Hugging Face's logo

dhruvil237
/
userutterance_classification_verplus

Text Classification
Transformers
PyTorch
TensorBoard
Safetensors
deberta-v2
Generated from Trainer
Eval Results
Model card Files
xet
Metrics Community
1
dhruvil237 commited on
Commit
8a32030
·
1 Parent(s): 7e24712

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +36 -19
README.md CHANGED
@@ -21,7 +21,7 @@ model-index:
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
- value: 0.9561290322580646
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 [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the clinc_oos dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 0.2190
35
- - Accuracy: 0.9561
36
 
37
  ## Model description
38
 
@@ -52,34 +52,51 @@ More information needed
52
 
53
  The following hyperparameters were used during training:
54
  - learning_rate: 2e-05
55
- - train_batch_size: 32
56
- - eval_batch_size: 32
57
  - seed: 42
58
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
  - lr_scheduler_type: linear
60
- - lr_scheduler_warmup_steps: 130
61
- - num_epochs: 5
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
- | 4.94 | 0.42 | 200 | 4.4744 | 0.1697 |
68
- | 3.8508 | 0.84 | 400 | 2.8790 | 0.6584 |
69
- | 2.5616 | 1.26 | 600 | 1.6906 | 0.8681 |
70
- | 1.59 | 1.68 | 800 | 0.9367 | 0.9152 |
71
- | 0.9566 | 2.1 | 1000 | 0.5392 | 0.9348 |
72
- | 0.5608 | 2.52 | 1200 | 0.3762 | 0.9465 |
73
- | 0.3678 | 2.94 | 1400 | 0.3008 | 0.9477 |
74
- | 0.2413 | 3.35 | 1600 | 0.2625 | 0.9497 |
75
- | 0.1837 | 3.77 | 1800 | 0.2367 | 0.9529 |
76
- | 0.136 | 4.19 | 2000 | 0.2193 | 0.9565 |
77
- | 0.1078 | 4.61 | 2200 | 0.2190 | 0.9561 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
78
 
79
 
80
  ### Framework versions
81
 
82
  - Transformers 4.28.0
83
  - Pytorch 2.0.1+cu118
84
- - Datasets 2.12.0
85
  - Tokenizers 0.13.3
 
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
+ value: 0.9619354838709677
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 [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the clinc_oos dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 0.2270
35
+ - Accuracy: 0.9619
36
 
37
  ## Model description
38
 
 
52
 
53
  The following hyperparameters were used during training:
54
  - learning_rate: 2e-05
55
+ - train_batch_size: 16
56
+ - eval_batch_size: 16
57
  - seed: 42
58
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
  - lr_scheduler_type: linear
60
+ - lr_scheduler_warmup_steps: 500
61
+ - num_epochs: 6
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
+ | 5.0219 | 0.21 | 200 | 4.9813 | 0.0077 |
68
+ | 4.8915 | 0.42 | 400 | 4.5741 | 0.1155 |
69
+ | 4.2736 | 0.63 | 600 | 3.5359 | 0.4719 |
70
+ | 3.2701 | 0.84 | 800 | 2.4291 | 0.7429 |
71
+ | 2.3578 | 1.05 | 1000 | 1.5793 | 0.8413 |
72
+ | 1.5695 | 1.26 | 1200 | 1.0029 | 0.8994 |
73
+ | 1.0412 | 1.47 | 1400 | 0.6475 | 0.9187 |
74
+ | 0.7034 | 1.68 | 1600 | 0.4439 | 0.9303 |
75
+ | 0.501 | 1.89 | 1800 | 0.3400 | 0.9381 |
76
+ | 0.3187 | 2.1 | 2000 | 0.2793 | 0.9439 |
77
+ | 0.2185 | 2.31 | 2200 | 0.2538 | 0.9490 |
78
+ | 0.1669 | 2.52 | 2400 | 0.2210 | 0.9523 |
79
+ | 0.1081 | 2.73 | 2600 | 0.2225 | 0.9519 |
80
+ | 0.1004 | 2.94 | 2800 | 0.2136 | 0.9555 |
81
+ | 0.0665 | 3.14 | 3000 | 0.2078 | 0.9561 |
82
+ | 0.0509 | 3.35 | 3200 | 0.2155 | 0.9568 |
83
+ | 0.05 | 3.56 | 3400 | 0.2107 | 0.9581 |
84
+ | 0.0527 | 3.77 | 3600 | 0.2171 | 0.9568 |
85
+ | 0.0447 | 3.98 | 3800 | 0.2128 | 0.9590 |
86
+ | 0.0259 | 4.19 | 4000 | 0.2099 | 0.9587 |
87
+ | 0.0279 | 4.4 | 4200 | 0.2179 | 0.9577 |
88
+ | 0.0176 | 4.61 | 4400 | 0.2191 | 0.9574 |
89
+ | 0.0288 | 4.82 | 4600 | 0.2216 | 0.9590 |
90
+ | 0.0328 | 5.03 | 4800 | 0.2237 | 0.9606 |
91
+ | 0.0154 | 5.24 | 5000 | 0.2241 | 0.9616 |
92
+ | 0.0157 | 5.45 | 5200 | 0.2265 | 0.9603 |
93
+ | 0.023 | 5.66 | 5400 | 0.2276 | 0.9613 |
94
+ | 0.0178 | 5.87 | 5600 | 0.2270 | 0.9619 |
95
 
96
 
97
  ### Framework versions
98
 
99
  - Transformers 4.28.0
100
  - Pytorch 2.0.1+cu118
101
+ - Datasets 2.13.1
102
  - Tokenizers 0.13.3