Commit
•
6899c63
1
Parent(s):
3901eb9
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- filter_v2
|
7 |
+
metrics:
|
8 |
+
- f1
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: favs_filter_classification_v2
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Text Classification
|
15 |
+
type: text-classification
|
16 |
+
dataset:
|
17 |
+
name: filter_v2
|
18 |
+
type: filter_v2
|
19 |
+
config: default
|
20 |
+
split: train
|
21 |
+
args: default
|
22 |
+
metrics:
|
23 |
+
- name: F1
|
24 |
+
type: f1
|
25 |
+
value: 1.0
|
26 |
+
- name: Accuracy
|
27 |
+
type: accuracy
|
28 |
+
value: 1.0
|
29 |
+
---
|
30 |
+
|
31 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
32 |
+
should probably proofread and complete it, then remove this comment. -->
|
33 |
+
|
34 |
+
# favs_filter_classification_v2
|
35 |
+
|
36 |
+
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the filter_v2 dataset.
|
37 |
+
It achieves the following results on the evaluation set:
|
38 |
+
- Loss: 0.2580
|
39 |
+
- F1: 1.0
|
40 |
+
- Roc Auc: 1.0
|
41 |
+
- Accuracy: 1.0
|
42 |
+
|
43 |
+
## Model description
|
44 |
+
|
45 |
+
More information needed
|
46 |
+
|
47 |
+
## Intended uses & limitations
|
48 |
+
|
49 |
+
More information needed
|
50 |
+
|
51 |
+
## Training and evaluation data
|
52 |
+
|
53 |
+
More information needed
|
54 |
+
|
55 |
+
## Training procedure
|
56 |
+
|
57 |
+
### Training hyperparameters
|
58 |
+
|
59 |
+
The following hyperparameters were used during training:
|
60 |
+
- learning_rate: 1.5e-05
|
61 |
+
- train_batch_size: 8
|
62 |
+
- eval_batch_size: 8
|
63 |
+
- seed: 42
|
64 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
65 |
+
- lr_scheduler_type: linear
|
66 |
+
- num_epochs: 15
|
67 |
+
|
68 |
+
### Training results
|
69 |
+
|
70 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|
71 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
|
72 |
+
| 0.6752 | 1.0 | 13 | 0.6166 | 0.3810 | 0.5772 | 0.0 |
|
73 |
+
| 0.5905 | 2.0 | 26 | 0.5326 | 0.6286 | 0.7399 | 0.3636 |
|
74 |
+
| 0.5004 | 3.0 | 39 | 0.4812 | 0.5 | 0.6636 | 0.2727 |
|
75 |
+
| 0.4268 | 4.0 | 52 | 0.4346 | 0.7027 | 0.7899 | 0.4545 |
|
76 |
+
| 0.391 | 5.0 | 65 | 0.4072 | 0.8205 | 0.8737 | 0.5455 |
|
77 |
+
| 0.3725 | 6.0 | 78 | 0.3666 | 0.8108 | 0.8575 | 0.6364 |
|
78 |
+
| 0.3215 | 7.0 | 91 | 0.3382 | 0.8889 | 0.9 | 0.7273 |
|
79 |
+
| 0.3094 | 8.0 | 104 | 0.3083 | 0.9474 | 0.95 | 0.8182 |
|
80 |
+
| 0.2825 | 9.0 | 117 | 0.2925 | 0.9189 | 0.925 | 0.7273 |
|
81 |
+
| 0.2596 | 10.0 | 130 | 0.2801 | 0.9474 | 0.95 | 0.8182 |
|
82 |
+
| 0.2517 | 11.0 | 143 | 0.2580 | 1.0 | 1.0 | 1.0 |
|
83 |
+
| 0.2308 | 12.0 | 156 | 0.2538 | 0.9744 | 0.975 | 0.9091 |
|
84 |
+
| 0.238 | 13.0 | 169 | 0.2459 | 0.9744 | 0.975 | 0.9091 |
|
85 |
+
| 0.2194 | 14.0 | 182 | 0.2379 | 1.0 | 1.0 | 1.0 |
|
86 |
+
| 0.2181 | 15.0 | 195 | 0.2366 | 1.0 | 1.0 | 1.0 |
|
87 |
+
|
88 |
+
|
89 |
+
### Framework versions
|
90 |
+
|
91 |
+
- Transformers 4.21.1
|
92 |
+
- Pytorch 1.12.1
|
93 |
+
- Datasets 2.4.0
|
94 |
+
- Tokenizers 0.12.1
|