Hugging Face's logo

gouse-73
/
distilbert-base-uncased-distilled-clinc

Text Classification
Transformers
PyTorch
distilbert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
gouse-73 commited on
Commit
6784f27
•
1 Parent(s): 672734a

Distillation Completed!!!

Browse files
Files changed (1) hide show
  1. README.md +12 -14
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.9287096774193548
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the clinc_oos dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.0346
36
- - Accuracy: 0.9287
37
 
38
  ## Model description
39
 
@@ -58,22 +58,20 @@ The following hyperparameters were used during training:
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
- - num_epochs: 10
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
- | 0.4545 | 1.0 | 318 | 0.2392 | 0.6261 |
68
- | 0.1973 | 2.0 | 636 | 0.1144 | 0.8494 |
69
- | 0.1193 | 3.0 | 954 | 0.0748 | 0.9058 |
70
- | 0.0881 | 4.0 | 1272 | 0.0565 | 0.9129 |
71
- | 0.0721 | 5.0 | 1590 | 0.0467 | 0.9187 |
72
- | 0.0628 | 6.0 | 1908 | 0.0420 | 0.9232 |
73
- | 0.057 | 7.0 | 2226 | 0.0381 | 0.9268 |
74
- | 0.0534 | 8.0 | 2544 | 0.0362 | 0.9290 |
75
- | 0.051 | 9.0 | 2862 | 0.0349 | 0.9287 |
76
- | 0.0499 | 10.0 | 3180 | 0.0346 | 0.9287 |
77
 
78
 
79
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.9438709677419355
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the clinc_oos dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.3238
36
+ - Accuracy: 0.9439
37
 
38
  ## Model description
39
 
 
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
+ - num_epochs: 8
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
+ | 4.0341 | 1.0 | 318 | 3.0230 | 0.7245 |
68
+ | 2.3266 | 2.0 | 636 | 1.5597 | 0.8494 |
69
+ | 1.1958 | 3.0 | 954 | 0.8316 | 0.9142 |
70
+ | 0.6396 | 4.0 | 1272 | 0.5287 | 0.9332 |
71
+ | 0.3865 | 5.0 | 1590 | 0.4087 | 0.9365 |
72
+ | 0.2679 | 6.0 | 1908 | 0.3519 | 0.9406 |
73
+ | 0.2118 | 7.0 | 2226 | 0.3313 | 0.9416 |
74
+ | 0.1874 | 8.0 | 2544 | 0.3238 | 0.9439 |
 
 
75
 
76
 
77
  ### Framework versions