Hugging Face's logo

phnghiapro
/
distilbert-base-uncased-distilled-clinc

Text Classification
Transformers
PyTorch
distilbert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
phnghiapro commited on
Commit
ac433a3
•
1 Parent(s): bb52fea

Training complete

Browse files
Files changed (3) hide show
  1. README.md +15 -15
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.9487096774193549
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the clinc_oos dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.1837
36
- - Accuracy: 0.9487
37
 
38
  ## Model description
39
 
@@ -53,8 +53,8 @@ More information needed
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 0.0004
56
- - train_batch_size: 1024
57
- - eval_batch_size: 1024
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
@@ -64,16 +64,16 @@ The following hyperparameters were used during training:
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
- | 1.9956 | 1.0 | 15 | 1.1757 | 0.6987 |
68
- | 0.636 | 2.0 | 30 | 0.4093 | 0.9032 |
69
- | 0.3301 | 3.0 | 45 | 0.2476 | 0.9384 |
70
- | 0.1833 | 4.0 | 60 | 0.2117 | 0.9465 |
71
- | 0.1628 | 5.0 | 75 | 0.1992 | 0.9468 |
72
- | 0.1458 | 6.0 | 90 | 0.1910 | 0.9484 |
73
- | 0.1402 | 7.0 | 105 | 0.1858 | 0.9481 |
74
- | 0.1362 | 8.0 | 120 | 0.1850 | 0.9477 |
75
- | 0.1344 | 9.0 | 135 | 0.1838 | 0.9484 |
76
- | 0.1336 | 10.0 | 150 | 0.1837 | 0.9487 |
77
 
78
 
79
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.9490322580645161
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the clinc_oos dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.1852
36
+ - Accuracy: 0.9490
37
 
38
  ## Model description
39
 
 
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 0.0004
56
+ - train_batch_size: 1280
57
+ - eval_batch_size: 1280
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
 
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
+ | 1.9692 | 1.0 | 12 | 1.3486 | 0.6574 |
68
+ | 1.1867 | 2.0 | 24 | 0.5409 | 0.8884 |
69
+ | 0.5614 | 3.0 | 36 | 0.2845 | 0.9387 |
70
+ | 0.295 | 4.0 | 48 | 0.2234 | 0.9471 |
71
+ | 0.1729 | 5.0 | 60 | 0.2021 | 0.9487 |
72
+ | 0.1574 | 6.0 | 72 | 0.1942 | 0.9513 |
73
+ | 0.1477 | 7.0 | 84 | 0.1895 | 0.9510 |
74
+ | 0.1446 | 8.0 | 96 | 0.1870 | 0.9497 |
75
+ | 0.1405 | 9.0 | 108 | 0.1856 | 0.9494 |
76
+ | 0.1382 | 10.0 | 120 | 0.1852 | 0.9490 |
77
 
78
 
79
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86b8472c1199bc82f252ac7dc0bc6171b04e5ebd37940d3889c3bedfa29d5770
3
  size 268313837
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b9fe72b73c0856132163dc1ba24d4a8890afee476d63a92034868b0fcc0d6c8
3
  size 268313837
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a29501d006c8c0ec229e0af501a7d43eba09ac9a90bc051a1ad64a63e8595fd
3
  size 4155
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:401be471130125cbacf03594b906e256d79765a934d4482feadbd02d0c3754e0
3
  size 4155