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
9bf4999
•
1 Parent(s): 7dd3131

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -14
README.md CHANGED
@@ -21,7 +21,7 @@ model-index:
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
- value: 0.9496774193548387
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
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: 0.2961
35
- - Accuracy: 0.9497
36
 
37
  ## Model description
38
 
@@ -57,22 +57,21 @@ The following hyperparameters were used during training:
57
  - seed: 42
58
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
  - lr_scheduler_type: linear
60
- - num_epochs: 10
61
 
62
  ### Training results
63
 
64
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
65
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
66
- | 3.0996 | 1.0 | 318 | 2.2986 | 0.7529 |
67
- | 1.7705 | 2.0 | 636 | 1.1762 | 0.8635 |
68
- | 0.9169 | 3.0 | 954 | 0.6479 | 0.9197 |
69
- | 0.5201 | 4.0 | 1272 | 0.4447 | 0.9358 |
70
- | 0.3452 | 5.0 | 1590 | 0.3640 | 0.9445 |
71
- | 0.2659 | 6.0 | 1908 | 0.3303 | 0.9455 |
72
- | 0.2245 | 7.0 | 2226 | 0.3105 | 0.9497 |
73
- | 0.2018 | 8.0 | 2544 | 0.3026 | 0.9487 |
74
- | 0.1896 | 9.0 | 2862 | 0.2987 | 0.9484 |
75
- | 0.1849 | 10.0 | 3180 | 0.2961 | 0.9497 |
76
 
77
 
78
  ### Framework versions
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
+ value: 0.9458064516129032
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: 0.3003
35
+ - Accuracy: 0.9458
36
 
37
  ## Model description
38
 
57
  - seed: 42
58
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
  - lr_scheduler_type: linear
60
+ - num_epochs: 9
61
 
62
  ### Training results
63
 
64
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
65
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
66
+ | 4.1086 | 1.0 | 318 | 3.0771 | 0.7519 |
67
+ | 2.3554 | 2.0 | 636 | 1.5490 | 0.8539 |
68
+ | 1.1715 | 3.0 | 954 | 0.7930 | 0.9145 |
69
+ | 0.5985 | 4.0 | 1272 | 0.4936 | 0.9319 |
70
+ | 0.3437 | 5.0 | 1590 | 0.3741 | 0.9439 |
71
+ | 0.2306 | 6.0 | 1908 | 0.3294 | 0.9439 |
72
+ | 0.1752 | 7.0 | 2226 | 0.3079 | 0.9468 |
73
+ | 0.1489 | 8.0 | 2544 | 0.3035 | 0.9458 |
74
+ | 0.1375 | 9.0 | 2862 | 0.3003 | 0.9458 |
 
75
 
76
 
77
  ### Framework versions