Hugging Face's logo

marieke93
/
MiniLM-evidence-types

Text Classification
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
2
marieke93 commited on
Commit
0ea84df
•
1 Parent(s): 585323e

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +35 -1
README.md CHANGED
@@ -2,6 +2,8 @@
2
  license: mit
3
  tags:
4
  - generated_from_trainer
 
 
5
  model-index:
6
  - name: MiniLM-evidence-types
7
  results: []
@@ -13,6 +15,12 @@ should probably proofread and complete it, then remove this comment. -->
13
  # MiniLM-evidence-types
14
 
15
  This model is a fine-tuned version of [microsoft/MiniLM-L12-H384-uncased](https://huggingface.co/microsoft/MiniLM-L12-H384-uncased) on the None dataset.
 
 
 
 
 
 
16
 
17
  ## Model description
18
 
@@ -31,7 +39,7 @@ More information needed
31
  ### Training hyperparameters
32
 
33
  The following hyperparameters were used during training:
34
- - learning_rate: 5e-05
35
  - train_batch_size: 16
36
  - eval_batch_size: 16
37
  - seed: 42
@@ -40,6 +48,32 @@ The following hyperparameters were used during training:
40
  - num_epochs: 20
41
  - mixed_precision_training: Native AMP
42
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
43
  ### Framework versions
44
 
45
  - Transformers 4.19.2
 
2
  license: mit
3
  tags:
4
  - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
  model-index:
8
  - name: MiniLM-evidence-types
9
  results: []
 
15
  # MiniLM-evidence-types
16
 
17
  This model is a fine-tuned version of [microsoft/MiniLM-L12-H384-uncased](https://huggingface.co/microsoft/MiniLM-L12-H384-uncased) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 1.8672
20
+ - Macro f1: 0.3726
21
+ - Weighted f1: 0.7030
22
+ - Accuracy: 0.7161
23
+ - Balanced accuracy: 0.3616
24
 
25
  ## Model description
26
 
 
39
  ### Training hyperparameters
40
 
41
  The following hyperparameters were used during training:
42
+ - learning_rate: 2e-05
43
  - train_batch_size: 16
44
  - eval_batch_size: 16
45
  - seed: 42
 
48
  - num_epochs: 20
49
  - mixed_precision_training: Native AMP
50
 
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Macro f1 | Weighted f1 | Accuracy | Balanced accuracy |
54
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------:|:--------:|:-----------------:|
55
+ | 1.4108 | 1.0 | 250 | 1.2698 | 0.1966 | 0.6084 | 0.6735 | 0.2195 |
56
+ | 1.1452 | 2.0 | 500 | 1.0985 | 0.3484 | 0.6914 | 0.7116 | 0.3536 |
57
+ | 0.9711 | 3.0 | 750 | 1.0901 | 0.2606 | 0.6413 | 0.6446 | 0.2932 |
58
+ | 0.8437 | 4.0 | 1000 | 1.0197 | 0.2764 | 0.7024 | 0.7237 | 0.2783 |
59
+ | 0.7186 | 5.0 | 1250 | 1.0895 | 0.2847 | 0.6824 | 0.6963 | 0.2915 |
60
+ | 0.6312 | 6.0 | 1500 | 1.1296 | 0.3487 | 0.6888 | 0.6948 | 0.3377 |
61
+ | 0.5311 | 7.0 | 1750 | 1.1515 | 0.3591 | 0.6982 | 0.7024 | 0.3496 |
62
+ | 0.4737 | 8.0 | 2000 | 1.1962 | 0.3626 | 0.7185 | 0.7314 | 0.3415 |
63
+ | 0.4047 | 9.0 | 2250 | 1.3313 | 0.3121 | 0.6920 | 0.7085 | 0.3033 |
64
+ | 0.3753 | 10.0 | 2500 | 1.3993 | 0.3628 | 0.6976 | 0.7047 | 0.3495 |
65
+ | 0.3217 | 11.0 | 2750 | 1.5078 | 0.3560 | 0.6958 | 0.7055 | 0.3464 |
66
+ | 0.3079 | 12.0 | 3000 | 1.5875 | 0.3685 | 0.6968 | 0.7062 | 0.3514 |
67
+ | 0.2623 | 13.0 | 3250 | 1.6470 | 0.3606 | 0.6976 | 0.7070 | 0.3490 |
68
+ | 0.2393 | 14.0 | 3500 | 1.7164 | 0.3714 | 0.7069 | 0.7207 | 0.3551 |
69
+ | 0.2335 | 15.0 | 3750 | 1.8151 | 0.3597 | 0.6975 | 0.7123 | 0.3466 |
70
+ | 0.2255 | 16.0 | 4000 | 1.7838 | 0.3940 | 0.7034 | 0.7123 | 0.3869 |
71
+ | 0.213 | 17.0 | 4250 | 1.8328 | 0.3725 | 0.6964 | 0.7062 | 0.3704 |
72
+ | 0.1908 | 18.0 | 4500 | 1.8788 | 0.3708 | 0.7019 | 0.7154 | 0.3591 |
73
+ | 0.1734 | 19.0 | 4750 | 1.8574 | 0.3752 | 0.7031 | 0.7161 | 0.3619 |
74
+ | 0.1807 | 20.0 | 5000 | 1.8672 | 0.3726 | 0.7030 | 0.7161 | 0.3616 |
75
+
76
+
77
  ### Framework versions
78
 
79
  - Transformers 4.19.2