Hugging Face's logo

motheecreator
/
vit-Facial-Expression-Recognition

Image Classification
Transformers
TensorBoard
Safetensors
vit
Inference Endpoints
Model card Files Metrics Community
motheecreator commited on
Commit
f8f9aa5
•
1 Parent(s): 7fc3a96

End of training

Browse files
Files changed (3) hide show
  1. README.md +31 -39
  2. all_results.json +6 -5
  3. eval_results.json +6 -5
README.md CHANGED
@@ -3,26 +3,11 @@ license: apache-2.0
3
  base_model: motheecreator/vit-Facial-Expression-Recognition
4
  tags:
5
  - generated_from_trainer
6
- datasets:
7
- - image_folder
8
  metrics:
9
  - accuracy
10
  model-index:
11
  - name: vit-Facial-Expression-Recognition
12
- results:
13
- - task:
14
- name: Image Classification
15
- type: image-classification
16
- dataset:
17
- name: image_folder
18
- type: image_folder
19
- config: default
20
- split: train
21
- args: default
22
- metrics:
23
- - name: Accuracy
24
- type: accuracy
25
- value: 0.7444126074498567
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
30
 
31
  # vit-Facial-Expression-Recognition
32
 
33
- This model is a fine-tuned version of [motheecreator/vit-Facial-Expression-Recognition](https://huggingface.co/motheecreator/vit-Facial-Expression-Recognition) on the image_folder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.7038
36
- - Accuracy: 0.7444
37
 
38
  ## Model description
39
 
@@ -52,31 +37,38 @@ More information needed
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
- - learning_rate: 5e-05
56
- - train_batch_size: 8
57
- - eval_batch_size: 8
58
  - seed: 42
59
- - gradient_accumulation_steps: 4
60
- - total_train_batch_size: 32
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: 10
65
 
66
  ### Training results
67
 
68
- | Training Loss | Epoch | Step | Accuracy | Validation Loss |
69
- |:-------------:|:-----:|:----:|:--------:|:---------------:|
70
- | 0.7175 | 1.0 | 654 | 0.7309 | 0.7081 |
71
- | 0.6952 | 2.0 | 1308 | 0.7379 | 0.6931 |
72
- | 0.5041 | 3.0 | 1962 | 0.7444 | 0.7038 |
73
- | 0.2461 | 4.0 | 2617 | 0.7393 | 0.7843 |
74
- | 0.1846 | 5.0 | 3270 | 0.7391 | 0.8219 |
75
- | 0.276 | 6.0 | 3924 | 0.8876 | 0.7335 |
76
- | 0.2217 | 7.0 | 4578 | 0.9752 | 0.7255 |
77
- | 0.0646 | 8.0 | 5232 | 1.0957 | 0.7263 |
78
- | 0.063 | 9.0 | 5887 | 1.1335 | 0.7263 |
79
- | 0.0562 | 10.0 | 6540 | 1.1663 | 0.7307 |
 
 
 
 
 
 
 
80
 
81
 
82
  ### Framework versions
 
3
  base_model: motheecreator/vit-Facial-Expression-Recognition
4
  tags:
5
  - generated_from_trainer
 
 
6
  metrics:
7
  - accuracy
8
  model-index:
9
  - name: vit-Facial-Expression-Recognition
10
+ results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
15
 
16
  # vit-Facial-Expression-Recognition
17
 
18
+ This model is a fine-tuned version of [motheecreator/vit-Facial-Expression-Recognition](https://huggingface.co/motheecreator/vit-Facial-Expression-Recognition) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.4503
21
+ - Accuracy: 0.8434
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 3e-05
41
+ - train_batch_size: 32
42
+ - eval_batch_size: 32
43
  - seed: 42
44
+ - gradient_accumulation_steps: 8
45
+ - total_train_batch_size: 256
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: cosine
48
+ - lr_scheduler_warmup_steps: 1000
49
+ - num_epochs: 3
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
+ | 1.3548 | 0.17 | 100 | 0.8024 | 0.7418 |
56
+ | 1.047 | 0.34 | 200 | 0.6823 | 0.7653 |
57
+ | 0.9398 | 0.51 | 300 | 0.6264 | 0.7827 |
58
+ | 0.8618 | 0.67 | 400 | 0.5857 | 0.7973 |
59
+ | 0.8363 | 0.84 | 500 | 0.5532 | 0.8104 |
60
+ | 0.8018 | 1.01 | 600 | 0.5279 | 0.8196 |
61
+ | 0.7567 | 1.18 | 700 | 0.5110 | 0.8248 |
62
+ | 0.7521 | 1.35 | 800 | 0.5080 | 0.8259 |
63
+ | 0.741 | 1.52 | 900 | 0.5002 | 0.8271 |
64
+ | 0.7229 | 1.69 | 1000 | 0.4967 | 0.8263 |
65
+ | 0.7157 | 1.85 | 1100 | 0.4876 | 0.8326 |
66
+ | 0.6868 | 2.02 | 1200 | 0.4836 | 0.8342 |
67
+ | 0.6605 | 2.19 | 1300 | 0.4711 | 0.8384 |
68
+ | 0.6449 | 2.36 | 1400 | 0.4608 | 0.8406 |
69
+ | 0.6085 | 2.53 | 1500 | 0.4503 | 0.8434 |
70
+ | 0.6178 | 2.7 | 1600 | 0.4434 | 0.8478 |
71
+ | 0.6166 | 2.87 | 1700 | 0.4420 | 0.8486 |
72
 
73
 
74
  ### Framework versions
all_results.json CHANGED
@@ -1,7 +1,8 @@
1
  {
2
- "eval_accuracy": 0.5408453673447876,
3
- "eval_loss": 1.5916377305984497,
4
- "eval_runtime": 393.1956,
5
- "eval_samples_per_second": 96.512,
6
- "eval_steps_per_second": 12.065
 
7
  }
 
1
  {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.8434436597449141,
4
+ "eval_loss": 0.45033568143844604,
5
+ "eval_runtime": 339.8465,
6
+ "eval_samples_per_second": 111.662,
7
+ "eval_steps_per_second": 3.49
8
  }
eval_results.json CHANGED
@@ -1,7 +1,8 @@
1
  {
2
- "eval_accuracy": 0.5408453673447876,
3
- "eval_loss": 1.5916377305984497,
4
- "eval_runtime": 393.1956,
5
- "eval_samples_per_second": 96.512,
6
- "eval_steps_per_second": 12.065
 
7
  }
 
1
  {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.8434436597449141,
4
+ "eval_loss": 0.45033568143844604,
5
+ "eval_runtime": 339.8465,
6
+ "eval_samples_per_second": 111.662,
7
+ "eval_steps_per_second": 3.49
8
  }