Hugging Face's logo

jetaimejeteveux
/
vit-emotions-fp16

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
jetaimejeteveux commited on
Commit
17fb491
·
verified ·
1 Parent(s): 40bb165

End of training

Browse files
Files changed (3) hide show
  1. README.md +55 -10
  2. model.safetensors +1 -1
  3. runs/Feb16_14-39-49_2bc63bcddec7/events.out.tfevents.1708096109.2bc63bcddec7.1650.1 +3 -0
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.6640625
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: 1.2090
36
- - Accuracy: 0.6641
37
 
38
  ## Model description
39
 
@@ -52,23 +52,68 @@ More information needed
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
- - learning_rate: 6e-05
56
  - train_batch_size: 16
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
- | No log | 1.0 | 40 | 1.8810 | 0.275 |
68
- | No log | 2.0 | 80 | 1.5765 | 0.4 |
69
- | No log | 3.0 | 120 | 1.4703 | 0.4313 |
70
- | No log | 4.0 | 160 | 1.4378 | 0.4437 |
71
- | No log | 5.0 | 200 | 1.4365 | 0.4688 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
72
 
73
 
74
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.9859375
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: 0.0725
36
+ - Accuracy: 0.9859
37
 
38
  ## Model description
39
 
 
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
+ - learning_rate: 5e-05
56
  - train_batch_size: 16
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: 50
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
+ | No log | 1.0 | 40 | 1.3965 | 0.4938 |
68
+ | No log | 2.0 | 80 | 1.4154 | 0.425 |
69
+ | No log | 3.0 | 120 | 1.3729 | 0.4562 |
70
+ | No log | 4.0 | 160 | 1.3532 | 0.4562 |
71
+ | No log | 5.0 | 200 | 1.2993 | 0.5062 |
72
+ | No log | 6.0 | 240 | 1.3438 | 0.4938 |
73
+ | No log | 7.0 | 280 | 1.3741 | 0.5 |
74
+ | No log | 8.0 | 320 | 1.5267 | 0.4313 |
75
+ | No log | 9.0 | 360 | 1.2778 | 0.5375 |
76
+ | No log | 10.0 | 400 | 1.3864 | 0.5062 |
77
+ | No log | 11.0 | 440 | 1.4221 | 0.4875 |
78
+ | No log | 12.0 | 480 | 1.5059 | 0.5062 |
79
+ | 0.7596 | 13.0 | 520 | 1.5004 | 0.5188 |
80
+ | 0.7596 | 14.0 | 560 | 1.4539 | 0.5125 |
81
+ | 0.7596 | 15.0 | 600 | 1.5219 | 0.5375 |
82
+ | 0.7596 | 16.0 | 640 | 1.6179 | 0.4813 |
83
+ | 0.7596 | 17.0 | 680 | 1.4562 | 0.55 |
84
+ | 0.7596 | 18.0 | 720 | 1.5473 | 0.4875 |
85
+ | 0.7596 | 19.0 | 760 | 1.5820 | 0.5188 |
86
+ | 0.7596 | 20.0 | 800 | 1.5877 | 0.5125 |
87
+ | 0.7596 | 21.0 | 840 | 1.4965 | 0.55 |
88
+ | 0.7596 | 22.0 | 880 | 1.5947 | 0.5375 |
89
+ | 0.7596 | 23.0 | 920 | 1.4672 | 0.5437 |
90
+ | 0.7596 | 24.0 | 960 | 1.7930 | 0.5 |
91
+ | 0.2328 | 25.0 | 1000 | 1.8033 | 0.4875 |
92
+ | 0.2328 | 26.0 | 1040 | 1.7193 | 0.5312 |
93
+ | 0.2328 | 27.0 | 1080 | 1.8072 | 0.4813 |
94
+ | 0.2328 | 28.0 | 1120 | 1.6767 | 0.5437 |
95
+ | 0.2328 | 29.0 | 1160 | 1.6138 | 0.5625 |
96
+ | 0.2328 | 30.0 | 1200 | 1.8484 | 0.4938 |
97
+ | 0.2328 | 31.0 | 1240 | 1.7691 | 0.5062 |
98
+ | 0.2328 | 32.0 | 1280 | 1.7797 | 0.5062 |
99
+ | 0.2328 | 33.0 | 1320 | 1.7575 | 0.5375 |
100
+ | 0.2328 | 34.0 | 1360 | 1.7550 | 0.5062 |
101
+ | 0.2328 | 35.0 | 1400 | 1.7933 | 0.5 |
102
+ | 0.2328 | 36.0 | 1440 | 1.7056 | 0.5563 |
103
+ | 0.2328 | 37.0 | 1480 | 1.8739 | 0.4938 |
104
+ | 0.1517 | 38.0 | 1520 | 1.7637 | 0.5188 |
105
+ | 0.1517 | 39.0 | 1560 | 1.7178 | 0.5563 |
106
+ | 0.1517 | 40.0 | 1600 | 1.9114 | 0.5 |
107
+ | 0.1517 | 41.0 | 1640 | 1.8453 | 0.5188 |
108
+ | 0.1517 | 42.0 | 1680 | 1.7571 | 0.5625 |
109
+ | 0.1517 | 43.0 | 1720 | 1.7757 | 0.5437 |
110
+ | 0.1517 | 44.0 | 1760 | 1.8389 | 0.5125 |
111
+ | 0.1517 | 45.0 | 1800 | 1.8109 | 0.5375 |
112
+ | 0.1517 | 46.0 | 1840 | 1.8537 | 0.4688 |
113
+ | 0.1517 | 47.0 | 1880 | 1.7422 | 0.5563 |
114
+ | 0.1517 | 48.0 | 1920 | 1.7807 | 0.5687 |
115
+ | 0.1517 | 49.0 | 1960 | 1.8111 | 0.525 |
116
+ | 0.1045 | 50.0 | 2000 | 1.9057 | 0.5125 |
117
 
118
 
119
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d4235e9f102b0a180e66d2b7b6482340f1bc838d7581e3de8a7bd0d3e80e0c0
3
  size 343242432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e3375a2f68c708910106001cac7fe167535cfd83b968323aaf93a78e37ddcc7
3
  size 343242432
runs/Feb16_14-39-49_2bc63bcddec7/events.out.tfevents.1708096109.2bc63bcddec7.1650.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccb74df4ef81933c138d0f9a04aae047c4224ceca86cd16bf5e5ebdfb0e3edad
3
+ size 411