Commit
•
ede1e04
1
Parent(s):
e178534
Model save
Browse files
README.md
ADDED
@@ -0,0 +1,151 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google/vit-base-patch16-224
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- imagefolder
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: vit-base-patch16-224-ve-U11-b-80
|
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: validation
|
21 |
+
args: default
|
22 |
+
metrics:
|
23 |
+
- name: Accuracy
|
24 |
+
type: accuracy
|
25 |
+
value: 0.8043478260869565
|
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 |
+
# vit-base-patch16-224-ve-U11-b-80
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.8161
|
36 |
+
- Accuracy: 0.8043
|
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: 5.5e-05
|
56 |
+
- train_batch_size: 32
|
57 |
+
- eval_batch_size: 32
|
58 |
+
- seed: 42
|
59 |
+
- gradient_accumulation_steps: 4
|
60 |
+
- total_train_batch_size: 128
|
61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
+
- lr_scheduler_type: linear
|
63 |
+
- lr_scheduler_warmup_ratio: 0.05
|
64 |
+
- num_epochs: 80
|
65 |
+
|
66 |
+
### Training results
|
67 |
+
|
68 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
69 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
70 |
+
| No log | 0.92 | 6 | 1.3848 | 0.3696 |
|
71 |
+
| 1.3848 | 2.0 | 13 | 1.3692 | 0.5217 |
|
72 |
+
| 1.3848 | 2.92 | 19 | 1.3197 | 0.5435 |
|
73 |
+
| 1.3517 | 4.0 | 26 | 1.2264 | 0.5 |
|
74 |
+
| 1.2334 | 4.92 | 32 | 1.1280 | 0.4348 |
|
75 |
+
| 1.2334 | 6.0 | 39 | 1.0437 | 0.5435 |
|
76 |
+
| 1.073 | 6.92 | 45 | 0.9771 | 0.5870 |
|
77 |
+
| 0.9358 | 8.0 | 52 | 0.9470 | 0.6739 |
|
78 |
+
| 0.9358 | 8.92 | 58 | 0.8528 | 0.7826 |
|
79 |
+
| 0.7955 | 10.0 | 65 | 0.7839 | 0.7609 |
|
80 |
+
| 0.6429 | 10.92 | 71 | 0.7620 | 0.7391 |
|
81 |
+
| 0.6429 | 12.0 | 78 | 0.6466 | 0.8043 |
|
82 |
+
| 0.5096 | 12.92 | 84 | 0.7396 | 0.7174 |
|
83 |
+
| 0.4086 | 14.0 | 91 | 0.7335 | 0.7174 |
|
84 |
+
| 0.4086 | 14.92 | 97 | 0.6473 | 0.7391 |
|
85 |
+
| 0.3355 | 16.0 | 104 | 0.6019 | 0.7391 |
|
86 |
+
| 0.2511 | 16.92 | 110 | 0.5275 | 0.8261 |
|
87 |
+
| 0.2511 | 18.0 | 117 | 0.6069 | 0.7826 |
|
88 |
+
| 0.1925 | 18.92 | 123 | 0.6447 | 0.7826 |
|
89 |
+
| 0.2121 | 20.0 | 130 | 0.5044 | 0.8261 |
|
90 |
+
| 0.2121 | 20.92 | 136 | 0.4805 | 0.8478 |
|
91 |
+
| 0.1883 | 22.0 | 143 | 0.6723 | 0.8043 |
|
92 |
+
| 0.1883 | 22.92 | 149 | 0.7730 | 0.7391 |
|
93 |
+
| 0.1693 | 24.0 | 156 | 0.6574 | 0.7609 |
|
94 |
+
| 0.1252 | 24.92 | 162 | 0.8192 | 0.7391 |
|
95 |
+
| 0.1252 | 26.0 | 169 | 0.5984 | 0.7826 |
|
96 |
+
| 0.1439 | 26.92 | 175 | 0.7633 | 0.7826 |
|
97 |
+
| 0.137 | 28.0 | 182 | 0.6566 | 0.8478 |
|
98 |
+
| 0.137 | 28.92 | 188 | 0.6550 | 0.8261 |
|
99 |
+
| 0.1316 | 30.0 | 195 | 0.7163 | 0.7391 |
|
100 |
+
| 0.1101 | 30.92 | 201 | 0.6241 | 0.7826 |
|
101 |
+
| 0.1101 | 32.0 | 208 | 0.6360 | 0.8478 |
|
102 |
+
| 0.0947 | 32.92 | 214 | 0.5273 | 0.8696 |
|
103 |
+
| 0.0885 | 34.0 | 221 | 0.6579 | 0.8261 |
|
104 |
+
| 0.0885 | 34.92 | 227 | 0.5920 | 0.8696 |
|
105 |
+
| 0.0967 | 36.0 | 234 | 0.6779 | 0.8261 |
|
106 |
+
| 0.0812 | 36.92 | 240 | 0.7354 | 0.8043 |
|
107 |
+
| 0.0812 | 38.0 | 247 | 0.6825 | 0.8261 |
|
108 |
+
| 0.0752 | 38.92 | 253 | 0.6348 | 0.8478 |
|
109 |
+
| 0.0757 | 40.0 | 260 | 0.7726 | 0.8043 |
|
110 |
+
| 0.0757 | 40.92 | 266 | 0.6737 | 0.8261 |
|
111 |
+
| 0.086 | 42.0 | 273 | 0.6738 | 0.7826 |
|
112 |
+
| 0.086 | 42.92 | 279 | 0.7295 | 0.7609 |
|
113 |
+
| 0.0533 | 44.0 | 286 | 0.6897 | 0.8261 |
|
114 |
+
| 0.0574 | 44.92 | 292 | 0.6427 | 0.8261 |
|
115 |
+
| 0.0574 | 46.0 | 299 | 0.6471 | 0.8261 |
|
116 |
+
| 0.0739 | 46.92 | 305 | 0.6645 | 0.8261 |
|
117 |
+
| 0.0849 | 48.0 | 312 | 0.6858 | 0.8043 |
|
118 |
+
| 0.0849 | 48.92 | 318 | 0.7475 | 0.8043 |
|
119 |
+
| 0.0719 | 50.0 | 325 | 0.6735 | 0.8261 |
|
120 |
+
| 0.0434 | 50.92 | 331 | 0.6892 | 0.8478 |
|
121 |
+
| 0.0434 | 52.0 | 338 | 0.6820 | 0.8478 |
|
122 |
+
| 0.0564 | 52.92 | 344 | 0.6677 | 0.8478 |
|
123 |
+
| 0.0408 | 54.0 | 351 | 0.7379 | 0.8043 |
|
124 |
+
| 0.0408 | 54.92 | 357 | 0.5456 | 0.8913 |
|
125 |
+
| 0.0464 | 56.0 | 364 | 0.7951 | 0.7826 |
|
126 |
+
| 0.0463 | 56.92 | 370 | 0.6356 | 0.8478 |
|
127 |
+
| 0.0463 | 58.0 | 377 | 0.7529 | 0.8261 |
|
128 |
+
| 0.0361 | 58.92 | 383 | 0.8017 | 0.8261 |
|
129 |
+
| 0.0457 | 60.0 | 390 | 0.7877 | 0.8478 |
|
130 |
+
| 0.0457 | 60.92 | 396 | 0.8019 | 0.7826 |
|
131 |
+
| 0.0371 | 62.0 | 403 | 0.8015 | 0.8043 |
|
132 |
+
| 0.0371 | 62.92 | 409 | 0.8487 | 0.8043 |
|
133 |
+
| 0.0452 | 64.0 | 416 | 0.9401 | 0.7609 |
|
134 |
+
| 0.0455 | 64.92 | 422 | 0.9647 | 0.7609 |
|
135 |
+
| 0.0455 | 66.0 | 429 | 0.8958 | 0.7609 |
|
136 |
+
| 0.0408 | 66.92 | 435 | 0.8531 | 0.7826 |
|
137 |
+
| 0.0418 | 68.0 | 442 | 0.8206 | 0.8043 |
|
138 |
+
| 0.0418 | 68.92 | 448 | 0.8045 | 0.8043 |
|
139 |
+
| 0.0424 | 70.0 | 455 | 0.8090 | 0.8043 |
|
140 |
+
| 0.038 | 70.92 | 461 | 0.7902 | 0.8043 |
|
141 |
+
| 0.038 | 72.0 | 468 | 0.8008 | 0.8261 |
|
142 |
+
| 0.0401 | 72.92 | 474 | 0.8122 | 0.8043 |
|
143 |
+
| 0.0347 | 73.85 | 480 | 0.8161 | 0.8043 |
|
144 |
+
|
145 |
+
|
146 |
+
### Framework versions
|
147 |
+
|
148 |
+
- Transformers 4.36.2
|
149 |
+
- Pytorch 2.1.2+cu118
|
150 |
+
- Datasets 2.16.1
|
151 |
+
- Tokenizers 0.15.0
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 343230128
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3bd01ab15444c625487895a50d332696f665339c30894df40fd622ef9ee6ae7d
|
3 |
size 343230128
|
runs/Jun11_20-47-43_DESKTOP-SKBE9FB/events.out.tfevents.1718160464.DESKTOP-SKBE9FB.5392.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f941e32c4c73aaaa4d62dc4ee4341979cd436d9a7de1d3579b3629317d3b891
|
3 |
+
size 36146
|