Asseh commited on
Commit
1a7ccdc
1 Parent(s): 51e4b86

End of training

Browse files
README.md ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: bhutanese-textile-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: 0.7208672086720868
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
+ # bhutanese-textile-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: 2.1699
36
+ - Accuracy: 0.7209
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: 5e-05
56
+ - train_batch_size: 16
57
+ - eval_batch_size: 16
58
+ - seed: 42
59
+ - gradient_accumulation_steps: 4
60
+ - total_train_batch_size: 64
61
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
+ - lr_scheduler_type: linear
63
+ - lr_scheduler_warmup_ratio: 0.1
64
+ - num_epochs: 3
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 2.6038 | 1.0 | 23 | 2.4811 | 0.5447 |
71
+ | 2.3394 | 2.0 | 46 | 2.2450 | 0.7100 |
72
+ | 2.1621 | 3.0 | 69 | 2.1699 | 0.7209 |
73
+
74
+
75
+ ### Framework versions
76
+
77
+ - Transformers 4.38.2
78
+ - Pytorch 2.2.1+cu121
79
+ - Datasets 2.18.0
80
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "american_football",
13
+ "1": "baseball",
14
+ "10": "rugby_ball",
15
+ "11": "shuttlecock",
16
+ "12": "table_tennis_ball",
17
+ "13": "tennis_ball",
18
+ "14": "volleyball",
19
+ "2": "basketball",
20
+ "3": "billiard_ball",
21
+ "4": "bowling_ball",
22
+ "5": "cricket_ball",
23
+ "6": "football",
24
+ "7": "golf_ball",
25
+ "8": "hockey_ball",
26
+ "9": "hockey_puck"
27
+ },
28
+ "image_size": 224,
29
+ "initializer_range": 0.02,
30
+ "intermediate_size": 3072,
31
+ "label2id": {
32
+ "american_football": "0",
33
+ "baseball": "1",
34
+ "basketball": "2",
35
+ "billiard_ball": "3",
36
+ "bowling_ball": "4",
37
+ "cricket_ball": "5",
38
+ "football": "6",
39
+ "golf_ball": "7",
40
+ "hockey_ball": "8",
41
+ "hockey_puck": "9",
42
+ "rugby_ball": "10",
43
+ "shuttlecock": "11",
44
+ "table_tennis_ball": "12",
45
+ "tennis_ball": "13",
46
+ "volleyball": "14"
47
+ },
48
+ "layer_norm_eps": 1e-12,
49
+ "model_type": "vit",
50
+ "num_attention_heads": 12,
51
+ "num_channels": 3,
52
+ "num_hidden_layers": 12,
53
+ "patch_size": 16,
54
+ "problem_type": "single_label_classification",
55
+ "qkv_bias": true,
56
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.38.2"
58
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aad65d68d3d242b5c0401f795b795c75ec5e840393a76bdb470004d62083f704
3
+ size 343263964
preprocessor_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "do_rescale": true,
4
+ "do_resize": true,
5
+ "image_mean": [
6
+ 0.5,
7
+ 0.5,
8
+ 0.5
9
+ ],
10
+ "image_processor_type": "ViTImageProcessor",
11
+ "image_std": [
12
+ 0.5,
13
+ 0.5,
14
+ 0.5
15
+ ],
16
+ "resample": 2,
17
+ "rescale_factor": 0.00392156862745098,
18
+ "size": {
19
+ "height": 224,
20
+ "width": 224
21
+ }
22
+ }
runs/Apr02_06-25-53_caff618d445e/events.out.tfevents.1712039154.caff618d445e.482.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:992f1a9cda0d3d53f2ed4352326a8938d41053c9e007bb830b0ac2ee9fcf557d
3
+ size 7787
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96a7e69353f30700cc1c8fe7bcc2300fd50cc0f3127291b462bb60dc7feb27b7
3
+ size 4920