Hugging Face's logo

songys
/
distilbert-base-uncased-distilled-clinc

Text Classification
Transformers
PyTorch
distilbert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
1
songys commited on
Commit
87d6d5e
•
1 Parent(s): 70266d1

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -13
README.md CHANGED
@@ -21,7 +21,7 @@ model-index:
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
- value: 0.9461290322580646
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: 0.2500
35
- - Accuracy: 0.9461
36
 
37
  ## Model description
38
 
@@ -63,16 +63,16 @@ The following hyperparameters were used during training:
63
 
64
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
65
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
66
- | 4.247 | 1.0 | 318 | 3.1740 | 0.7555 |
67
- | 2.4149 | 2.0 | 636 | 1.5652 | 0.8639 |
68
- | 1.1633 | 3.0 | 954 | 0.7781 | 0.9061 |
69
- | 0.5688 | 4.0 | 1272 | 0.4624 | 0.9342 |
70
- | 0.3005 | 5.0 | 1590 | 0.3368 | 0.9429 |
71
- | 0.1785 | 6.0 | 1908 | 0.2871 | 0.9429 |
72
- | 0.1174 | 7.0 | 2226 | 0.2673 | 0.9458 |
73
- | 0.0877 | 8.0 | 2544 | 0.2525 | 0.9465 |
74
- | 0.0728 | 9.0 | 2862 | 0.2521 | 0.9465 |
75
- | 0.0661 | 10.0 | 3180 | 0.2500 | 0.9461 |
76
 
77
 
78
  ### Framework versions
 
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
+ value: 0.9474193548387096
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: 0.2676
35
+ - Accuracy: 0.9474
36
 
37
  ## Model description
38
 
 
63
 
64
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
65
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
66
+ | 4.1402 | 1.0 | 318 | 3.0979 | 0.7503 |
67
+ | 2.3572 | 2.0 | 636 | 1.5361 | 0.8577 |
68
+ | 1.1469 | 3.0 | 954 | 0.7670 | 0.9168 |
69
+ | 0.5652 | 4.0 | 1272 | 0.4659 | 0.9345 |
70
+ | 0.308 | 5.0 | 1590 | 0.3458 | 0.9448 |
71
+ | 0.1934 | 6.0 | 1908 | 0.3009 | 0.9448 |
72
+ | 0.1368 | 7.0 | 2226 | 0.2781 | 0.9471 |
73
+ | 0.1088 | 8.0 | 2544 | 0.2724 | 0.9484 |
74
+ | 0.0949 | 9.0 | 2862 | 0.2704 | 0.9468 |
75
+ | 0.0897 | 10.0 | 3180 | 0.2676 | 0.9474 |
76
 
77
 
78
  ### Framework versions