miyagawaorj commited on
Commit
f1a389d
1 Parent(s): af56ee9

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +33 -6
README.md CHANGED
@@ -4,9 +4,22 @@ tags:
4
  - generated_from_trainer
5
  datasets:
6
  - clinc_oos
 
 
7
  model-index:
8
  - name: distilbert-base-uncased-finetuned-clinc
9
- results: []
 
 
 
 
 
 
 
 
 
 
 
10
  ---
11
 
12
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,6 +28,9 @@ should probably proofread and complete it, then remove this comment. -->
15
  # distilbert-base-uncased-finetuned-clinc
16
 
17
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the clinc_oos dataset.
 
 
 
18
 
19
  ## Model description
20
 
@@ -34,16 +50,27 @@ More information needed
34
 
35
  The following hyperparameters were used during training:
36
  - learning_rate: 2e-05
37
- - train_batch_size: 48
38
- - eval_batch_size: 48
39
  - seed: 42
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: linear
42
  - num_epochs: 5
43
 
 
 
 
 
 
 
 
 
 
 
 
44
  ### Framework versions
45
 
46
- - Transformers 4.11.3
47
- - Pytorch 1.11.0+cu113
48
  - Datasets 1.16.1
49
- - Tokenizers 0.10.3
 
4
  - generated_from_trainer
5
  datasets:
6
  - clinc_oos
7
+ metrics:
8
+ - accuracy
9
  model-index:
10
  - name: distilbert-base-uncased-finetuned-clinc
11
+ results:
12
+ - task:
13
+ name: Text Classification
14
+ type: text-classification
15
+ dataset:
16
+ name: clinc_oos
17
+ type: clinc_oos
18
+ args: plus
19
+ metrics:
20
+ - name: Accuracy
21
+ type: accuracy
22
+ value: 0.9474193548387096
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
28
  # distilbert-base-uncased-finetuned-clinc
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: 0.2454
33
+ - Accuracy: 0.9474
34
 
35
  ## Model description
36
 
 
50
 
51
  The following hyperparameters were used during training:
52
  - learning_rate: 2e-05
53
+ - train_batch_size: 16
54
+ - eval_batch_size: 16
55
  - seed: 42
56
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
57
  - lr_scheduler_type: linear
58
  - num_epochs: 5
59
 
60
+ ### Training results
61
+
62
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
63
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
64
+ | 3.496 | 1.0 | 954 | 1.8019 | 0.8306 |
65
+ | 1.0663 | 2.0 | 1908 | 0.5690 | 0.9174 |
66
+ | 0.3267 | 3.0 | 2862 | 0.3128 | 0.9406 |
67
+ | 0.1397 | 4.0 | 3816 | 0.2567 | 0.9445 |
68
+ | 0.0846 | 5.0 | 4770 | 0.2454 | 0.9474 |
69
+
70
+
71
  ### Framework versions
72
 
73
+ - Transformers 4.19.2
74
+ - Pytorch 1.11.0
75
  - Datasets 1.16.1
76
+ - Tokenizers 0.12.1