Hugging Face's logo

codefactory4791
/
distilbert-base-uncased-distilled-clinc

Text Classification
Transformers
PyTorch
distilbert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
1
codefactory4791 commited on
Commit
190f34d
•
1 Parent(s): 8c01f50

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -13
README.md CHANGED
@@ -19,7 +19,7 @@ model-index:
19
  metrics:
20
  - name: Accuracy
21
  type: accuracy
22
- value: 0.9438709677419355
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,8 +29,8 @@ 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: 0.2108
33
- - Accuracy: 0.9439
34
 
35
  ## Model description
36
 
@@ -55,21 +55,22 @@ The following hyperparameters were used during training:
55
  - seed: 42
56
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
57
  - lr_scheduler_type: linear
58
- - num_epochs: 9
59
 
60
  ### Training results
61
 
62
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
63
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
64
- | 2.0011 | 1.0 | 318 | 1.4515 | 0.7655 |
65
- | 1.142 | 2.0 | 636 | 0.7762 | 0.87 |
66
- | 0.6315 | 3.0 | 954 | 0.4564 | 0.9171 |
67
- | 0.3865 | 4.0 | 1272 | 0.3170 | 0.9329 |
68
- | 0.2678 | 5.0 | 1590 | 0.2573 | 0.9426 |
69
- | 0.2125 | 6.0 | 1908 | 0.2316 | 0.9432 |
70
- | 0.184 | 7.0 | 2226 | 0.2185 | 0.9432 |
71
- | 0.1699 | 8.0 | 2544 | 0.2124 | 0.9445 |
72
- | 0.1638 | 9.0 | 2862 | 0.2108 | 0.9439 |
 
73
 
74
 
75
  ### Framework versions
 
19
  metrics:
20
  - name: Accuracy
21
  type: accuracy
22
+ value: 0.9306451612903226
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
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: 0.0376
33
+ - Accuracy: 0.9306
34
 
35
  ## Model description
36
 
 
55
  - seed: 42
56
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
57
  - lr_scheduler_type: linear
58
+ - num_epochs: 10
59
 
60
  ### Training results
61
 
62
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
63
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
64
+ | 0.819 | 1.0 | 318 | 0.4220 | 0.6687 |
65
+ | 0.3215 | 2.0 | 636 | 0.1501 | 0.8429 |
66
+ | 0.149 | 3.0 | 954 | 0.0783 | 0.9019 |
67
+ | 0.0958 | 4.0 | 1272 | 0.0571 | 0.9132 |
68
+ | 0.0751 | 5.0 | 1590 | 0.0484 | 0.9229 |
69
+ | 0.0649 | 6.0 | 1908 | 0.0437 | 0.9281 |
70
+ | 0.059 | 7.0 | 2226 | 0.0408 | 0.9313 |
71
+ | 0.0553 | 8.0 | 2544 | 0.0390 | 0.93 |
72
+ | 0.0532 | 9.0 | 2862 | 0.0379 | 0.9313 |
73
+ | 0.0518 | 10.0 | 3180 | 0.0376 | 0.9306 |
74
 
75
 
76
  ### Framework versions