hbjoo commited on
Commit
ffbd69d
·
verified ·
1 Parent(s): 2006cac
README.md ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/vit-base-patch16-224-in21k
4
+ tags:
5
+ - image-classification
6
+ - ViT
7
+ - generated_from_trainer
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: vit-base-beans-demo-v5
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # vit-base-beans-demo-v5
19
+
20
+ 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 beans dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.2667
23
+ - Accuracy: 0.9453
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 0.0002
43
+ - train_batch_size: 16
44
+ - eval_batch_size: 8
45
+ - seed: 42
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - num_epochs: 4
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
+ |:-------------:|:------:|:----:|:---------------:|:--------:|
55
+ | 0.0045 | 1.5385 | 100 | 0.0047 | 1.0 |
56
+ | 0.0032 | 3.0769 | 200 | 0.0034 | 1.0 |
57
+
58
+
59
+ ### Framework versions
60
+
61
+ - Transformers 4.41.2
62
+ - Pytorch 2.3.0+cu121
63
+ - Datasets 2.20.0
64
+ - Tokenizers 0.19.1
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "eval_accuracy": 0.9453125,
4
+ "eval_loss": 0.26672494411468506,
5
+ "eval_runtime": 2.2262,
6
+ "eval_samples_per_second": 57.497,
7
+ "eval_steps_per_second": 7.187,
8
+ "total_flos": 3.205097416476426e+17,
9
+ "train_loss": 0.004694984795955511,
10
+ "train_runtime": 92.0924,
11
+ "train_samples_per_second": 44.911,
12
+ "train_steps_per_second": 2.823
13
+ }
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "angular_leaf_spot",
13
+ "1": "bean_rust",
14
+ "2": "healthy"
15
+ },
16
+ "image_size": 224,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "angular_leaf_spot": "0",
21
+ "bean_rust": "1",
22
+ "healthy": "2"
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "model_type": "vit",
26
+ "num_attention_heads": 12,
27
+ "num_channels": 3,
28
+ "num_hidden_layers": 12,
29
+ "patch_size": 16,
30
+ "problem_type": "single_label_classification",
31
+ "qkv_bias": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.41.2"
34
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03ee9dc13bbda66da69b8463cdb763750024fc97f1d9c9840d2d15ef3b75f6ef
3
+ size 343227052
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/Jul04_01-50-29_1c8bd75ea4e4/events.out.tfevents.1720059259.1c8bd75ea4e4.3722.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6da544cfe977965ed690090087ce932d4574fbd191e81c7829a05a72669a349e
3
+ size 11323
runs/Jul04_01-50-29_1c8bd75ea4e4/events.out.tfevents.1720059399.1c8bd75ea4e4.3722.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52f2acef5699b96ada3058db569998a35f325354fb44e546d66381173def6f0b
3
+ size 11417
runs/Jul04_01-50-29_1c8bd75ea4e4/events.out.tfevents.1720060008.1c8bd75ea4e4.3722.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcca699789c3a3c5b49780fec3612e5f2bf465db63de4c0293d5bb2e449b3974
3
+ size 734
test_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "eval_accuracy": 0.9453125,
4
+ "eval_loss": 0.26672494411468506,
5
+ "eval_runtime": 2.2262,
6
+ "eval_samples_per_second": 57.497,
7
+ "eval_steps_per_second": 7.187
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "total_flos": 3.205097416476426e+17,
4
+ "train_loss": 0.004694984795955511,
5
+ "train_runtime": 92.0924,
6
+ "train_samples_per_second": 44.911,
7
+ "train_steps_per_second": 2.823
8
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b79cf45f07c45dbab4ff18b48f57877275750a6ff301b5cfec97afd8f2c2ed31
3
+ size 5112