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
56f59a9
•
1 Parent(s): 18841c8

End of training

Browse files
Files changed (2) hide show
  1. README.md +10 -15
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -17,12 +17,12 @@ model-index:
17
  name: imagefolder
18
  type: imagefolder
19
  config: default
20
- split: train
21
  args: default
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.15
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: 2.1605
36
- - Accuracy: 0.15
37
 
38
  ## Model description
39
 
@@ -58,22 +58,17 @@ The following hyperparameters were used during training:
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
- - num_epochs: 10
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
- | No log | 1.0 | 10 | 2.3360 | 0.1125 |
68
- | No log | 2.0 | 20 | 2.2480 | 0.1187 |
69
- | No log | 3.0 | 30 | 2.1605 | 0.15 |
70
- | No log | 4.0 | 40 | 2.1227 | 0.15 |
71
- | No log | 5.0 | 50 | 2.1005 | 0.1125 |
72
- | No log | 6.0 | 60 | 2.1004 | 0.1062 |
73
- | No log | 7.0 | 70 | 2.0920 | 0.1062 |
74
- | No log | 8.0 | 80 | 2.0841 | 0.1125 |
75
- | No log | 9.0 | 90 | 2.0897 | 0.1062 |
76
- | No log | 10.0 | 100 | 2.0876 | 0.1062 |
77
 
78
 
79
  ### Framework versions
 
17
  name: imagefolder
18
  type: imagefolder
19
  config: default
20
+ split: train[:600]
21
  args: default
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.15833333333333333
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: 1.8191
36
+ - Accuracy: 0.1583
37
 
38
  ## Model description
39
 
 
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 | 8 | 1.8607 | 0.125 |
68
+ | No log | 2.0 | 16 | 1.8180 | 0.1833 |
69
+ | No log | 3.0 | 24 | 1.7982 | 0.1667 |
70
+ | No log | 4.0 | 32 | 1.8021 | 0.1583 |
71
+ | No log | 5.0 | 40 | 1.8006 | 0.1083 |
 
 
 
 
 
72
 
73
 
74
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:879698d0d3d0b5d4c30bdc1a28c294f2c10c8ed5a253911444126127ce3a130e
3
  size 343287149
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1345f7c1ba220013627b822c493a8d93280ba5bcfba69497597f9f0309dbcd3e
3
  size 343287149