Hugging Face's logo

Realgon
/
distilbert_agnews_padding100model

Text Classification
Transformers
PyTorch
distilbert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
Realgon commited on
Commit
475084e
•
1 Parent(s): 4d65533

End of training

Browse files
Files changed (1) hide show
  1. README.md +45 -8
README.md CHANGED
@@ -5,9 +5,24 @@ tags:
5
  - generated_from_trainer
6
  datasets:
7
  - ag_news
 
 
8
  model-index:
9
  - name: distilbert_agnews_padding100model
10
- results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,6 +31,9 @@ should probably proofread and complete it, then remove this comment. -->
16
  # distilbert_agnews_padding100model
17
 
18
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the ag_news dataset.
 
 
 
19
 
20
  ## Model description
21
 
@@ -40,18 +58,37 @@ The following hyperparameters were used during training:
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
- - num_epochs: 0.01
44
 
45
  ### Training results
46
 
47
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
48
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
49
- | No log | 0.01 | 75 | 0.8625 | 0.8455 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
50
 
51
 
52
  ### Framework versions
53
 
54
- - Transformers 4.32.1
55
- - Pytorch 2.1.1
56
- - Datasets 2.12.0
57
  - Tokenizers 0.13.3
 
5
  - generated_from_trainer
6
  datasets:
7
  - ag_news
8
+ metrics:
9
+ - accuracy
10
  model-index:
11
  - name: distilbert_agnews_padding100model
12
+ results:
13
+ - task:
14
+ name: Text Classification
15
+ type: text-classification
16
+ dataset:
17
+ name: ag_news
18
+ type: ag_news
19
+ config: default
20
+ split: test
21
+ args: default
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.9448684210526316
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
31
  # distilbert_agnews_padding100model
32
 
33
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the ag_news dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.6590
36
+ - Accuracy: 0.9449
37
 
38
  ## Model description
39
 
 
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
+ - num_epochs: 20
62
 
63
  ### Training results
64
 
65
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
+ |:-------------:|:-----:|:------:|:---------------:|:--------:|
67
+ | 0.1885 | 1.0 | 7500 | 0.1952 | 0.9407 |
68
+ | 0.1438 | 2.0 | 15000 | 0.1912 | 0.9442 |
69
+ | 0.1323 | 3.0 | 22500 | 0.2133 | 0.9442 |
70
+ | 0.0953 | 4.0 | 30000 | 0.2650 | 0.9442 |
71
+ | 0.0595 | 5.0 | 37500 | 0.2934 | 0.9404 |
72
+ | 0.0444 | 6.0 | 45000 | 0.3532 | 0.9439 |
73
+ | 0.0431 | 7.0 | 52500 | 0.3903 | 0.9368 |
74
+ | 0.0324 | 8.0 | 60000 | 0.4585 | 0.94 |
75
+ | 0.0241 | 9.0 | 67500 | 0.4216 | 0.9426 |
76
+ | 0.0208 | 10.0 | 75000 | 0.4646 | 0.9442 |
77
+ | 0.015 | 11.0 | 82500 | 0.5329 | 0.9426 |
78
+ | 0.0115 | 12.0 | 90000 | 0.5237 | 0.9424 |
79
+ | 0.0109 | 13.0 | 97500 | 0.5406 | 0.9426 |
80
+ | 0.009 | 14.0 | 105000 | 0.5572 | 0.9421 |
81
+ | 0.0046 | 15.0 | 112500 | 0.5948 | 0.9428 |
82
+ | 0.0039 | 16.0 | 120000 | 0.5682 | 0.9436 |
83
+ | 0.0025 | 17.0 | 127500 | 0.6096 | 0.9454 |
84
+ | 0.0008 | 18.0 | 135000 | 0.6312 | 0.9447 |
85
+ | 0.0014 | 19.0 | 142500 | 0.6435 | 0.9439 |
86
+ | 0.0002 | 20.0 | 150000 | 0.6590 | 0.9449 |
87
 
88
 
89
  ### Framework versions
90
 
91
+ - Transformers 4.33.2
92
+ - Pytorch 2.0.1+cu117
93
+ - Datasets 2.14.5
94
  - Tokenizers 0.13.3