Hugging Face's logo

haesun
/
distilbert-base-uncased-distilled-clinc

Text Classification Transformers PyTorch
distilbert generated_from_trainer Eval Results Inference Endpoints
Model card Files Community
haesun commited on
Commit
c9eba11
•
1 Parent(s): 0c39ad7

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +17 -15
README.md CHANGED
@@ -15,11 +15,13 @@ model-index:
15
  dataset:
16
  name: clinc_oos
17
  type: clinc_oos
 
 
18
  args: plus
19
  metrics:
20
  - name: Accuracy
21
  type: accuracy
22
- value: 0.9496774193548387
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
29
 
30
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the clinc_oos dataset.
31
  It achieves the following results on the evaluation set:
32
- - Loss: 0.2819
33
- - Accuracy: 0.9497
34
 
35
  ## Model description
36
 
@@ -61,21 +63,21 @@ The following hyperparameters were used during training:
61
 
62
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
63
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
64
- | 2.8206 | 1.0 | 318 | 2.0803 | 0.7535 |
65
- | 1.6059 | 2.0 | 636 | 1.0697 | 0.8665 |
66
- | 0.8427 | 3.0 | 954 | 0.6011 | 0.9206 |
67
- | 0.4898 | 4.0 | 1272 | 0.4185 | 0.9361 |
68
- | 0.3321 | 5.0 | 1590 | 0.3450 | 0.9435 |
69
- | 0.26 | 6.0 | 1908 | 0.3129 | 0.9477 |
70
- | 0.2225 | 7.0 | 2226 | 0.2949 | 0.9494 |
71
- | 0.2021 | 8.0 | 2544 | 0.2876 | 0.9481 |
72
- | 0.1913 | 9.0 | 2862 | 0.2843 | 0.9494 |
73
- | 0.1871 | 10.0 | 3180 | 0.2819 | 0.9497 |
74
 
75
 
76
  ### Framework versions
77
 
78
- - Transformers 4.13.0
79
  - Pytorch 1.12.0+cu113
80
  - Datasets 1.16.1
81
- - Tokenizers 0.10.3
15
  dataset:
16
  name: clinc_oos
17
  type: clinc_oos
18
+ config: plus
19
+ split: train
20
  args: plus
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
+ value: 0.9487096774193549
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
31
 
32
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the clinc_oos dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 0.2773
35
+ - Accuracy: 0.9487
36
 
37
  ## Model description
38
 
63
 
64
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
65
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
66
+ | 4.1605 | 1.0 | 318 | 3.1094 | 0.7532 |
67
+ | 2.3647 | 2.0 | 636 | 1.5376 | 0.8574 |
68
+ | 1.1472 | 3.0 | 954 | 0.7664 | 0.9155 |
69
+ | 0.5639 | 4.0 | 1272 | 0.4662 | 0.9326 |
70
+ | 0.3079 | 5.0 | 1590 | 0.3482 | 0.9448 |
71
+ | 0.1954 | 6.0 | 1908 | 0.3063 | 0.9448 |
72
+ | 0.141 | 7.0 | 2226 | 0.2850 | 0.9477 |
73
+ | 0.1148 | 8.0 | 2544 | 0.2808 | 0.9477 |
74
+ | 0.1021 | 9.0 | 2862 | 0.2798 | 0.9477 |
75
+ | 0.0975 | 10.0 | 3180 | 0.2773 | 0.9487 |
76
 
77
 
78
  ### Framework versions
79
 
80
+ - Transformers 4.21.1
81
  - Pytorch 1.12.0+cu113
82
  - Datasets 1.16.1
83
+ - Tokenizers 0.12.1