Hugging Face's logo

cafbr
/
distilbert-base-uncased-distilled-clinc

Text Classification
Transformers
PyTorch
distilbert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
cafbr commited on
Commit
e9bcc7c
•
1 Parent(s): 16ecb71

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -17
README.md CHANGED
@@ -21,7 +21,7 @@ model-index:
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
@@ -31,8 +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: 0.2643
35
- - Accuracy: 0.9471
36
 
37
  ## Model description
38
 
@@ -52,32 +52,27 @@ 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
60
- - num_epochs: 10
61
 
62
  ### Training results
63
 
64
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
65
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
66
- | No log | 1.0 | 318 | 3.0509 | 0.7519 |
67
- | 3.5593 | 2.0 | 636 | 1.5225 | 0.8539 |
68
- | 3.5593 | 3.0 | 954 | 0.7708 | 0.9139 |
69
- | 1.3006 | 4.0 | 1272 | 0.4680 | 0.9329 |
70
- | 0.4433 | 5.0 | 1590 | 0.3504 | 0.9423 |
71
- | 0.4433 | 6.0 | 1908 | 0.3061 | 0.9426 |
72
- | 0.1996 | 7.0 | 2226 | 0.2799 | 0.9468 |
73
- | 0.12 | 8.0 | 2544 | 0.2692 | 0.9471 |
74
- | 0.12 | 9.0 | 2862 | 0.2669 | 0.9455 |
75
- | 0.0942 | 10.0 | 3180 | 0.2643 | 0.9471 |
76
 
77
 
78
  ### Framework versions
79
 
80
  - Transformers 4.28.1
81
- - Pytorch 2.0.0+cpu
82
  - Datasets 2.11.0
83
  - Tokenizers 0.13.3
 
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
+ value: 0.9483870967741935
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: 0.2141
35
+ - Accuracy: 0.9484
36
 
37
  ## Model description
38
 
 
52
 
53
  The following hyperparameters were used during training:
54
  - learning_rate: 2e-05
55
+ - train_batch_size: 8
56
+ - eval_batch_size: 8
57
  - seed: 42
58
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
  - lr_scheduler_type: linear
60
+ - num_epochs: 5
61
 
62
  ### Training results
63
 
64
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
65
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
66
+ | 1.4176 | 1.0 | 1907 | 0.7492 | 0.8610 |
67
+ | 0.336 | 2.0 | 3814 | 0.2997 | 0.9368 |
68
+ | 0.174 | 3.0 | 5721 | 0.2329 | 0.9468 |
69
+ | 0.122 | 4.0 | 7628 | 0.2155 | 0.9484 |
70
+ | 0.1068 | 5.0 | 9535 | 0.2141 | 0.9484 |
 
 
 
 
 
71
 
72
 
73
  ### Framework versions
74
 
75
  - Transformers 4.28.1
76
+ - Pytorch 1.11.0+cu113
77
  - Datasets 2.11.0
78
  - Tokenizers 0.13.3