Hugging Face's logo

bansilp
/
xyz

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
bansilp commited on
Commit
8729c37
•
1 Parent(s): f1bb2ae

Model save

Browse files
Files changed (6) hide show
  1. README.md +15 -15
  2. config.json +10 -8
  3. model.safetensors +2 -2
  4. runs/Dec27_05-35-49_1e3910c69210/events.out.tfevents.1703655359.1e3910c69210.475.0 +3 -0
  5. runs/Dec27_06-07-45_1e3910c69210/events.out.tfevents.1703657271.1e3910c69210.10071.0 +3 -0
  6. training_args.bin +1 -1
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: 0.9018518518518519
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: 0.4588
36
- - Accuracy: 0.9019
37
 
38
  ## Model description
39
 
@@ -58,27 +58,27 @@ The following hyperparameters were used during training:
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
- - num_epochs: 10
62
  - mixed_precision_training: Native AMP
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | 0.1739 | 1.11 | 100 | 0.5771 | 0.8407 |
69
- | 0.0677 | 2.22 | 200 | 0.5907 | 0.8519 |
70
- | 0.0699 | 3.33 | 300 | 0.4160 | 0.8870 |
71
- | 0.0598 | 4.44 | 400 | 0.7336 | 0.8380 |
72
- | 0.0108 | 5.56 | 500 | 0.5133 | 0.8898 |
73
- | 0.0082 | 6.67 | 600 | 0.4786 | 0.8981 |
74
- | 0.0031 | 7.78 | 700 | 0.4624 | 0.9009 |
75
- | 0.0046 | 8.89 | 800 | 0.4594 | 0.9 |
76
- | 0.0052 | 10.0 | 900 | 0.4588 | 0.9019 |
77
 
78
 
79
  ### Framework versions
80
 
81
  - Transformers 4.35.2
82
  - Pytorch 2.1.0+cu121
83
- - Datasets 2.15.0
84
  - Tokenizers 0.15.0
 
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: 0.565
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: 2.0792
36
+ - Accuracy: 0.565
37
 
38
  ## Model description
39
 
 
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
  - mixed_precision_training: Native AMP
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 0.8643 | 0.55 | 100 | 1.7445 | 0.45 |
69
+ | 0.3609 | 1.09 | 200 | 1.4977 | 0.565 |
70
+ | 0.2602 | 1.64 | 300 | 1.8113 | 0.525 |
71
+ | 0.1278 | 2.19 | 400 | 1.8174 | 0.53 |
72
+ | 0.051 | 2.73 | 500 | 1.9151 | 0.525 |
73
+ | 0.0619 | 3.28 | 600 | 2.0656 | 0.55 |
74
+ | 0.0263 | 3.83 | 700 | 2.1127 | 0.555 |
75
+ | 0.0104 | 4.37 | 800 | 2.1411 | 0.55 |
76
+ | 0.01 | 4.92 | 900 | 2.0792 | 0.565 |
77
 
78
 
79
  ### Framework versions
80
 
81
  - Transformers 4.35.2
82
  - Pytorch 2.1.0+cu121
83
+ - Datasets 2.16.0
84
  - Tokenizers 0.15.0
config.json CHANGED
@@ -14,10 +14,11 @@
14
  "2": "country",
15
  "3": "disco",
16
  "4": "hiphop",
17
- "5": "metal",
18
- "6": "pop",
19
- "7": "reggae",
20
- "8": "rock"
 
21
  },
22
  "image_size": 224,
23
  "initializer_range": 0.02,
@@ -28,10 +29,11 @@
28
  "country": "2",
29
  "disco": "3",
30
  "hiphop": "4",
31
- "metal": "5",
32
- "pop": "6",
33
- "reggae": "7",
34
- "rock": "8"
 
35
  },
36
  "layer_norm_eps": 1e-12,
37
  "model_type": "vit",
 
14
  "2": "country",
15
  "3": "disco",
16
  "4": "hiphop",
17
+ "5": "jazz",
18
+ "6": "metal",
19
+ "7": "pop",
20
+ "8": "reggae",
21
+ "9": "rock"
22
  },
23
  "image_size": 224,
24
  "initializer_range": 0.02,
 
29
  "country": "2",
30
  "disco": "3",
31
  "hiphop": "4",
32
+ "jazz": "5",
33
+ "metal": "6",
34
+ "pop": "7",
35
+ "reggae": "8",
36
+ "rock": "9"
37
  },
38
  "layer_norm_eps": 1e-12,
39
  "model_type": "vit",
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35885972c930164a157c2ac6031f4f0bbb728ae3cfb7310362498b088b84a04e
3
- size 343245508
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1a4c64815db0e92c56c2bb871dd2966520968f896d08461d93478f23c74077a
3
+ size 343248584
runs/Dec27_05-35-49_1e3910c69210/events.out.tfevents.1703655359.1e3910c69210.475.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27bf3f106b53752eb900420771e3e828432a44ad31756a16458d941cba3ba86f
3
+ size 23026
runs/Dec27_06-07-45_1e3910c69210/events.out.tfevents.1703657271.1e3910c69210.10071.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00cae1327496ef4abb049ab6f402d6e7adca2c14235cde1153b8e01d5663f053
3
+ size 21966
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2f84633d96f461c6cad6bc6d2052b12d6fc4b45d0640428f182e9d3e3a67b5f
3
  size 4536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8febe3690baf444e4b63fc6e4872faf9e5e7e7de793e544695e21eeb08116372
3
  size 4536