Hugging Face's logo

shinta0615
/
distilbert-base-uncased-distilled-clinc

Text Classification
Transformers
PyTorch
distilbert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
2
shinta0615 commited on
Commit
be9e73e
•
1 Parent(s): 5f22aa8

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: 0.9487096774193549
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: 0.3490
35
- - Accuracy: 0.9487
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
- | No log | 1.0 | 318 | 2.5457 | 0.7519 |
67
- | 2.9907 | 2.0 | 636 | 1.2820 | 0.8561 |
68
- | 2.9907 | 3.0 | 954 | 0.6966 | 0.9123 |
69
- | 1.1204 | 4.0 | 1272 | 0.4778 | 0.9339 |
70
- | 0.4583 | 5.0 | 1590 | 0.4046 | 0.9439 |
71
- | 0.4583 | 6.0 | 1908 | 0.3771 | 0.9435 |
72
- | 0.2898 | 7.0 | 2226 | 0.3619 | 0.9474 |
73
- | 0.2371 | 8.0 | 2544 | 0.3541 | 0.9471 |
74
- | 0.2371 | 9.0 | 2862 | 0.3515 | 0.9484 |
75
- | 0.2197 | 10.0 | 3180 | 0.3490 | 0.9487 |
76
 
77
 
78
  ### Framework versions
 
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
+ value: 0.9483870967741935
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: 0.3469
35
+ - Accuracy: 0.9484
36
 
37
  ## Model description
38
 
 
63
 
64
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
65
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
66
+ | No log | 1.0 | 318 | 2.4602 | 0.7535 |
67
+ | 2.8954 | 2.0 | 636 | 1.2412 | 0.8558 |
68
+ | 2.8954 | 3.0 | 954 | 0.6810 | 0.9126 |
69
+ | 1.0885 | 4.0 | 1272 | 0.4728 | 0.9335 |
70
+ | 0.455 | 5.0 | 1590 | 0.4025 | 0.9439 |
71
+ | 0.455 | 6.0 | 1908 | 0.3754 | 0.9439 |
72
+ | 0.2936 | 7.0 | 2226 | 0.3600 | 0.9471 |
73
+ | 0.2422 | 8.0 | 2544 | 0.3522 | 0.9468 |
74
+ | 0.2422 | 9.0 | 2862 | 0.3493 | 0.9481 |
75
+ | 0.2251 | 10.0 | 3180 | 0.3469 | 0.9484 |
76
 
77
 
78
  ### Framework versions