update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: spellcorrector_1209_v5
|
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 |
+
# spellcorrector_1209_v5
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [google/canine-s](https://huggingface.co/google/canine-s) on the None dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.0129
|
23 |
+
- Precision: 0.9884
|
24 |
+
- Recall: 0.9845
|
25 |
+
- F1: 0.9865
|
26 |
+
- Accuracy: 0.9958
|
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-05
|
46 |
+
- train_batch_size: 4
|
47 |
+
- eval_batch_size: 4
|
48 |
+
- seed: 42
|
49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
+
- lr_scheduler_type: linear
|
51 |
+
- num_epochs: 20
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
56 |
+
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
57 |
+
| 0.2592 | 1.0 | 1951 | 0.1973 | 0.7990 | 0.7403 | 0.7686 | 0.9462 |
|
58 |
+
| 0.2036 | 2.0 | 3902 | 0.1430 | 0.8304 | 0.7969 | 0.8133 | 0.9591 |
|
59 |
+
| 0.1643 | 3.0 | 5853 | 0.1090 | 0.8775 | 0.8292 | 0.8527 | 0.9688 |
|
60 |
+
| 0.1339 | 4.0 | 7804 | 0.0898 | 0.8971 | 0.8539 | 0.8750 | 0.9743 |
|
61 |
+
| 0.1143 | 5.0 | 9755 | 0.0788 | 0.9104 | 0.8768 | 0.8933 | 0.9773 |
|
62 |
+
| 0.0996 | 6.0 | 11706 | 0.0648 | 0.9240 | 0.8929 | 0.9082 | 0.9810 |
|
63 |
+
| 0.0874 | 7.0 | 13657 | 0.0568 | 0.9349 | 0.9035 | 0.9189 | 0.9829 |
|
64 |
+
| 0.0797 | 8.0 | 15608 | 0.0496 | 0.9439 | 0.9215 | 0.9326 | 0.9851 |
|
65 |
+
| 0.0696 | 9.0 | 17559 | 0.0426 | 0.9538 | 0.9289 | 0.9412 | 0.9868 |
|
66 |
+
| 0.0647 | 10.0 | 19510 | 0.0385 | 0.9596 | 0.9372 | 0.9482 | 0.9880 |
|
67 |
+
| 0.0532 | 11.0 | 21461 | 0.0335 | 0.9636 | 0.9465 | 0.9550 | 0.9895 |
|
68 |
+
| 0.0481 | 12.0 | 23412 | 0.0298 | 0.9704 | 0.9570 | 0.9636 | 0.9907 |
|
69 |
+
| 0.0443 | 13.0 | 25363 | 0.0240 | 0.9745 | 0.9654 | 0.9699 | 0.9923 |
|
70 |
+
| 0.0414 | 14.0 | 27314 | 0.0229 | 0.9795 | 0.9671 | 0.9732 | 0.9926 |
|
71 |
+
| 0.0369 | 15.0 | 29265 | 0.0195 | 0.9809 | 0.9737 | 0.9773 | 0.9938 |
|
72 |
+
| 0.0339 | 16.0 | 31216 | 0.0171 | 0.9831 | 0.9778 | 0.9805 | 0.9944 |
|
73 |
+
| 0.0312 | 17.0 | 33167 | 0.0156 | 0.9859 | 0.9797 | 0.9828 | 0.9949 |
|
74 |
+
| 0.0276 | 18.0 | 35118 | 0.0140 | 0.9874 | 0.9821 | 0.9847 | 0.9954 |
|
75 |
+
| 0.0277 | 19.0 | 37069 | 0.0133 | 0.9880 | 0.9840 | 0.9860 | 0.9957 |
|
76 |
+
| 0.0253 | 20.0 | 39020 | 0.0129 | 0.9884 | 0.9845 | 0.9865 | 0.9958 |
|
77 |
+
|
78 |
+
|
79 |
+
### Framework versions
|
80 |
+
|
81 |
+
- Transformers 4.28.0
|
82 |
+
- Pytorch 2.0.1+cu118
|
83 |
+
- Datasets 2.14.5
|
84 |
+
- Tokenizers 0.13.3
|