Hugging Face's logo

cj-mills
/
distilbert-base-uncased-distilled-clinc

Text Classification
Transformers
PyTorch
distilbert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
1
cj-mills commited on
Commit
280dd09
•
1 Parent(s): 1913ae3

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +16 -15
README.md CHANGED
@@ -19,7 +19,7 @@ model-index:
19
  metrics:
20
  - name: Accuracy
21
  type: accuracy
22
- value: 0.9435483870967742
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: 0.2540
33
- - Accuracy: 0.9435
34
 
35
  ## Model description
36
 
@@ -55,27 +55,28 @@ 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
  - mixed_precision_training: Native AMP
60
 
61
  ### Training results
62
 
63
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
64
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
65
- | 2.5782 | 1.0 | 318 | 1.9025 | 0.7574 |
66
- | 1.4836 | 2.0 | 636 | 1.0083 | 0.8674 |
67
- | 0.8085 | 3.0 | 954 | 0.5846 | 0.9187 |
68
- | 0.4816 | 4.0 | 1272 | 0.4023 | 0.9339 |
69
- | 0.3265 | 5.0 | 1590 | 0.3224 | 0.9429 |
70
- | 0.2479 | 6.0 | 1908 | 0.2838 | 0.9426 |
71
- | 0.2071 | 7.0 | 2226 | 0.2644 | 0.9445 |
72
- | 0.186 | 8.0 | 2544 | 0.2564 | 0.9432 |
73
- | 0.1771 | 9.0 | 2862 | 0.2540 | 0.9435 |
 
74
 
75
 
76
  ### Framework versions
77
 
78
- - Transformers 4.11.3
79
  - Pytorch 1.11.0
80
  - Datasets 2.0.0
81
- - Tokenizers 0.10.3
 
19
  metrics:
20
  - name: Accuracy
21
  type: accuracy
22
+ value: 0.94
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: 0.0734
33
+ - Accuracy: 0.94
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
  - mixed_precision_training: Native AMP
60
 
61
  ### Training results
62
 
63
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
64
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
65
+ | 0.6673 | 1.0 | 318 | 0.4082 | 0.7090 |
66
+ | 0.3283 | 2.0 | 636 | 0.2116 | 0.8774 |
67
+ | 0.1988 | 3.0 | 954 | 0.1404 | 0.9194 |
68
+ | 0.144 | 4.0 | 1272 | 0.1077 | 0.9281 |
69
+ | 0.1175 | 5.0 | 1590 | 0.0922 | 0.9355 |
70
+ | 0.1029 | 6.0 | 1908 | 0.0836 | 0.9365 |
71
+ | 0.094 | 7.0 | 2226 | 0.0786 | 0.9371 |
72
+ | 0.0883 | 8.0 | 2544 | 0.0756 | 0.9394 |
73
+ | 0.0853 | 9.0 | 2862 | 0.0740 | 0.9394 |
74
+ | 0.0835 | 10.0 | 3180 | 0.0734 | 0.94 |
75
 
76
 
77
  ### Framework versions
78
 
79
+ - Transformers 4.18.0
80
  - Pytorch 1.11.0
81
  - Datasets 2.0.0
82
+ - Tokenizers 0.12.1