | 5.7282 | 0.45 | 25 | 5.8980 |
54
- | 5.6804 | 0.55 | 30 | 5.8942 |
55
- | 5.6095 | 0.64 | 35 | 5.8912 |
56
- | 5.5418 | 0.73 | 40 | 5.8890 |
57
- | 5.5853 | 0.82 | 45 | 5.8864 |
58
- | 5.55 | 0.91 | 50 | 5.8844 |
59
- | 5.5284 | 1.0 | 55 | 5.8828 |
60
- | 5.4085 | 1.09 | 60 | 5.8818 |
61
- | 5.368 | 1.18 | 65 | 5.8812 |
62
- | 5.4048 | 1.27 | 70 | 5.8807 |
63
- | 5.4172 | 1.36 | 75 | 5.8802 |
64
- | 5.4134 | 1.45 | 80 | 5.8796 |
65
- | 5.4728 | 1.55 | 85 | 5.8791 |
66
- | 5.3326 | 1.64 | 90 | 5.8787 |
67
- | 5.3464 | 1.73 | 95 | 5.8789 |
68
- | 5.3447 | 1.82 | 100 | 5.8791 |
69
- | 5.3264 | 1.91 | 105 | 5.8793 |
70
- | 5.2265 | 2.0 | 110 | 5.8797 |
71
- | 5.1223 | 2.09 | 115 | 5.8803 |
72
- | 5.232 | 2.18 | 120 | 5.8811 |
73
- | 5.3772 | 2.27 | 125 | 5.8815 |
74
- | 5.2502 | 2.36 | 130 | 5.8821 |
75
- | 5.2293 | 2.45 | 135 | 5.8825 |
76
- | 5.1182 | 2.55 | 140 | 5.8832 |
77
- | 5.0885 | 2.64 | 145 | 5.8839 |
78
- | 5.157 | 2.73 | 150 | 5.8844 |
79
- | 5.3388 | 2.82 | 155 | 5.8845 |
80
- | 5.2609 | 2.91 | 160 | 5.8846 |
81
- | 5.2008 | 3.0 | 165 | 5.8847 |
82
 
83
 
84
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [emilyalsentzer/Bio_ClinicalBERT](https://huggingface.co/emilyalsentzer/Bio_ClinicalBERT) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 5.9825
19
 
20
  ## Model description
21
 
 
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
+ - learning_rate: 2e-05
38
  - train_batch_size: 16
39
  - eval_batch_size: 16
40
  - seed: 42
 
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | 5.9707 | 0.09 | 5 | 6.0008 |
50
+ | 5.9661 | 0.18 | 10 | 5.9998 |
51
+ | 5.9659 | 0.27 | 15 | 5.9987 |
52
+ | 5.9441 | 0.36 | 20 | 5.9974 |
53
+ | 5.9937 | 0.45 | 25 | 5.9965 |
54
+ | 5.9483 | 0.55 | 30 | 5.9953 |
55
+ | 5.9214 | 0.64 | 35 | 5.9945 |
56
+ | 5.9332 | 0.73 | 40 | 5.9937 |
57
+ | 5.9383 | 0.82 | 45 | 5.9926 |
58
+ | 5.9223 | 0.91 | 50 | 5.9919 |
59
+ | 5.9233 | 1.0 | 55 | 5.9911 |
60
+ | 5.8762 | 1.09 | 60 | 5.9905 |
61
+ | 5.8967 | 1.18 | 65 | 5.9899 |
62
+ | 5.9024 | 1.27 | 70 | 5.9891 |
63
+ | 5.9122 | 1.36 | 75 | 5.9885 |
64
+ | 5.902 | 1.45 | 80 | 5.9879 |
65
+ | 5.874 | 1.55 | 85 | 5.9872 |
66
+ | 5.8774 | 1.64 | 90 | 5.9867 |
67
+ | 5.8782 | 1.73 | 95 | 5.9862 |
68
+ | 5.8664 | 1.82 | 100 | 5.9857 |
69
+ | 5.8833 | 1.91 | 105 | 5.9852 |
70
+ | 5.8488 | 2.0 | 110 | 5.9848 |
71
+ | 5.8747 | 2.09 | 115 | 5.9843 |
72
+ | 5.8333 | 2.18 | 120 | 5.9840 |
73
+ | 5.8573 | 2.27 | 125 | 5.9837 |
74
+ | 5.8398 | 2.36 | 130 | 5.9834 |
75
+ | 5.8371 | 2.45 | 135 | 5.9832 |
76
+ | 5.8274 | 2.55 | 140 | 5.9831 |
77
+ | 5.863 | 2.64 | 145 | 5.9829 |
78
+ | 5.8183 | 2.73 | 150 | 5.9827 |
79
+ | 5.8448 | 2.82 | 155 | 5.9826 |
80
+ | 5.9111 | 2.91 | 160 | 5.9825 |
81
+ | 5.8316 | 3.0 | 165 | 5.9825 |
82
 
83
 
84
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb00cbf12b875c9ef7520c84b36703983ec1b755c76ff02351a0597c1e332257
3
  size 430952617
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5aadac48788e07a39334e64f3203ffade099c2c9cc37650dba3230a41b0cbdf
3
  size 430952617
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6e07b50a456386531fe72ea0acf086656e80fdc669ee7ae5b03a232ca753d23
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7c56e46b7375cf3682e27820e628153848b0387ac5aab8a8d6e32e4ce0e68d0
3
  size 4091