Hugging Face's logo

pradanaadn
/
vit-emotional-classifier

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
pradanaadn commited on
Commit
7f5c5f1
•
1 Parent(s): 6d39eef

End of training

Browse files
Files changed (3) hide show
  1. README.md +14 -14
  2. model.safetensors +1 -1
  3. runs/Jun05_09-22-24_f8aa38a62fb7/events.out.tfevents.1717579746.f8aa38a62fb7.237.10 +3 -0
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.63125
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 [pradanaadn/vit-emotional-classifier](https://huggingface.co/pradanaadn/vit-emotional-classifier) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 1.1830
36
- - Accuracy: 0.6312
37
 
38
  ## Model description
39
 
@@ -57,23 +57,23 @@ The following hyperparameters were used during training:
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: cosine_with_restarts
61
  - num_epochs: 5
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
- | 0.9412 | 0.5 | 20 | 1.3606 | 0.575 |
68
- | 0.8621 | 1.0 | 40 | 1.3134 | 0.6125 |
69
- | 0.8025 | 1.5 | 60 | 1.2917 | 0.6062 |
70
- | 0.7077 | 2.0 | 80 | 1.2553 | 0.6062 |
71
- | 0.7259 | 2.5 | 100 | 1.2128 | 0.625 |
72
- | 0.5685 | 3.0 | 120 | 1.2036 | 0.625 |
73
- | 0.5604 | 3.5 | 140 | 1.2057 | 0.6062 |
74
- | 0.4817 | 4.0 | 160 | 1.1830 | 0.6312 |
75
- | 0.4421 | 4.5 | 180 | 1.2004 | 0.5875 |
76
- | 0.4692 | 5.0 | 200 | 1.1568 | 0.6188 |
77
 
78
 
79
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.65625
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 [pradanaadn/vit-emotional-classifier](https://huggingface.co/pradanaadn/vit-emotional-classifier) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 1.1495
36
+ - Accuracy: 0.6562
37
 
38
  ## Model description
39
 
 
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
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
+ | 0.4801 | 0.5 | 20 | 1.2238 | 0.5875 |
68
+ | 0.4681 | 1.0 | 40 | 1.2062 | 0.6188 |
69
+ | 0.3414 | 1.5 | 60 | 1.1674 | 0.6 |
70
+ | 0.2972 | 2.0 | 80 | 1.1362 | 0.6125 |
71
+ | 0.2503 | 2.5 | 100 | 1.1508 | 0.6 |
72
+ | 0.1872 | 3.0 | 120 | 1.1495 | 0.6562 |
73
+ | 0.1929 | 3.5 | 140 | 1.1998 | 0.5875 |
74
+ | 0.1883 | 4.0 | 160 | 1.2023 | 0.5938 |
75
+ | 0.1729 | 4.5 | 180 | 1.2130 | 0.6 |
76
+ | 0.2007 | 5.0 | 200 | 1.2021 | 0.5813 |
77
 
78
 
79
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6447b4444314cfb6fca9554a42b7f40b05c36cd8e6b76c9f3788b7028175b134
3
  size 343242432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e06daf1b5092c4b1dcc4c6e866809668ed60e89ad98214c50be59d86c14c433
3
  size 343242432
runs/Jun05_09-22-24_f8aa38a62fb7/events.out.tfevents.1717579746.f8aa38a62fb7.237.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08c5528d165645cba7e67b274a2e63b98d8c97891954b4b854de00b8cbe99486
3
+ size 411