Hugging Face's logo

minhdang1
/
vit-base-patch16-224-finetuned-eurosat

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
minhdang1 commited on
Commit
1d99309
•
1 Parent(s): 5517788

Model save

Browse files
Files changed (3) hide show
  1. README.md +18 -11
  2. model.safetensors +1 -1
  3. runs/Jun18_21-55-04_DangPC/events.out.tfevents.1718722504.DangPC.22553.0 +2 -2
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: 0.8554216867469879
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](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.3497
36
- - Accuracy: 0.8554
37
 
38
  ## Model description
39
 
@@ -53,23 +53,30 @@ More information needed
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 5e-05
56
- - train_batch_size: 32
57
- - eval_batch_size: 32
58
  - seed: 42
59
  - gradient_accumulation_steps: 4
60
- - total_train_batch_size: 128
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
- | 1.3804 | 0.97 | 17 | 0.5244 | 0.8193 |
71
- | 0.52 | 2.0 | 35 | 0.3712 | 0.8394 |
72
- | 0.3909 | 2.91 | 51 | 0.3497 | 0.8554 |
 
 
 
 
 
 
 
73
 
74
 
75
  ### Framework versions
 
17
  name: imagefolder
18
  type: imagefolder
19
  config: default
20
+ split: test
21
  args: default
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.8446601941747572
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](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.3894
36
+ - Accuracy: 0.8447
37
 
38
  ## Model description
39
 
 
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 5e-05
56
+ - train_batch_size: 128
57
+ - eval_batch_size: 128
58
  - seed: 42
59
  - gradient_accumulation_steps: 4
60
+ - total_train_batch_size: 512
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 | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | No log | 1.0 | 5 | 1.0761 | 0.5469 |
71
+ | 1.1435 | 2.0 | 10 | 0.6466 | 0.7735 |
72
+ | 1.1435 | 3.0 | 15 | 0.4962 | 0.8123 |
73
+ | 0.5372 | 4.0 | 20 | 0.4365 | 0.8252 |
74
+ | 0.5372 | 5.0 | 25 | 0.4118 | 0.8382 |
75
+ | 0.362 | 6.0 | 30 | 0.4031 | 0.8414 |
76
+ | 0.362 | 7.0 | 35 | 0.3944 | 0.8511 |
77
+ | 0.3028 | 8.0 | 40 | 0.3930 | 0.8414 |
78
+ | 0.3028 | 9.0 | 45 | 0.3928 | 0.8479 |
79
+ | 0.2708 | 10.0 | 50 | 0.3894 | 0.8447 |
80
 
81
 
82
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:440eb6ca2ac0a01eecd7d1fce55eb081f1b1f4a1afaf7f971839a8d2f1bb7490
3
  size 343230128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abe12790a2a3a3c6f3d1102566dfbf9a1bdf70611dc5cc0ad741df1d461a1ece
3
  size 343230128
runs/Jun18_21-55-04_DangPC/events.out.tfevents.1718722504.DangPC.22553.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62bf2dd548477329379a6fb40348b603e1bf1c82b40d2e6725b659c615e66f66
3
- size 7543
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f146dca2db80b0aafc951ef429b9dcad843090f6687e12bee4429c8c8ad6b8a
3
+ size 8679