Hugging Face's logo

Raihan004
/
Action_model

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Raihan004 commited on
Commit
ab61030
•
1 Parent(s): e5dbacd

Model save

Browse files
Files changed (6) hide show
  1. README.md +38 -38
  2. config.json +9 -9
  3. model.safetensors +1 -1
  4. preprocessor_config.json +8 -21
  5. runs/Apr18_08-26-03_0516a0f7e8d9/events.out.tfevents.1713428782.0516a0f7e8d9.4214.0 +3 -0
  6. training_args.bin +2 -2
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.7876190476190477
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: 0.9250
36
- - Accuracy: 0.7876
37
 
38
  ## Model description
39
 
@@ -53,54 +53,54 @@ More information needed
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 0.0001
56
- - train_batch_size: 32
57
  - eval_batch_size: 8
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
- | 1.1285 | 0.32 | 100 | 1.0131 | 0.7743 |
69
- | 0.7868 | 0.64 | 200 | 0.7684 | 0.7867 |
70
- | 0.6015 | 0.96 | 300 | 0.7090 | 0.7714 |
71
- | 0.5209 | 1.27 | 400 | 0.7650 | 0.7571 |
72
- | 0.4536 | 1.59 | 500 | 0.7826 | 0.7419 |
73
- | 0.4069 | 1.91 | 600 | 0.6878 | 0.7876 |
74
- | 0.3244 | 2.23 | 700 | 0.9184 | 0.7238 |
75
- | 0.2618 | 2.55 | 800 | 0.8178 | 0.7552 |
76
- | 0.342 | 2.87 | 900 | 0.8192 | 0.7648 |
77
- | 0.2778 | 3.18 | 1000 | 0.7542 | 0.7848 |
78
- | 0.2331 | 3.5 | 1100 | 0.8133 | 0.7695 |
79
- | 0.2426 | 3.82 | 1200 | 0.9022 | 0.7476 |
80
- | 0.2363 | 4.14 | 1300 | 0.9009 | 0.7619 |
81
- | 0.2143 | 4.46 | 1400 | 0.8545 | 0.7790 |
82
- | 0.1624 | 4.78 | 1500 | 0.9543 | 0.7533 |
83
- | 0.2302 | 5.1 | 1600 | 0.8138 | 0.78 |
84
- | 0.1682 | 5.41 | 1700 | 0.8490 | 0.7790 |
85
- | 0.1674 | 5.73 | 1800 | 0.9097 | 0.7724 |
86
- | 0.1595 | 6.05 | 1900 | 1.0542 | 0.7486 |
87
- | 0.1335 | 6.37 | 2000 | 0.8957 | 0.7876 |
88
- | 0.1696 | 6.69 | 2100 | 0.8860 | 0.7781 |
89
- | 0.148 | 7.01 | 2200 | 0.9529 | 0.7733 |
90
- | 0.1281 | 7.32 | 2300 | 0.9364 | 0.7848 |
91
- | 0.1274 | 7.64 | 2400 | 0.9252 | 0.7676 |
92
- | 0.1585 | 7.96 | 2500 | 0.9068 | 0.7914 |
93
- | 0.0985 | 8.28 | 2600 | 0.9400 | 0.7829 |
94
- | 0.1211 | 8.6 | 2700 | 0.9464 | 0.7790 |
95
- | 0.1459 | 8.92 | 2800 | 0.9800 | 0.7695 |
96
- | 0.1221 | 9.24 | 2900 | 0.9457 | 0.78 |
97
- | 0.1072 | 9.55 | 3000 | 0.9209 | 0.7857 |
98
- | 0.0607 | 9.87 | 3100 | 0.9250 | 0.7876 |
99
 
100
 
101
  ### Framework versions
102
 
103
- - Transformers 4.39.3
104
- - Pytorch 2.1.2
105
  - Datasets 2.18.0
106
  - Tokenizers 0.15.2
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.7495238095238095
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: 0.9816
36
+ - Accuracy: 0.7495
37
 
38
  ## Model description
39
 
 
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 0.0001
56
+ - train_batch_size: 16
57
  - eval_batch_size: 8
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
+ | 1.4818 | 0.16 | 100 | 1.2573 | 0.7219 |
69
+ | 1.0598 | 0.32 | 200 | 0.9673 | 0.7419 |
70
+ | 0.9126 | 0.48 | 300 | 0.8612 | 0.7514 |
71
+ | 0.6733 | 0.64 | 400 | 0.9162 | 0.7038 |
72
+ | 0.7302 | 0.8 | 500 | 0.9483 | 0.7124 |
73
+ | 0.7024 | 0.96 | 600 | 0.7318 | 0.7752 |
74
+ | 0.5469 | 1.11 | 700 | 1.0155 | 0.6990 |
75
+ | 0.4757 | 1.27 | 800 | 0.8299 | 0.7438 |
76
+ | 0.4618 | 1.43 | 900 | 0.7697 | 0.7648 |
77
+ | 0.5045 | 1.59 | 1000 | 0.9454 | 0.7152 |
78
+ | 0.4229 | 1.75 | 1100 | 0.7776 | 0.7629 |
79
+ | 0.3894 | 1.91 | 1200 | 0.8798 | 0.7495 |
80
+ | 0.3432 | 2.07 | 1300 | 0.8088 | 0.7590 |
81
+ | 0.3212 | 2.23 | 1400 | 0.7810 | 0.7733 |
82
+ | 0.3043 | 2.39 | 1500 | 1.0076 | 0.7295 |
83
+ | 0.255 | 2.55 | 1600 | 0.8672 | 0.7590 |
84
+ | 0.2834 | 2.71 | 1700 | 0.9165 | 0.7438 |
85
+ | 0.341 | 2.87 | 1800 | 0.7474 | 0.7838 |
86
+ | 0.1858 | 3.03 | 1900 | 1.0221 | 0.7229 |
87
+ | 0.2463 | 3.18 | 2000 | 0.8464 | 0.7829 |
88
+ | 0.2661 | 3.34 | 2100 | 0.9434 | 0.7476 |
89
+ | 0.2367 | 3.5 | 2200 | 0.9285 | 0.76 |
90
+ | 0.2299 | 3.66 | 2300 | 0.9777 | 0.7486 |
91
+ | 0.221 | 3.82 | 2400 | 0.9455 | 0.7533 |
92
+ | 0.2799 | 3.98 | 2500 | 1.0371 | 0.74 |
93
+ | 0.1185 | 4.14 | 2600 | 1.0378 | 0.7390 |
94
+ | 0.1405 | 4.3 | 2700 | 1.0870 | 0.7352 |
95
+ | 0.263 | 4.46 | 2800 | 1.1081 | 0.7276 |
96
+ | 0.254 | 4.62 | 2900 | 1.0279 | 0.7381 |
97
+ | 0.158 | 4.78 | 3000 | 0.9646 | 0.7514 |
98
+ | 0.1496 | 4.94 | 3100 | 0.9816 | 0.7495 |
99
 
100
 
101
  ### Framework versions
102
 
103
+ - Transformers 4.38.2
104
+ - Pytorch 2.2.1+cu121
105
  - Datasets 2.18.0
106
  - Tokenizers 0.15.2
config.json CHANGED
@@ -11,11 +11,11 @@
11
  "id2label": {
12
  "0": "\u0995\u09a5\u09be_\u09ac\u09b2\u09be",
13
  "1": "\u0995\u09ae\u09cd\u09aa\u09bf\u0989\u099f\u09be\u09b0_\u09ac\u09cd\u09af\u09ac\u09b9\u09be\u09b0_\u0995\u09b0\u09be",
14
- "2": "\u0996\u09be\u0993\u09df\u09be",
15
  "3": "\u0996\u09c7\u09b2\u09be_\u0995\u09b0\u09be",
16
- "4": "\u0998\u09c1\u09ae\u09be\u09a8\u09cb",
17
- "5": "\u09aa\u09be\u09a8_\u0995\u09b0\u09be",
18
- "6": "\u09aa\u09dc\u09be",
19
  "7": "\u09b0\u09be\u09a8\u09cd\u09a8\u09be_\u0995\u09b0\u09be",
20
  "8": "\u09b2\u09c7\u0996\u09be",
21
  "9": "\u09b9\u09be\u0981\u099f\u09be"
@@ -26,11 +26,11 @@
26
  "label2id": {
27
  "\u0995\u09a5\u09be_\u09ac\u09b2\u09be": "0",
28
  "\u0995\u09ae\u09cd\u09aa\u09bf\u0989\u099f\u09be\u09b0_\u09ac\u09cd\u09af\u09ac\u09b9\u09be\u09b0_\u0995\u09b0\u09be": "1",
29
- "\u0996\u09be\u0993\u09df\u09be": "2",
30
  "\u0996\u09c7\u09b2\u09be_\u0995\u09b0\u09be": "3",
31
- "\u0998\u09c1\u09ae\u09be\u09a8\u09cb": "4",
32
- "\u09aa\u09be\u09a8_\u0995\u09b0\u09be": "5",
33
- "\u09aa\u09dc\u09be": "6",
34
  "\u09b0\u09be\u09a8\u09cd\u09a8\u09be_\u0995\u09b0\u09be": "7",
35
  "\u09b2\u09c7\u0996\u09be": "8",
36
  "\u09b9\u09be\u0981\u099f\u09be": "9"
@@ -44,5 +44,5 @@
44
  "problem_type": "single_label_classification",
45
  "qkv_bias": true,
46
  "torch_dtype": "float32",
47
- "transformers_version": "4.39.3"
48
  }
 
11
  "id2label": {
12
  "0": "\u0995\u09a5\u09be_\u09ac\u09b2\u09be",
13
  "1": "\u0995\u09ae\u09cd\u09aa\u09bf\u0989\u099f\u09be\u09b0_\u09ac\u09cd\u09af\u09ac\u09b9\u09be\u09b0_\u0995\u09b0\u09be",
14
+ "2": "\u0996\u09be\u0993\u09af\u09bc\u09be",
15
  "3": "\u0996\u09c7\u09b2\u09be_\u0995\u09b0\u09be",
16
+ "4": "\u0998\u09c1\u09ae\u09be\u09a8\u09c7\u09be",
17
+ "5": "\u09aa\u09a1\u09bc\u09be",
18
+ "6": "\u09aa\u09be\u09a8_\u0995\u09b0\u09be",
19
  "7": "\u09b0\u09be\u09a8\u09cd\u09a8\u09be_\u0995\u09b0\u09be",
20
  "8": "\u09b2\u09c7\u0996\u09be",
21
  "9": "\u09b9\u09be\u0981\u099f\u09be"
 
26
  "label2id": {
27
  "\u0995\u09a5\u09be_\u09ac\u09b2\u09be": "0",
28
  "\u0995\u09ae\u09cd\u09aa\u09bf\u0989\u099f\u09be\u09b0_\u09ac\u09cd\u09af\u09ac\u09b9\u09be\u09b0_\u0995\u09b0\u09be": "1",
29
+ "\u0996\u09be\u0993\u09af\u09bc\u09be": "2",
30
  "\u0996\u09c7\u09b2\u09be_\u0995\u09b0\u09be": "3",
31
+ "\u0998\u09c1\u09ae\u09be\u09a8\u09c7\u09be": "4",
32
+ "\u09aa\u09a1\u09bc\u09be": "5",
33
+ "\u09aa\u09be\u09a8_\u0995\u09b0\u09be": "6",
34
  "\u09b0\u09be\u09a8\u09cd\u09a8\u09be_\u0995\u09b0\u09be": "7",
35
  "\u09b2\u09c7\u0996\u09be": "8",
36
  "\u09b9\u09be\u0981\u099f\u09be": "9"
 
44
  "problem_type": "single_label_classification",
45
  "qkv_bias": true,
46
  "torch_dtype": "float32",
47
+ "transformers_version": "4.38.2"
48
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:153f18d25d7912510cefd2640e92b08d86143be3b6d13c82547b96b75caf0bda
3
  size 343248584
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0681eeb853514c6fc22e890c28568b80d1638a955ba6e64e20e0e40effef8bad
3
  size 343248584
preprocessor_config.json CHANGED
@@ -1,33 +1,20 @@
1
  {
2
- "_valid_processor_keys": [
3
- "images",
4
- "do_resize",
5
- "size",
6
- "resample",
7
- "do_rescale",
8
- "rescale_factor",
9
- "do_normalize",
10
- "image_mean",
11
- "image_std",
12
- "return_tensors",
13
- "data_format",
14
- "input_data_format"
15
- ],
16
  "do_normalize": true,
17
  "do_rescale": true,
18
  "do_resize": true,
19
  "image_mean": [
20
- 0.5,
21
- 0.5,
22
- 0.5
23
  ],
24
  "image_processor_type": "ViTFeatureExtractor",
25
  "image_std": [
26
- 0.5,
27
- 0.5,
28
- 0.5
29
  ],
30
- "resample": 2,
31
  "rescale_factor": 0.00392156862745098,
32
  "size": {
33
  "height": 224,
 
1
  {
2
+ "crop_pct": 0.875,
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "do_normalize": true,
4
  "do_rescale": true,
5
  "do_resize": true,
6
  "image_mean": [
7
+ 0.485,
8
+ 0.456,
9
+ 0.406
10
  ],
11
  "image_processor_type": "ViTFeatureExtractor",
12
  "image_std": [
13
+ 0.229,
14
+ 0.224,
15
+ 0.225
16
  ],
17
+ "resample": 3,
18
  "rescale_factor": 0.00392156862745098,
19
  "size": {
20
  "height": 224,
runs/Apr18_08-26-03_0516a0f7e8d9/events.out.tfevents.1713428782.0516a0f7e8d9.4214.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26c8c11fbad94f9091735eed1ae091ba4230f3ee459f4d936812d8353ac43403
3
+ size 49069
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec1f6259cf9da5fa2c57800562b7b68eb62e99117b398b55b9727ca2ac9a9e45
3
- size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:925d834b296b8710f6b33928fcef2163fe7700059c92b91e34f893b610b60c59
3
+ size 4856