Hugging Face's logo

kanak8278
/
electra-base-ner-food-recipe-v2

Token Classification
Transformers
PyTorch
TensorBoard
electra
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
kanak8278 commited on
Commit
d7567ee
•
1 Parent(s): c3795a6

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +19 -34
README.md CHANGED
@@ -1,5 +1,4 @@
1
  ---
2
- license: apache-2.0
3
  tags:
4
  - generated_from_trainer
5
  metrics:
@@ -17,13 +16,13 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  # electra-base-ner-food-recipe-v2
19
 
20
- This model is a fine-tuned version of [google/electra-base-discriminator](https://huggingface.co/google/electra-base-discriminator) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.0818
23
- - Precision: 0.8510
24
- - Recall: 0.8785
25
- - F1: 0.8645
26
- - Accuracy: 0.9735
27
 
28
  ## Model description
29
 
@@ -42,41 +41,27 @@ More information needed
42
  ### Training hyperparameters
43
 
44
  The following hyperparameters were used during training:
45
- - learning_rate: 2e-06
46
  - train_batch_size: 8
47
  - eval_batch_size: 8
48
  - seed: 42
49
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
  - lr_scheduler_type: linear
51
- - num_epochs: 15
52
 
53
  ### Training results
54
 
55
- | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
56
- |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
57
- | 0.1958 | 0.63 | 500 | 0.0924 | 0.8293 | 0.8557 | 0.8423 | 0.9710 |
58
- | 0.0939 | 1.26 | 1000 | 0.0827 | 0.8358 | 0.8826 | 0.8585 | 0.9727 |
59
- | 0.0837 | 1.88 | 1500 | 0.0797 | 0.8542 | 0.8776 | 0.8657 | 0.9740 |
60
- | 0.0817 | 2.51 | 2000 | 0.0799 | 0.8441 | 0.8821 | 0.8627 | 0.9732 |
61
- | 0.0761 | 3.14 | 2500 | 0.0793 | 0.8527 | 0.8853 | 0.8687 | 0.9743 |
62
- | 0.0743 | 3.77 | 3000 | 0.0799 | 0.8381 | 0.8885 | 0.8626 | 0.9729 |
63
- | 0.076 | 4.4 | 3500 | 0.0793 | 0.8458 | 0.8862 | 0.8655 | 0.9736 |
64
- | 0.07 | 5.03 | 4000 | 0.0782 | 0.8448 | 0.8844 | 0.8641 | 0.9730 |
65
- | 0.067 | 5.65 | 4500 | 0.0784 | 0.8558 | 0.8835 | 0.8694 | 0.9738 |
66
- | 0.0732 | 6.28 | 5000 | 0.0787 | 0.8559 | 0.8785 | 0.8670 | 0.9742 |
67
- | 0.0655 | 6.91 | 5500 | 0.0780 | 0.8627 | 0.8780 | 0.8703 | 0.9749 |
68
- | 0.0668 | 7.54 | 6000 | 0.0778 | 0.8563 | 0.8789 | 0.8675 | 0.9739 |
69
- | 0.0653 | 8.17 | 6500 | 0.0789 | 0.8537 | 0.8821 | 0.8677 | 0.9738 |
70
- | 0.0671 | 8.79 | 7000 | 0.0786 | 0.8533 | 0.8817 | 0.8672 | 0.9739 |
71
- | 0.06 | 9.42 | 7500 | 0.0806 | 0.8482 | 0.8826 | 0.8650 | 0.9731 |
72
- | 0.0645 | 10.05 | 8000 | 0.0792 | 0.8546 | 0.8803 | 0.8673 | 0.9740 |
73
- | 0.0615 | 10.68 | 8500 | 0.0795 | 0.8464 | 0.8803 | 0.8630 | 0.9731 |
74
- | 0.0597 | 11.31 | 9000 | 0.0807 | 0.8502 | 0.8780 | 0.8639 | 0.9734 |
75
- | 0.0609 | 11.93 | 9500 | 0.0810 | 0.8527 | 0.8771 | 0.8647 | 0.9737 |
76
- | 0.0592 | 12.56 | 10000 | 0.0818 | 0.8502 | 0.8757 | 0.8628 | 0.9733 |
77
- | 0.0607 | 13.19 | 10500 | 0.0812 | 0.8495 | 0.8812 | 0.8651 | 0.9734 |
78
- | 0.0597 | 13.82 | 11000 | 0.0813 | 0.8484 | 0.8785 | 0.8631 | 0.9733 |
79
- | 0.0589 | 14.45 | 11500 | 0.0818 | 0.8510 | 0.8785 | 0.8645 | 0.9735 |
80
 
81
 
82
  ### Framework versions
 
1
  ---
 
2
  tags:
3
  - generated_from_trainer
4
  metrics:
 
16
 
17
  # electra-base-ner-food-recipe-v2
18
 
19
+ This model was trained from scratch on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.1709
22
+ - Precision: 0.8007
23
+ - Recall: 0.8867
24
+ - F1: 0.8415
25
+ - Accuracy: 0.9669
26
 
27
  ## Model description
28
 
 
41
  ### Training hyperparameters
42
 
43
  The following hyperparameters were used during training:
44
+ - learning_rate: 5e-06
45
  - train_batch_size: 8
46
  - eval_batch_size: 8
47
  - seed: 42
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
+ - num_epochs: 5
51
 
52
  ### Training results
53
 
54
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
55
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
56
+ | No log | 0.5 | 400 | 0.1420 | 0.7862 | 0.8871 | 0.8336 | 0.9655 |
57
+ | 0.101 | 1.01 | 800 | 0.1580 | 0.8317 | 0.8817 | 0.8559 | 0.9716 |
58
+ | 0.0966 | 1.51 | 1200 | 0.1467 | 0.8105 | 0.8917 | 0.8492 | 0.9693 |
59
+ | 0.0849 | 2.01 | 1600 | 0.1408 | 0.7966 | 0.8771 | 0.8349 | 0.9669 |
60
+ | 0.085 | 2.51 | 2000 | 0.1487 | 0.7941 | 0.8880 | 0.8384 | 0.9662 |
61
+ | 0.085 | 3.02 | 2400 | 0.1477 | 0.7773 | 0.8867 | 0.8284 | 0.9635 |
62
+ | 0.0766 | 3.52 | 2800 | 0.1852 | 0.8298 | 0.8807 | 0.8545 | 0.9710 |
63
+ | 0.0725 | 4.02 | 3200 | 0.1674 | 0.8073 | 0.8830 | 0.8435 | 0.9679 |
64
+ | 0.069 | 4.52 | 3600 | 0.1709 | 0.8007 | 0.8867 | 0.8415 | 0.9669 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
65
 
66
 
67
  ### Framework versions