Hugging Face's logo

pkr7098
/
vit-cifar100-cifar100

Image Classification
Transformers
Safetensors
vit
vision
Generated from Trainer
Inference Endpoints
Model card Files Community
pkr7098 commited on
Commit
aee3386
•
1 Parent(s): 1e7dd94

Model save

Browse files
Files changed (3) hide show
  1. README.md +10 -12
  2. config.json +0 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -3,8 +3,6 @@ library_name: transformers
3
  license: apache-2.0
4
  base_model: google/vit-base-patch16-224-in21k
5
  tags:
6
- - image-classification
7
- - vision
8
  - generated_from_trainer
9
  metrics:
10
  - accuracy
@@ -18,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  # vit-cifar100-cifar100
20
 
21
- 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 cifar100 dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.2955
24
  - Accuracy: 0.9241
 
25
 
26
  ## Model description
27
 
@@ -40,7 +38,7 @@ More information needed
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
- - learning_rate: 2e-05
44
  - train_batch_size: 8
45
  - eval_batch_size: 8
46
  - seed: 1337
@@ -50,13 +48,13 @@ The following hyperparameters were used during training:
50
 
51
  ### Training results
52
 
53
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
- |:-------------:|:-----:|:-----:|:---------------:|:--------:|
55
- | 1.4469 | 1.0 | 5313 | 1.1871 | 0.8716 |
56
- | 0.7861 | 2.0 | 10626 | 0.4685 | 0.9056 |
57
- | 0.732 | 3.0 | 15939 | 0.3551 | 0.9139 |
58
- | 0.3327 | 4.0 | 21252 | 0.3090 | 0.9199 |
59
- | 0.4886 | 5.0 | 26565 | 0.2955 | 0.9241 |
60
 
61
 
62
  ### Framework versions
 
3
  license: apache-2.0
4
  base_model: google/vit-base-patch16-224-in21k
5
  tags:
 
 
6
  - generated_from_trainer
7
  metrics:
8
  - accuracy
 
16
 
17
  # vit-cifar100-cifar100
18
 
19
+ This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
 
21
  - Accuracy: 0.9241
22
+ - Loss: 0.2955
23
 
24
  ## Model description
25
 
 
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
+ - learning_rate: 3e-05
42
  - train_batch_size: 8
43
  - eval_batch_size: 8
44
  - seed: 1337
 
48
 
49
  ### Training results
50
 
51
+ | Training Loss | Epoch | Step | Accuracy | Validation Loss |
52
+ |:-------------:|:-----:|:-----:|:--------:|:---------------:|
53
+ | 1.4469 | 1.0 | 5313 | 0.8716 | 1.1871 |
54
+ | 0.7861 | 2.0 | 10626 | 0.9056 | 0.4685 |
55
+ | 0.732 | 3.0 | 15939 | 0.9139 | 0.3551 |
56
+ | 0.3327 | 4.0 | 21252 | 0.9199 | 0.3090 |
57
+ | 0.4886 | 5.0 | 26565 | 0.9241 | 0.2955 |
58
 
59
 
60
  ### Framework versions
config.json CHANGED
@@ -222,7 +222,6 @@
222
  "num_channels": 3,
223
  "num_hidden_layers": 12,
224
  "patch_size": 16,
225
- "problem_type": "single_label_classification",
226
  "qkv_bias": true,
227
  "torch_dtype": "float32",
228
  "transformers_version": "4.44.2"
 
222
  "num_channels": 3,
223
  "num_hidden_layers": 12,
224
  "patch_size": 16,
 
225
  "qkv_bias": true,
226
  "torch_dtype": "float32",
227
  "transformers_version": "4.44.2"
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f546d7c168500d01876c6dc01808c6f5263ddae91b75572ea4fda1436a1527a2
3
  size 4795
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f2ebefcdbe23da3e8a07bd33f18d9c819628aad720be522b150e8dcf2962fbc
3
  size 4795