Hugging Face's logo

shmuhammad
/
distilbert-base-uncased-distilled-clinc

Text Classification
Transformers
PyTorch
distilbert
Generated from Trainer
Eval Results
Model card Files
xet
Community
2
shmuhammad commited on
Commit
4a0ea0c
·
1 Parent(s): dae2241

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -13
README.md CHANGED
@@ -19,7 +19,7 @@ model-index:
19
  metrics:
20
  - name: Accuracy
21
  type: accuracy
22
- value: 0.9409677419354838
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,8 +29,8 @@ should probably proofread and complete it, then remove this comment. -->
29
 
30
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the clinc_oos dataset.
31
  It achieves the following results on the evaluation set:
32
- - Loss: 0.1348
33
- - Accuracy: 0.9410
34
 
35
  ## Model description
36
 
@@ -61,16 +61,16 @@ The following hyperparameters were used during training:
61
 
62
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
63
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
64
- | 1.2777 | 1.0 | 318 | 0.7817 | 0.7155 |
65
- | 0.6021 | 2.0 | 636 | 0.3564 | 0.8613 |
66
- | 0.3068 | 3.0 | 954 | 0.2092 | 0.9181 |
67
- | 0.2015 | 4.0 | 1272 | 0.1677 | 0.9306 |
68
- | 0.1639 | 5.0 | 1590 | 0.1517 | 0.9368 |
69
- | 0.148 | 6.0 | 1908 | 0.1435 | 0.9397 |
70
- | 0.1386 | 7.0 | 2226 | 0.1392 | 0.9394 |
71
- | 0.1334 | 8.0 | 2544 | 0.1366 | 0.9416 |
72
- | 0.1303 | 9.0 | 2862 | 0.1351 | 0.9410 |
73
- | 0.1283 | 10.0 | 3180 | 0.1348 | 0.9410 |
74
 
75
 
76
  ### Framework versions
 
19
  metrics:
20
  - name: Accuracy
21
  type: accuracy
22
+ value: 0.9487096774193549
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
29
 
30
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the clinc_oos dataset.
31
  It achieves the following results on the evaluation set:
32
+ - Loss: 0.3060
33
+ - Accuracy: 0.9487
34
 
35
  ## Model description
36
 
 
61
 
62
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
63
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
64
+ | 2.643 | 1.0 | 318 | 1.9110 | 0.7452 |
65
+ | 1.4751 | 2.0 | 636 | 0.9678 | 0.8606 |
66
+ | 0.7736 | 3.0 | 954 | 0.5578 | 0.9168 |
67
+ | 0.4652 | 4.0 | 1272 | 0.4081 | 0.9352 |
68
+ | 0.3364 | 5.0 | 1590 | 0.3538 | 0.9442 |
69
+ | 0.2801 | 6.0 | 1908 | 0.3294 | 0.9465 |
70
+ | 0.2515 | 7.0 | 2226 | 0.3165 | 0.9471 |
71
+ | 0.2366 | 8.0 | 2544 | 0.3107 | 0.9487 |
72
+ | 0.2292 | 9.0 | 2862 | 0.3069 | 0.9490 |
73
+ | 0.2247 | 10.0 | 3180 | 0.3060 | 0.9487 |
74
 
75
 
76
  ### Framework versions