Hugging Face's logo

winegarj
/
distilbert-base-uncased-finetuned-sst2

Text Classification
Transformers
PyTorch
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Community
5
winegarj commited on
Commit
1f0712a
•
1 Parent(s): 85cbf31

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +18 -16
README.md CHANGED
@@ -15,11 +15,13 @@ model-index:
15
  dataset:
16
  name: glue
17
  type: glue
 
 
18
  args: sst2
19
  metrics:
20
  - name: Accuracy
21
  type: accuracy
22
- value: 0.908256880733945
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,8 +31,8 @@ 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 glue dataset.
31
  It achieves the following results on the evaluation set:
32
- - Loss: 0.4493
33
- - Accuracy: 0.9083
34
 
35
  ## Model description
36
 
@@ -50,8 +52,8 @@ More information needed
50
 
51
  The following hyperparameters were used during training:
52
  - learning_rate: 2e-05
53
- - train_batch_size: 32
54
- - eval_batch_size: 32
55
  - seed: 42
56
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
57
  - lr_scheduler_type: linear
@@ -59,18 +61,18 @@ The following hyperparameters were used during training:
59
 
60
  ### Training results
61
 
62
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
63
- |:-------------:|:-----:|:-----:|:---------------:|:--------:|
64
- | 0.1804 | 1.0 | 2105 | 0.2843 | 0.9025 |
65
- | 0.1216 | 2.0 | 4210 | 0.3242 | 0.9025 |
66
- | 0.0871 | 3.0 | 6315 | 0.3320 | 0.9060 |
67
- | 0.0607 | 4.0 | 8420 | 0.3913 | 0.9025 |
68
- | 0.0429 | 5.0 | 10525 | 0.4493 | 0.9083 |
69
 
70
 
71
  ### Framework versions
72
 
73
- - Transformers 4.18.0
74
- - Pytorch 1.12.0.dev20220409+cu115
75
- - Datasets 2.0.0
76
- - Tokenizers 0.12.0
 
15
  dataset:
16
  name: glue
17
  type: glue
18
+ config: sst2
19
+ split: train
20
  args: sst2
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
+ value: 0.9025229357798165
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 [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the glue dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 0.2823
35
+ - Accuracy: 0.9025
36
 
37
  ## Model description
38
 
 
52
 
53
  The following hyperparameters were used during training:
54
  - learning_rate: 2e-05
55
+ - train_batch_size: 512
56
+ - eval_batch_size: 512
57
  - seed: 42
58
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
  - lr_scheduler_type: linear
 
61
 
62
  ### Training results
63
 
64
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
65
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
66
+ | No log | 1.0 | 132 | 0.2528 | 0.8933 |
67
+ | No log | 2.0 | 264 | 0.2675 | 0.8979 |
68
+ | No log | 3.0 | 396 | 0.2823 | 0.9025 |
69
+ | 0.1898 | 4.0 | 528 | 0.2986 | 0.8968 |
70
+ | 0.1898 | 5.0 | 660 | 0.3029 | 0.9002 |
71
 
72
 
73
  ### Framework versions
74
 
75
+ - Transformers 4.21.1
76
+ - Pytorch 1.12.1+cu116
77
+ - Datasets 2.4.0
78
+ - Tokenizers 0.12.1