Hugging Face's logo

kensvin
/
emotion_classification

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
kensvin commited on
Commit
402cc76
•
1 Parent(s): 0fc63d6

End of training

Browse files
Files changed (2) hide show
  1. README.md +12 -13
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.1
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 [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 2.0858
36
- - Accuracy: 0.1
37
 
38
  ## Model description
39
 
@@ -52,24 +52,23 @@ 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
- - gradient_accumulation_steps: 4
60
- - total_train_batch_size: 64
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
- - lr_scheduler_warmup_ratio: 0.1
64
- - num_epochs: 3
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 2.0873 | 1.0 | 10 | 2.0876 | 0.1062 |
71
- | 2.0773 | 2.0 | 20 | 2.0864 | 0.1 |
72
- | 2.0798 | 3.0 | 30 | 2.0903 | 0.1562 |
 
 
73
 
74
 
75
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.1125
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 [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 2.0843
36
+ - Accuracy: 0.1125
37
 
38
  ## Model description
39
 
 
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
+ - learning_rate: 0.001
56
+ - train_batch_size: 64
57
+ - eval_batch_size: 64
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
 
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
+ | No log | 1.0 | 10 | 2.0843 | 0.1313 |
68
+ | No log | 2.0 | 20 | 2.0856 | 0.1 |
69
+ | No log | 3.0 | 30 | 2.0849 | 0.1125 |
70
+ | No log | 4.0 | 40 | 2.0856 | 0.1 |
71
+ | No log | 5.0 | 50 | 2.0857 | 0.1125 |
72
 
73
 
74
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:453331d1e8c2968a5c2782c752ab4024d5c5ce3309b44681fd357220024159f2
3
  size 343287149
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a25a97508db88a813fd02629d22ccb97dcc30be0c7740fa5057fc0f35fc52820
3
  size 343287149