Hugging Face's logo

GV05
/
distilbert-base-uncased-distilled-clinc

Text Classification
Transformers
PyTorch
distilbert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
GV05 commited on
Commit
208ad1a
•
1 Parent(s): 42220e1

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +17 -18
README.md CHANGED
@@ -16,12 +16,12 @@ model-index:
16
  name: clinc_oos
17
  type: clinc_oos
18
  config: plus
19
- split: train
20
  args: plus
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
- value: 0.9367741935483871
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: 0.0699
35
- - Accuracy: 0.9368
36
 
37
  ## Model description
38
 
@@ -57,27 +57,26 @@ 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
- | No log | 1.0 | 318 | 0.5280 | 0.6855 |
67
- | 0.7764 | 2.0 | 636 | 0.2080 | 0.8603 |
68
- | 0.7764 | 3.0 | 954 | 0.1184 | 0.9090 |
69
- | 0.2195 | 4.0 | 1272 | 0.0923 | 0.9239 |
70
- | 0.1171 | 5.0 | 1590 | 0.0821 | 0.9284 |
71
- | 0.1171 | 6.0 | 1908 | 0.0764 | 0.9319 |
72
- | 0.0933 | 7.0 | 2226 | 0.0735 | 0.9345 |
73
- | 0.0836 | 8.0 | 2544 | 0.0715 | 0.9368 |
74
- | 0.0836 | 9.0 | 2862 | 0.0702 | 0.9377 |
75
- | 0.0796 | 10.0 | 3180 | 0.0699 | 0.9368 |
76
 
77
 
78
  ### Framework versions
79
 
80
- - Transformers 4.25.1
81
- - Pytorch 1.13.0+cu116
82
- - Datasets 2.8.0
83
  - Tokenizers 0.13.2
 
16
  name: clinc_oos
17
  type: clinc_oos
18
  config: plus
19
+ split: validation
20
  args: plus
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
+ value: 0.9470967741935484
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: 0.1800
35
+ - Accuracy: 0.9471
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
+ | No log | 1.0 | 318 | 1.1371 | 0.7587 |
67
+ | 1.3942 | 2.0 | 636 | 0.5981 | 0.8813 |
68
+ | 1.3942 | 3.0 | 954 | 0.3519 | 0.9216 |
69
+ | 0.5437 | 4.0 | 1272 | 0.2509 | 0.9368 |
70
+ | 0.2651 | 5.0 | 1590 | 0.2124 | 0.9413 |
71
+ | 0.2651 | 6.0 | 1908 | 0.1945 | 0.9468 |
72
+ | 0.1875 | 7.0 | 2226 | 0.1853 | 0.9477 |
73
+ | 0.161 | 8.0 | 2544 | 0.1815 | 0.9474 |
74
+ | 0.161 | 9.0 | 2862 | 0.1800 | 0.9471 |
 
75
 
76
 
77
  ### Framework versions
78
 
79
+ - Transformers 4.26.1
80
+ - Pytorch 1.13.1+cu116
81
+ - Datasets 2.9.0
82
  - Tokenizers 0.13.2