Model save
Browse files- README.md +65 -0
- config.json +48 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- runs/Apr07_13-19-06_9b51f9451925/events.out.tfevents.1712495947.9b51f9451925.6697.0 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: WinKawaks/vit-small-patch16-224
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: vit-small-patch16-224-finetuned-cifar10
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# vit-small-patch16-224-finetuned-cifar10
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [WinKawaks/vit-small-patch16-224](https://huggingface.co/WinKawaks/vit-small-patch16-224) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.0427
|
21 |
+
- Accuracy: 0.9859
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 5e-05
|
41 |
+
- train_batch_size: 32
|
42 |
+
- eval_batch_size: 32
|
43 |
+
- seed: 42
|
44 |
+
- gradient_accumulation_steps: 4
|
45 |
+
- total_train_batch_size: 128
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: linear
|
48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
49 |
+
- num_epochs: 3
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
54 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
55 |
+
| 0.3038 | 1.0 | 273 | 0.0686 | 0.9786 |
|
56 |
+
| 0.3003 | 2.0 | 547 | 0.0474 | 0.9847 |
|
57 |
+
| 0.1961 | 2.99 | 819 | 0.0427 | 0.9859 |
|
58 |
+
|
59 |
+
|
60 |
+
### Framework versions
|
61 |
+
|
62 |
+
- Transformers 4.38.2
|
63 |
+
- Pytorch 2.2.1+cu121
|
64 |
+
- Datasets 2.18.0
|
65 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "WinKawaks/vit-small-patch16-224",
|
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": 384,
|
11 |
+
"id2label": {
|
12 |
+
"0": "airplane",
|
13 |
+
"1": "automobile",
|
14 |
+
"2": "bird",
|
15 |
+
"3": "cat",
|
16 |
+
"4": "deer",
|
17 |
+
"5": "dog",
|
18 |
+
"6": "frog",
|
19 |
+
"7": "horse",
|
20 |
+
"8": "ship",
|
21 |
+
"9": "truck"
|
22 |
+
},
|
23 |
+
"image_size": 224,
|
24 |
+
"initializer_range": 0.02,
|
25 |
+
"intermediate_size": 1536,
|
26 |
+
"label2id": {
|
27 |
+
"airplane": 0,
|
28 |
+
"automobile": 1,
|
29 |
+
"bird": 2,
|
30 |
+
"cat": 3,
|
31 |
+
"deer": 4,
|
32 |
+
"dog": 5,
|
33 |
+
"frog": 6,
|
34 |
+
"horse": 7,
|
35 |
+
"ship": 8,
|
36 |
+
"truck": 9
|
37 |
+
},
|
38 |
+
"layer_norm_eps": 1e-12,
|
39 |
+
"model_type": "vit",
|
40 |
+
"num_attention_heads": 6,
|
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": "4.38.2"
|
48 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10e87215cd770e14f18fbc636a334c30238bae51036ba78251bb3a162a6f9258
|
3 |
+
size 86700952
|
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/Apr07_13-19-06_9b51f9451925/events.out.tfevents.1712495947.9b51f9451925.6697.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f94a0bdd51f14fd2bc1af1e5dcb641a81847f812a556117d462e4d0bb5ed2fb4
|
3 |
+
size 23301
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45fb83ab6b062abe9c465dd5226f607b6c05e5179c7849234055211667519fd8
|
3 |
+
size 4920
|