haesun commited on
Commit
adb4136
1 Parent(s): c6ea802

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -13
README.md CHANGED
@@ -21,7 +21,7 @@ model-index:
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
- value: 0.9454838709677419
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: 0.3584
35
- - Accuracy: 0.9455
36
 
37
  ## Model description
38
 
@@ -57,21 +57,22 @@ 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: 9
61
 
62
  ### Training results
63
 
64
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
65
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
66
- | 3.4679 | 1.0 | 318 | 2.5744 | 0.7461 |
67
- | 1.9854 | 2.0 | 636 | 1.3150 | 0.8616 |
68
- | 1.0196 | 3.0 | 954 | 0.7191 | 0.9087 |
69
- | 0.5718 | 4.0 | 1272 | 0.4885 | 0.9348 |
70
- | 0.3844 | 5.0 | 1590 | 0.4113 | 0.9429 |
71
- | 0.3028 | 6.0 | 1908 | 0.3816 | 0.9432 |
72
- | 0.2636 | 7.0 | 2226 | 0.3652 | 0.9461 |
73
- | 0.2428 | 8.0 | 2544 | 0.3604 | 0.9452 |
74
- | 0.2353 | 9.0 | 2862 | 0.3584 | 0.9455 |
 
75
 
76
 
77
  ### Framework versions
 
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: 0.3180
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: 10
61
 
62
  ### Training results
63
 
64
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
65
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
66
+ | 2.8197 | 1.0 | 318 | 2.0528 | 0.7435 |
67
+ | 1.5825 | 2.0 | 636 | 1.0403 | 0.8684 |
68
+ | 0.8215 | 3.0 | 954 | 0.5924 | 0.9110 |
69
+ | 0.486 | 4.0 | 1272 | 0.4252 | 0.9345 |
70
+ | 0.3488 | 5.0 | 1590 | 0.3693 | 0.9452 |
71
+ | 0.2872 | 6.0 | 1908 | 0.3440 | 0.9452 |
72
+ | 0.2564 | 7.0 | 2226 | 0.3297 | 0.9468 |
73
+ | 0.2393 | 8.0 | 2544 | 0.3241 | 0.9465 |
74
+ | 0.2317 | 9.0 | 2862 | 0.3208 | 0.9471 |
75
+ | 0.2265 | 10.0 | 3180 | 0.3180 | 0.9471 |
76
 
77
 
78
  ### Framework versions