update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- precision
|
7 |
+
- recall
|
8 |
+
- f1
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: electra-base-ner-food-recipe-v2
|
12 |
+
results: []
|
13 |
+
---
|
14 |
+
|
15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
+
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 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Intended uses & limitations
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training and evaluation data
|
37 |
+
|
38 |
+
More information needed
|
39 |
+
|
40 |
+
## Training procedure
|
41 |
+
|
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
|
83 |
+
|
84 |
+
- Transformers 4.27.4
|
85 |
+
- Pytorch 2.0.0+cu118
|
86 |
+
- Datasets 2.11.0
|
87 |
+
- Tokenizers 0.13.3
|