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
75ec409
·
1 Parent(s): ec414a8

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +28 -28
README.md CHANGED
@@ -16,11 +16,11 @@ should probably proofread and complete it, then remove this comment. -->
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: 2.4011
20
- - Macro f1: 0.3527
21
- - Weighted f1: 0.6956
22
- - Accuracy: 0.7177
23
- - Balanced accuracy: 0.3299
24
 
25
  ## Model description
26
 
@@ -39,9 +39,9 @@ More information needed
39
  ### Training hyperparameters
40
 
41
  The following hyperparameters were used during training:
42
- - learning_rate: 5e-05
43
- - train_batch_size: 16
44
- - eval_batch_size: 16
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
@@ -52,26 +52,26 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Macro f1 | Weighted f1 | Accuracy | Balanced accuracy |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------:|:--------:|:-----------------:|
55
- | 1.2992 | 1.0 | 250 | 1.1977 | 0.1984 | 0.6212 | 0.6979 | 0.2104 |
56
- | 1.1076 | 2.0 | 500 | 1.0809 | 0.2865 | 0.6479 | 0.6986 | 0.2924 |
57
- | 0.912 | 3.0 | 750 | 1.1359 | 0.2677 | 0.6718 | 0.6804 | 0.2882 |
58
- | 0.7969 | 4.0 | 1000 | 1.1522 | 0.2643 | 0.6840 | 0.7047 | 0.2692 |
59
- | 0.6313 | 5.0 | 1250 | 1.2438 | 0.3176 | 0.6856 | 0.6986 | 0.3149 |
60
- | 0.542 | 6.0 | 1500 | 1.3582 | 0.3212 | 0.6736 | 0.6872 | 0.3173 |
61
- | 0.4401 | 7.0 | 1750 | 1.4300 | 0.3472 | 0.6921 | 0.7024 | 0.3305 |
62
- | 0.382 | 8.0 | 2000 | 1.5530 | 0.3669 | 0.6965 | 0.7146 | 0.3480 |
63
- | 0.309 | 9.0 | 2250 | 1.7972 | 0.3390 | 0.6777 | 0.6986 | 0.3174 |
64
- | 0.2762 | 10.0 | 2500 | 1.7713 | 0.3745 | 0.6923 | 0.7161 | 0.3396 |
65
- | 0.242 | 11.0 | 2750 | 1.9214 | 0.3672 | 0.6982 | 0.7215 | 0.3373 |
66
- | 0.2112 | 12.0 | 3000 | 1.9624 | 0.3543 | 0.6917 | 0.7093 | 0.3310 |
67
- | 0.179 | 13.0 | 3250 | 2.0087 | 0.3658 | 0.6922 | 0.7078 | 0.3431 |
68
- | 0.1563 | 14.0 | 3500 | 2.1266 | 0.3554 | 0.7016 | 0.7237 | 0.3331 |
69
- | 0.1531 | 15.0 | 3750 | 2.2341 | 0.3479 | 0.6951 | 0.7123 | 0.3284 |
70
- | 0.115 | 16.0 | 4000 | 2.2671 | 0.3565 | 0.6970 | 0.7207 | 0.3308 |
71
- | 0.115 | 17.0 | 4250 | 2.3446 | 0.3547 | 0.6988 | 0.7199 | 0.3342 |
72
- | 0.0931 | 18.0 | 4500 | 2.3784 | 0.3570 | 0.6977 | 0.7169 | 0.3333 |
73
- | 0.0886 | 19.0 | 4750 | 2.3871 | 0.3557 | 0.6970 | 0.7169 | 0.3325 |
74
- | 0.0747 | 20.0 | 5000 | 2.4011 | 0.3527 | 0.6956 | 0.7177 | 0.3299 |
75
 
76
 
77
  ### Framework versions
 
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: 1.4194
20
+ - Macro f1: 0.3364
21
+ - Weighted f1: 0.6725
22
+ - Accuracy: 0.6804
23
+ - Balanced accuracy: 0.3323
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: 32
44
+ - eval_batch_size: 32
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Macro f1 | Weighted f1 | Accuracy | Balanced accuracy |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------:|:--------:|:-----------------:|
55
+ | 1.5192 | 1.0 | 125 | 1.3472 | 0.1654 | 0.5688 | 0.6682 | 0.1753 |
56
+ | 1.2145 | 2.0 | 250 | 1.2057 | 0.1824 | 0.5605 | 0.6088 | 0.2214 |
57
+ | 1.0542 | 3.0 | 375 | 1.1082 | 0.2704 | 0.6759 | 0.6865 | 0.2899 |
58
+ | 0.9415 | 4.0 | 500 | 1.1175 | 0.2565 | 0.6605 | 0.6781 | 0.2705 |
59
+ | 0.8555 | 5.0 | 625 | 1.0788 | 0.2700 | 0.6802 | 0.6903 | 0.2864 |
60
+ | 0.7929 | 6.0 | 750 | 1.1857 | 0.2523 | 0.6198 | 0.6187 | 0.2910 |
61
+ | 0.7124 | 7.0 | 875 | 1.1302 | 0.2671 | 0.6764 | 0.6865 | 0.2842 |
62
+ | 0.6624 | 8.0 | 1000 | 1.1157 | 0.2877 | 0.6909 | 0.7062 | 0.2921 |
63
+ | 0.6023 | 9.0 | 1125 | 1.1985 | 0.3128 | 0.6704 | 0.6758 | 0.3094 |
64
+ | 0.5433 | 10.0 | 1250 | 1.1837 | 0.3514 | 0.7048 | 0.7177 | 0.3348 |
65
+ | 0.4984 | 11.0 | 1375 | 1.2266 | 0.3391 | 0.6944 | 0.7040 | 0.3286 |
66
+ | 0.4692 | 12.0 | 1500 | 1.2620 | 0.3343 | 0.6786 | 0.6796 | 0.3317 |
67
+ | 0.4299 | 13.0 | 1625 | 1.3404 | 0.3337 | 0.6714 | 0.6781 | 0.3289 |
68
+ | 0.414 | 14.0 | 1750 | 1.3125 | 0.3517 | 0.6866 | 0.6948 | 0.3492 |
69
+ | 0.383 | 15.0 | 1875 | 1.3714 | 0.3324 | 0.6699 | 0.6743 | 0.3354 |
70
+ | 0.3706 | 16.0 | 2000 | 1.3334 | 0.3491 | 0.6937 | 0.7032 | 0.3412 |
71
+ | 0.3499 | 17.0 | 2125 | 1.3905 | 0.3379 | 0.6785 | 0.6849 | 0.3344 |
72
+ | 0.3613 | 18.0 | 2250 | 1.4032 | 0.3386 | 0.6783 | 0.6872 | 0.3335 |
73
+ | 0.3203 | 19.0 | 2375 | 1.4074 | 0.3422 | 0.6844 | 0.6903 | 0.3416 |
74
+ | 0.336 | 20.0 | 2500 | 1.4194 | 0.3364 | 0.6725 | 0.6804 | 0.3323 |
75
 
76
 
77
  ### Framework versions