Hugging Face's logo

ThuyNT03
/
PhoBERT-cls-detail-in-Non_OCR

Text Classification
Transformers
PyTorch
roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
ThuyNT03 commited on
Commit
92a95e5
•
1 Parent(s): 1dcc366

Training completed!

Browse files
Files changed (1) hide show
  1. README.md +13 -11
README.md CHANGED
@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.2037
21
  - Accuracy: 0.93
22
- - F1: 0.9339
23
 
24
  ## Model description
25
 
@@ -44,20 +44,22 @@ The following hyperparameters were used during training:
44
  - seed: 42
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
- - num_epochs: 8
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
53
- | 1.1155 | 1.0 | 25 | 0.9023 | 0.68 | 0.5898 |
54
- | 0.725 | 2.0 | 50 | 0.4912 | 0.91 | 0.8689 |
55
- | 0.4564 | 3.0 | 75 | 0.3118 | 0.92 | 0.8911 |
56
- | 0.3084 | 4.0 | 100 | 0.2391 | 0.93 | 0.9339 |
57
- | 0.2426 | 5.0 | 125 | 0.2064 | 0.93 | 0.9339 |
58
- | 0.182 | 6.0 | 150 | 0.1888 | 0.96 | 0.96 |
59
- | 0.1705 | 7.0 | 175 | 0.2049 | 0.93 | 0.9339 |
60
- | 0.1599 | 8.0 | 200 | 0.2037 | 0.93 | 0.9339 |
 
 
61
 
62
 
63
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.2800
21
  - Accuracy: 0.93
22
+ - F1: 0.9325
23
 
24
  ## Model description
25
 
 
44
  - seed: 42
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
+ - num_epochs: 10
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
53
+ | 0.9516 | 1.0 | 50 | 0.4520 | 0.915 | 0.9120 |
54
+ | 0.351 | 2.0 | 100 | 0.2371 | 0.92 | 0.9229 |
55
+ | 0.1989 | 3.0 | 150 | 0.2468 | 0.935 | 0.9370 |
56
+ | 0.1569 | 4.0 | 200 | 0.2072 | 0.93 | 0.9333 |
57
+ | 0.1161 | 5.0 | 250 | 0.2266 | 0.935 | 0.9370 |
58
+ | 0.0963 | 6.0 | 300 | 0.2373 | 0.945 | 0.9455 |
59
+ | 0.089 | 7.0 | 350 | 0.2682 | 0.93 | 0.9331 |
60
+ | 0.0852 | 8.0 | 400 | 0.2738 | 0.925 | 0.9257 |
61
+ | 0.069 | 9.0 | 450 | 0.2825 | 0.93 | 0.9325 |
62
+ | 0.0701 | 10.0 | 500 | 0.2800 | 0.93 | 0.9325 |
63
 
64
 
65
  ### Framework versions