Hugging Face's logo

Alnusjaponica
/
toxicity-score-multi-classification

Transformers
PyTorch
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Community
1
Alnusjaponica commited on
Commit
2daf9c9
•
1 Parent(s): c22acd6

End of training

Browse files
Files changed (2) hide show
  1. README.md +34 -34
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [line-corporation/line-distilbert-base-japanese](https://huggingface.co/line-corporation/line-distilbert-base-japanese) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.3743
19
- - Roc Auc: 0.7379
20
 
21
  ## Model description
22
 
@@ -35,8 +35,8 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - learning_rate: 0.0002542935559686549
39
- - train_batch_size: 32
40
  - eval_batch_size: 8
41
  - seed: 42
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
@@ -47,36 +47,36 @@ The following hyperparameters were used during training:
47
 
48
  | Training Loss | Epoch | Step | Validation Loss | Roc Auc |
49
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
50
- | No log | 1.0 | 10 | 0.3083 | 0.7924 |
51
- | No log | 2.0 | 20 | 0.3026 | 0.7713 |
52
- | No log | 3.0 | 30 | 0.3020 | 0.7160 |
53
- | No log | 4.0 | 40 | 0.2936 | 0.7490 |
54
- | No log | 5.0 | 50 | 0.3544 | 0.7550 |
55
- | No log | 6.0 | 60 | 0.3428 | 0.7477 |
56
- | No log | 7.0 | 70 | 0.3322 | 0.7773 |
57
- | No log | 8.0 | 80 | 0.3140 | 0.7851 |
58
- | No log | 9.0 | 90 | 0.3289 | 0.7761 |
59
- | No log | 10.0 | 100 | 0.3341 | 0.7593 |
60
- | No log | 11.0 | 110 | 0.3265 | 0.7722 |
61
- | No log | 12.0 | 120 | 0.3676 | 0.7293 |
62
- | No log | 13.0 | 130 | 0.2694 | 0.7533 |
63
- | No log | 14.0 | 140 | 0.2732 | 0.7653 |
64
- | No log | 15.0 | 150 | 0.2542 | 0.7555 |
65
- | No log | 16.0 | 160 | 0.2663 | 0.7606 |
66
- | No log | 17.0 | 170 | 0.3504 | 0.7375 |
67
- | No log | 18.0 | 180 | 0.3900 | 0.7280 |
68
- | No log | 19.0 | 190 | 0.3436 | 0.7113 |
69
- | No log | 20.0 | 200 | 0.3466 | 0.7340 |
70
- | No log | 21.0 | 210 | 0.3485 | 0.6855 |
71
- | No log | 22.0 | 220 | 0.3455 | 0.7276 |
72
- | No log | 23.0 | 230 | 0.3898 | 0.7194 |
73
- | No log | 24.0 | 240 | 0.3379 | 0.7340 |
74
- | No log | 25.0 | 250 | 0.3860 | 0.7293 |
75
- | No log | 26.0 | 260 | 0.3898 | 0.7276 |
76
- | No log | 27.0 | 270 | 0.3647 | 0.7375 |
77
- | No log | 28.0 | 280 | 0.3642 | 0.7400 |
78
- | No log | 29.0 | 290 | 0.3724 | 0.7379 |
79
- | No log | 30.0 | 300 | 0.3743 | 0.7379 |
80
 
81
 
82
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [line-corporation/line-distilbert-base-japanese](https://huggingface.co/line-corporation/line-distilbert-base-japanese) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.2649
19
+ - Roc Auc: 0.7992
20
 
21
  ## Model description
22
 
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - learning_rate: 8.133692392125703e-06
39
+ - train_batch_size: 16
40
  - eval_batch_size: 8
41
  - seed: 42
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 
47
 
48
  | Training Loss | Epoch | Step | Validation Loss | Roc Auc |
49
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
50
+ | No log | 1.0 | 20 | 0.6213 | 0.5148 |
51
+ | No log | 2.0 | 40 | 0.4762 | 0.4616 |
52
+ | No log | 3.0 | 60 | 0.3754 | 0.5830 |
53
+ | No log | 4.0 | 80 | 0.3314 | 0.5706 |
54
+ | No log | 5.0 | 100 | 0.3140 | 0.5740 |
55
+ | No log | 6.0 | 120 | 0.3067 | 0.6238 |
56
+ | No log | 7.0 | 140 | 0.3010 | 0.6645 |
57
+ | No log | 8.0 | 160 | 0.2975 | 0.7177 |
58
+ | No log | 9.0 | 180 | 0.2949 | 0.7392 |
59
+ | No log | 10.0 | 200 | 0.2892 | 0.7731 |
60
+ | No log | 11.0 | 220 | 0.2828 | 0.7954 |
61
+ | No log | 12.0 | 240 | 0.2827 | 0.7932 |
62
+ | No log | 13.0 | 260 | 0.2756 | 0.7984 |
63
+ | No log | 14.0 | 280 | 0.2715 | 0.8052 |
64
+ | No log | 15.0 | 300 | 0.2733 | 0.8100 |
65
+ | No log | 16.0 | 320 | 0.2754 | 0.8142 |
66
+ | No log | 17.0 | 340 | 0.2668 | 0.8130 |
67
+ | No log | 18.0 | 360 | 0.2642 | 0.8138 |
68
+ | No log | 19.0 | 380 | 0.2639 | 0.8117 |
69
+ | No log | 20.0 | 400 | 0.2659 | 0.8052 |
70
+ | No log | 21.0 | 420 | 0.2646 | 0.8082 |
71
+ | No log | 22.0 | 440 | 0.2643 | 0.8039 |
72
+ | No log | 23.0 | 460 | 0.2646 | 0.8022 |
73
+ | No log | 24.0 | 480 | 0.2644 | 0.8044 |
74
+ | 0.2305 | 25.0 | 500 | 0.2639 | 0.8035 |
75
+ | 0.2305 | 26.0 | 520 | 0.2639 | 0.8027 |
76
+ | 0.2305 | 27.0 | 540 | 0.2647 | 0.8001 |
77
+ | 0.2305 | 28.0 | 560 | 0.2643 | 0.8005 |
78
+ | 0.2305 | 29.0 | 580 | 0.2649 | 0.8001 |
79
+ | 0.2305 | 30.0 | 600 | 0.2649 | 0.7992 |
80
 
81
 
82
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9dee69bcfb9e06d15dfce6bc02c895b6d40664f8c476ce220bbe08a6a2d23bf5
3
  size 274772269
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bf018f39d6f457e24aac0e7de1951824b2952ad5f07598bda988ca2e4ab5fb8
3
  size 274772269