Hugging Face's logo

itsLeen
/
finetuned-fake-food

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
itsLeen commited on
Commit
635f04a
•
1 Parent(s): 0e4f896

Model save

Browse files
Files changed (5) hide show
  1. README.md +19 -16
  2. config.json +8 -0
  3. model.safetensors +1 -1
  4. runs/Oct02_14-40-06_dcbb13f74eeb/events.out.tfevents.1727880032.dcbb13f74eeb.1604.0 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -23,7 +23,7 @@ model-index:
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
- value: 0.8234200743494424
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
33
 
34
  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.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 0.3684
37
- - Accuracy: 0.8234
38
 
39
  ## Model description
40
 
@@ -53,26 +53,29 @@ More information needed
53
  ### Training hyperparameters
54
 
55
  The following hyperparameters were used during training:
56
- - learning_rate: 0.0002
57
- - train_batch_size: 16
58
  - eval_batch_size: 8
59
  - seed: 42
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
- - lr_scheduler_type: linear
62
- - num_epochs: 4
63
  - mixed_precision_training: Native AMP
64
 
65
  ### Training results
66
 
67
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
- |:-------------:|:------:|:----:|:---------------:|:--------:|
69
- | 0.5282 | 0.5236 | 100 | 0.6420 | 0.6506 |
70
- | 0.5825 | 1.0471 | 200 | 0.4441 | 0.7937 |
71
- | 0.5148 | 1.5707 | 300 | 0.4870 | 0.7342 |
72
- | 0.5144 | 2.0942 | 400 | 0.6652 | 0.6580 |
73
- | 0.493 | 2.6178 | 500 | 0.4075 | 0.8141 |
74
- | 0.4884 | 3.1414 | 600 | 0.4667 | 0.7732 |
75
- | 0.3899 | 3.6649 | 700 | 0.3684 | 0.8234 |
 
 
 
76
 
77
 
78
  ### Framework versions
 
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
+ value: 0.8011152416356877
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
33
 
34
  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.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 0.5222
37
+ - Accuracy: 0.8011
38
 
39
  ## Model description
40
 
 
53
  ### Training hyperparameters
54
 
55
  The following hyperparameters were used during training:
56
+ - learning_rate: 0.0001
57
+ - train_batch_size: 2
58
  - eval_batch_size: 8
59
  - seed: 42
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
+ - lr_scheduler_type: cosine
62
+ - num_epochs: 10
63
  - mixed_precision_training: Native AMP
64
 
65
  ### Training results
66
 
67
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
69
+ | 0.717 | 1.0 | 1522 | 0.8198 | 0.5186 |
70
+ | 0.7935 | 2.0 | 3044 | 0.6689 | 0.6989 |
71
+ | 0.7885 | 3.0 | 4566 | 0.5983 | 0.7082 |
72
+ | 0.7315 | 4.0 | 6088 | 0.6050 | 0.7398 |
73
+ | 0.7526 | 5.0 | 7610 | 0.6488 | 0.7454 |
74
+ | 0.7844 | 6.0 | 9132 | 0.6292 | 0.7584 |
75
+ | 0.8785 | 7.0 | 10654 | 0.5291 | 0.7900 |
76
+ | 0.529 | 8.0 | 12176 | 0.4577 | 0.8160 |
77
+ | 0.9946 | 9.0 | 13698 | 0.4851 | 0.8160 |
78
+ | 0.7006 | 10.0 | 15220 | 0.5222 | 0.8011 |
79
 
80
 
81
  ### Framework versions
config.json CHANGED
@@ -8,9 +8,17 @@
8
  "hidden_act": "gelu",
9
  "hidden_dropout_prob": 0.0,
10
  "hidden_size": 768,
 
 
 
 
11
  "image_size": 224,
12
  "initializer_range": 0.02,
13
  "intermediate_size": 3072,
 
 
 
 
14
  "layer_norm_eps": 1e-12,
15
  "model_type": "vit",
16
  "num_attention_heads": 12,
 
8
  "hidden_act": "gelu",
9
  "hidden_dropout_prob": 0.0,
10
  "hidden_size": 768,
11
+ "id2label": {
12
+ "0": 0,
13
+ "1": 1
14
+ },
15
  "image_size": 224,
16
  "initializer_range": 0.02,
17
  "intermediate_size": 3072,
18
+ "label2id": {
19
+ "0": "0",
20
+ "1": "1"
21
+ },
22
  "layer_norm_eps": 1e-12,
23
  "model_type": "vit",
24
  "num_attention_heads": 12,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2db04dca56c64c7c9b7d5cd25ca47c182f972392b6e7557f8ec072a0f5f98aac
3
  size 343223968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f96ad6896ae934f3ebc65ef27bc7bc9170fa060f905eeba7398b34f6cfa6737
3
  size 343223968
runs/Oct02_14-40-06_dcbb13f74eeb/events.out.tfevents.1727880032.dcbb13f74eeb.1604.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0160fe601d3b4cedf0dea2077d106c2818632af009ece69271360694d6b853f
3
+ size 329554
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8fb02a0a2cba10384d13aa30d74774be5892cf68173be206e8a561269e8d9a9
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abeb52e96ac7f76ce392655f864ffc8d4f25020703f19d61bcd76e5c61524d99
3
  size 5176