Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,53 @@
|
|
1 |
---
|
2 |
license: mit
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: mit
|
3 |
---
|
4 |
+
|
5 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
6 |
+
should probably proofread and complete it, then remove this comment. -->
|
7 |
+
|
8 |
+
# test_trainer
|
9 |
+
|
10 |
+
this model is based on distilbert to train on fake reviews dataset
|
11 |
+
It achieves the following results on the evaluation set:
|
12 |
+
- Loss: 0.1408
|
13 |
+
- Accuracy: 0.9834
|
14 |
+
|
15 |
+
## Model description
|
16 |
+
|
17 |
+
Based on Distilbert
|
18 |
+
|
19 |
+
## Intended uses & limitations
|
20 |
+
|
21 |
+
More information needed
|
22 |
+
|
23 |
+
## Training and evaluation data
|
24 |
+
|
25 |
+
Dataset is
|
26 |
+
## Training procedure
|
27 |
+
|
28 |
+
### Training hyperparameters
|
29 |
+
|
30 |
+
The following hyperparameters were used during training:
|
31 |
+
- learning_rate: 5e-05
|
32 |
+
- train_batch_size: 8
|
33 |
+
- eval_batch_size: 8
|
34 |
+
- seed: 42
|
35 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
36 |
+
- lr_scheduler_type: linear
|
37 |
+
- num_epochs: 3.0
|
38 |
+
|
39 |
+
### Training results
|
40 |
+
|
41 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
42 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
43 |
+
| 0.0622 | 1.0 | 3791 | 0.1079 | 0.9800 |
|
44 |
+
| 0.0174 | 2.0 | 7582 | 0.2099 | 0.9692 |
|
45 |
+
| 0.005 | 3.0 | 11373 | 0.1408 | 0.9834 |
|
46 |
+
|
47 |
+
|
48 |
+
### Framework versions
|
49 |
+
|
50 |
+
- Transformers 4.32.1
|
51 |
+
- Pytorch 2.1.0
|
52 |
+
- Datasets 2.14.6
|
53 |
+
- Tokenizers 0.13.2
|