Raihan004 commited on
Commit
da590d4
1 Parent(s): a1fb8a3

Model save

Browse files
README.md ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/vit-base-patch16-224-in21k
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: Action_model
12
+ results:
13
+ - task:
14
+ name: Image Classification
15
+ type: image-classification
16
+ dataset:
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: 0.78
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # Action_model
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: 0.9408
36
+ - Accuracy: 0.78
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
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
+ | 1.1382 | 0.32 | 100 | 1.0002 | 0.7676 |
69
+ | 0.782 | 0.64 | 200 | 0.7673 | 0.7676 |
70
+ | 0.6289 | 0.96 | 300 | 0.7073 | 0.7867 |
71
+ | 0.5028 | 1.27 | 400 | 0.7261 | 0.7686 |
72
+ | 0.4746 | 1.59 | 500 | 0.7464 | 0.7619 |
73
+ | 0.4298 | 1.91 | 600 | 0.6551 | 0.7990 |
74
+ | 0.3488 | 2.23 | 700 | 0.7359 | 0.7733 |
75
+ | 0.266 | 2.55 | 800 | 0.8296 | 0.7514 |
76
+ | 0.3651 | 2.87 | 900 | 0.8661 | 0.7305 |
77
+ | 0.2796 | 3.18 | 1000 | 0.7188 | 0.7867 |
78
+ | 0.2703 | 3.5 | 1100 | 0.8422 | 0.7476 |
79
+ | 0.2608 | 3.82 | 1200 | 0.8207 | 0.7724 |
80
+ | 0.251 | 4.14 | 1300 | 1.0252 | 0.7267 |
81
+ | 0.2085 | 4.46 | 1400 | 1.0475 | 0.7171 |
82
+ | 0.1715 | 4.78 | 1500 | 0.8852 | 0.7495 |
83
+ | 0.2051 | 5.1 | 1600 | 0.8164 | 0.7790 |
84
+ | 0.1481 | 5.41 | 1700 | 0.8825 | 0.7629 |
85
+ | 0.177 | 5.73 | 1800 | 0.8623 | 0.7867 |
86
+ | 0.1607 | 6.05 | 1900 | 0.9487 | 0.7610 |
87
+ | 0.1273 | 6.37 | 2000 | 0.8985 | 0.7733 |
88
+ | 0.1609 | 6.69 | 2100 | 0.9624 | 0.7505 |
89
+ | 0.1583 | 7.01 | 2200 | 0.9015 | 0.7781 |
90
+ | 0.1178 | 7.32 | 2300 | 0.9143 | 0.7762 |
91
+ | 0.1175 | 7.64 | 2400 | 0.9671 | 0.7590 |
92
+ | 0.1257 | 7.96 | 2500 | 0.8925 | 0.7838 |
93
+ | 0.0939 | 8.28 | 2600 | 0.9257 | 0.7705 |
94
+ | 0.1238 | 8.6 | 2700 | 0.9797 | 0.7648 |
95
+ | 0.1219 | 8.92 | 2800 | 0.9399 | 0.7724 |
96
+ | 0.0985 | 9.24 | 2900 | 0.9940 | 0.7648 |
97
+ | 0.1069 | 9.55 | 3000 | 0.9392 | 0.7743 |
98
+ | 0.0589 | 9.87 | 3100 | 0.9408 | 0.78 |
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
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/vit-base-patch16-224-in21k",
3
+ "architectures": [
4
+ "ViTForImageClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "encoder_stride": 16,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.0,
10
+ "hidden_size": 768,
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"
22
+ },
23
+ "image_size": 224,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 3072,
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"
37
+ },
38
+ "layer_norm_eps": 1e-12,
39
+ "model_type": "vit",
40
+ "num_attention_heads": 12,
41
+ "num_channels": 3,
42
+ "num_hidden_layers": 12,
43
+ "patch_size": 16,
44
+ "problem_type": "single_label_classification",
45
+ "qkv_bias": true,
46
+ "torch_dtype": "float32",
47
+ "transformers_version": "4.39.3"
48
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ff997581ddd6642e58b1bb4fe1550a4aea0cc57679090651e721750b79b12b0
3
+ size 343248584
preprocessor_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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,
34
+ "width": 224
35
+ }
36
+ }
runs/Apr15_19-54-29_beac81f7e97f/events.out.tfevents.1713210973.beac81f7e97f.34.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd7438baee405769b0c742d9a5b723ddc8ebdd18d7bcbdf38f27c74d46285eb8
3
+ size 49066
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8894c7e4e95f3786de873c5a43602402b76fd332eea765b39d0b3d59a27cf039
3
+ size 4920