hhffxx commited on
Commit
a961b6d
1 Parent(s): 584017b

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -13
README.md CHANGED
@@ -21,7 +21,7 @@ model-index:
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
- value: 0.9170967741935484
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: 0.7775
35
- - Accuracy: 0.9171
36
 
37
  ## Model description
38
 
@@ -52,8 +52,8 @@ More information needed
52
 
53
  The following hyperparameters were used during training:
54
  - learning_rate: 2e-05
55
- - train_batch_size: 48
56
- - eval_batch_size: 48
57
  - seed: 42
58
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
  - lr_scheduler_type: linear
@@ -63,16 +63,16 @@ The following hyperparameters were used during training:
63
 
64
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
65
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
66
- | 4.2882 | 1.0 | 318 | 3.2774 | 0.7394 |
67
- | 2.6225 | 2.0 | 636 | 1.8737 | 0.8284 |
68
- | 1.5435 | 3.0 | 954 | 1.1615 | 0.89 |
69
- | 1.0107 | 4.0 | 1272 | 0.8598 | 0.9090 |
70
- | 0.7994 | 5.0 | 1590 | 0.7775 | 0.9171 |
71
 
72
 
73
  ### Framework versions
74
 
75
- - Transformers 4.21.1
76
- - Pytorch 1.11.0
77
- - Datasets 2.3.0
78
  - Tokenizers 0.12.1
 
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
+ value: 0.9503225806451613
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: 0.2339
35
+ - Accuracy: 0.9503
36
 
37
  ## Model description
38
 
 
52
 
53
  The following hyperparameters were used during training:
54
  - learning_rate: 2e-05
55
+ - train_batch_size: 12
56
+ - eval_batch_size: 12
57
  - seed: 42
58
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
  - lr_scheduler_type: linear
 
63
 
64
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
65
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
66
+ | 3.2073 | 1.0 | 1271 | 1.3840 | 0.8542 |
67
+ | 0.7452 | 2.0 | 2542 | 0.4053 | 0.9316 |
68
+ | 0.1916 | 3.0 | 3813 | 0.2580 | 0.9452 |
69
+ | 0.0768 | 4.0 | 5084 | 0.2371 | 0.9477 |
70
+ | 0.0455 | 5.0 | 6355 | 0.2339 | 0.9503 |
71
 
72
 
73
  ### Framework versions
74
 
75
+ - Transformers 4.21.3
76
+ - Pytorch 1.12.1
77
+ - Datasets 2.4.0
78
  - Tokenizers 0.12.1