Hugging Face's logo

stuser2023
/
distilbert-base-uncased-finetuned-cola

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
stuser2023 commited on
Commit
a8c46e3
•
1 Parent(s): 0e5aaf1

End of training

Browse files
Files changed (2) hide show
  1. README.md +11 -11
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Matthews Correlation
24
  type: matthews_correlation
25
- value: 0.5383825234212567
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 glue dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 1.1576
36
- - Matthews Correlation: 0.5384
37
 
38
  ## Model description
39
 
@@ -52,10 +52,10 @@ More information needed
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
- - learning_rate: 2e-05
56
- - train_batch_size: 16
57
  - eval_batch_size: 16
58
- - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
  - num_epochs: 5
@@ -64,11 +64,11 @@ The following hyperparameters were used during training:
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
67
- | 0.1317 | 1.0 | 535 | 0.9153 | 0.5159 |
68
- | 0.091 | 2.0 | 1070 | 1.0238 | 0.4934 |
69
- | 0.0741 | 3.0 | 1605 | 1.0645 | 0.5224 |
70
- | 0.0551 | 4.0 | 2140 | 1.1498 | 0.5321 |
71
- | 0.0588 | 5.0 | 2675 | 1.1576 | 0.5384 |
72
 
73
 
74
  ### Framework versions
 
22
  metrics:
23
  - name: Matthews Correlation
24
  type: matthews_correlation
25
+ value: 0.5120519207329847
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 glue dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.6114
36
+ - Matthews Correlation: 0.5121
37
 
38
  ## Model description
39
 
 
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
+ - learning_rate: 1.6477448170002332e-05
56
+ - train_batch_size: 32
57
  - eval_batch_size: 16
58
+ - seed: 34
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
  - num_epochs: 5
 
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
67
+ | No log | 1.0 | 268 | 0.4802 | 0.4522 |
68
+ | 0.4583 | 2.0 | 536 | 0.5012 | 0.4811 |
69
+ | 0.4583 | 3.0 | 804 | 0.5001 | 0.5202 |
70
+ | 0.2539 | 4.0 | 1072 | 0.5616 | 0.5291 |
71
+ | 0.2539 | 5.0 | 1340 | 0.6114 | 0.5121 |
72
 
73
 
74
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ccdf837c8ebda4caa44681d02bb2d6ae6b721c17415e8e1a9bdb75243aad05a
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1402dcc1a9ea22b48cf3678b18d6951fa650c0a1abcbdb78851001f2e57e5684
3
  size 267832560