Hugging Face's logo

sepehrbakhshi
/
bert-base-uncased-finetuned-cola_HW2_sepehr_bakhshi_dropout_05

Text Classification
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
sepehrbakhshi commited on
Commit
fda9330
•
1 Parent(s): 72e5c66

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +27 -8
README.md CHANGED
@@ -21,7 +21,7 @@ model-index:
21
  metrics:
22
  - name: Matthews Correlation
23
  type: matthews_correlation
24
- value: 0.5152882228132933
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 [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the glue dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 0.4508
35
- - Matthews Correlation: 0.5153
36
 
37
  ## Model description
38
 
@@ -51,19 +51,38 @@ More information needed
51
  ### Training hyperparameters
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
- - num_epochs: 1
61
 
62
  ### Training results
63
 
64
- | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
65
- |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
66
- | 0.4886 | 1.0 | 535 | 0.4508 | 0.5153 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
67
 
68
 
69
  ### Framework versions
 
21
  metrics:
22
  - name: Matthews Correlation
23
  type: matthews_correlation
24
+ value: 0.5779953180551635
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 [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the glue dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 1.4260
35
+ - Matthews Correlation: 0.5780
36
 
37
  ## Model description
38
 
 
51
  ### Training hyperparameters
52
 
53
  The following hyperparameters were used during training:
54
+ - learning_rate: 7.530341440816975e-06
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
+ - num_epochs: 20
61
 
62
  ### Training results
63
 
64
+ | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
65
+ |:-------------:|:-----:|:-----:|:---------------:|:--------------------:|
66
+ | 0.5137 | 1.0 | 535 | 0.4936 | 0.4808 |
67
+ | 0.362 | 2.0 | 1070 | 0.4270 | 0.5781 |
68
+ | 0.2679 | 3.0 | 1605 | 0.6409 | 0.5148 |
69
+ | 0.2046 | 4.0 | 2140 | 0.5658 | 0.5892 |
70
+ | 0.1736 | 5.0 | 2675 | 0.7711 | 0.5624 |
71
+ | 0.1378 | 6.0 | 3210 | 0.8053 | 0.5956 |
72
+ | 0.1137 | 7.0 | 3745 | 0.9714 | 0.5523 |
73
+ | 0.0903 | 8.0 | 4280 | 0.9119 | 0.5735 |
74
+ | 0.0839 | 9.0 | 4815 | 1.0448 | 0.5839 |
75
+ | 0.0629 | 10.0 | 5350 | 1.2056 | 0.5521 |
76
+ | 0.0577 | 11.0 | 5885 | 1.1880 | 0.5889 |
77
+ | 0.0505 | 12.0 | 6420 | 1.1722 | 0.5836 |
78
+ | 0.0519 | 13.0 | 6955 | 1.2863 | 0.5884 |
79
+ | 0.0369 | 14.0 | 7490 | 1.2971 | 0.5608 |
80
+ | 0.032 | 15.0 | 8025 | 1.3024 | 0.5785 |
81
+ | 0.0244 | 16.0 | 8560 | 1.3904 | 0.5737 |
82
+ | 0.0166 | 17.0 | 9095 | 1.4044 | 0.5778 |
83
+ | 0.0185 | 18.0 | 9630 | 1.4234 | 0.5650 |
84
+ | 0.0168 | 19.0 | 10165 | 1.4384 | 0.5727 |
85
+ | 0.0224 | 20.0 | 10700 | 1.4260 | 0.5780 |
86
 
87
 
88
  ### Framework versions