Ali Mazhar Luqmani
commited on
Commit
•
a96dcca
1
Parent(s):
c9ec2cf
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
+
- f1
|
8 |
+
- precision
|
9 |
+
- recall
|
10 |
+
model-index:
|
11 |
+
- name: website_classification
|
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 |
+
# website_classification
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.2909
|
23 |
+
- Accuracy: 0.9362
|
24 |
+
- F1: 0.9354
|
25 |
+
- Precision: 0.9380
|
26 |
+
- Recall: 0.9362
|
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: 16
|
47 |
+
- eval_batch_size: 16
|
48 |
+
- seed: 42
|
49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
+
- lr_scheduler_type: linear
|
51 |
+
- num_epochs: 30
|
52 |
+
- mixed_precision_training: Native AMP
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
58 |
+
| 2.4251 | 1.0 | 71 | 1.8259 | 0.8688 | 0.8615 | 0.8645 | 0.8688 |
|
59 |
+
| 1.34 | 2.0 | 142 | 0.8796 | 0.9078 | 0.8978 | 0.8929 | 0.9078 |
|
60 |
+
| 0.6342 | 3.0 | 213 | 0.5158 | 0.9113 | 0.9052 | 0.9078 | 0.9113 |
|
61 |
+
| 0.3265 | 4.0 | 284 | 0.3381 | 0.9326 | 0.9268 | 0.9254 | 0.9326 |
|
62 |
+
| 0.165 | 5.0 | 355 | 0.3140 | 0.9255 | 0.9201 | 0.9215 | 0.9255 |
|
63 |
+
| 0.0939 | 6.0 | 426 | 0.2805 | 0.9291 | 0.9252 | 0.9279 | 0.9291 |
|
64 |
+
| 0.0568 | 7.0 | 497 | 0.2679 | 0.9362 | 0.9308 | 0.9290 | 0.9362 |
|
65 |
+
| 0.0337 | 8.0 | 568 | 0.2728 | 0.9291 | 0.9227 | 0.9217 | 0.9291 |
|
66 |
+
| 0.0216 | 9.0 | 639 | 0.2531 | 0.9362 | 0.9355 | 0.9379 | 0.9362 |
|
67 |
+
| 0.0141 | 10.0 | 710 | 0.2741 | 0.9326 | 0.9325 | 0.9362 | 0.9326 |
|
68 |
+
| 0.0108 | 11.0 | 781 | 0.2749 | 0.9291 | 0.9278 | 0.9302 | 0.9291 |
|
69 |
+
| 0.0086 | 12.0 | 852 | 0.2680 | 0.9291 | 0.9278 | 0.9302 | 0.9291 |
|
70 |
+
| 0.0074 | 13.0 | 923 | 0.2688 | 0.9326 | 0.9303 | 0.9317 | 0.9326 |
|
71 |
+
| 0.0065 | 14.0 | 994 | 0.2736 | 0.9362 | 0.9354 | 0.9380 | 0.9362 |
|
72 |
+
| 0.0057 | 15.0 | 1065 | 0.2780 | 0.9362 | 0.9354 | 0.9380 | 0.9362 |
|
73 |
+
| 0.0051 | 16.0 | 1136 | 0.2730 | 0.9362 | 0.9323 | 0.9321 | 0.9362 |
|
74 |
+
| 0.0047 | 17.0 | 1207 | 0.2793 | 0.9362 | 0.9344 | 0.9361 | 0.9362 |
|
75 |
+
| 0.0044 | 18.0 | 1278 | 0.2784 | 0.9362 | 0.9354 | 0.9380 | 0.9362 |
|
76 |
+
| 0.0039 | 19.0 | 1349 | 0.2799 | 0.9362 | 0.9354 | 0.9380 | 0.9362 |
|
77 |
+
| 0.0036 | 20.0 | 1420 | 0.2820 | 0.9362 | 0.9354 | 0.9380 | 0.9362 |
|
78 |
+
| 0.0035 | 21.0 | 1491 | 0.2836 | 0.9362 | 0.9354 | 0.9380 | 0.9362 |
|
79 |
+
| 0.0032 | 22.0 | 1562 | 0.2851 | 0.9362 | 0.9354 | 0.9380 | 0.9362 |
|
80 |
+
| 0.0032 | 23.0 | 1633 | 0.2863 | 0.9362 | 0.9354 | 0.9380 | 0.9362 |
|
81 |
+
| 0.0031 | 24.0 | 1704 | 0.2901 | 0.9362 | 0.9354 | 0.9380 | 0.9362 |
|
82 |
+
| 0.0029 | 25.0 | 1775 | 0.2896 | 0.9362 | 0.9354 | 0.9380 | 0.9362 |
|
83 |
+
| 0.0028 | 26.0 | 1846 | 0.2892 | 0.9362 | 0.9354 | 0.9380 | 0.9362 |
|
84 |
+
| 0.0027 | 27.0 | 1917 | 0.2891 | 0.9362 | 0.9354 | 0.9380 | 0.9362 |
|
85 |
+
| 0.0026 | 28.0 | 1988 | 0.2898 | 0.9362 | 0.9354 | 0.9380 | 0.9362 |
|
86 |
+
| 0.0027 | 29.0 | 2059 | 0.2909 | 0.9362 | 0.9354 | 0.9380 | 0.9362 |
|
87 |
+
| 0.0026 | 30.0 | 2130 | 0.2909 | 0.9362 | 0.9354 | 0.9380 | 0.9362 |
|
88 |
+
|
89 |
+
|
90 |
+
### Framework versions
|
91 |
+
|
92 |
+
- Transformers 4.26.0
|
93 |
+
- Pytorch 1.13.1+cu116
|
94 |
+
- Datasets 2.9.0
|
95 |
+
- Tokenizers 0.13.2
|