Commit
•
0a7f88f
1
Parent(s):
8e676a3
Model save
Browse files
README.md
ADDED
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-RU2-40
|
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: 0.7666666666666667
|
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-RU2-40
|
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: 1.2597
|
36 |
+
- Accuracy: 0.7667
|
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: 40
|
65 |
+
|
66 |
+
### Training results
|
67 |
+
|
68 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
69 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
70 |
+
| 1.3226 | 0.99 | 38 | 1.2293 | 0.6 |
|
71 |
+
| 0.9048 | 2.0 | 77 | 0.7969 | 0.7 |
|
72 |
+
| 0.4039 | 2.99 | 115 | 0.6800 | 0.7167 |
|
73 |
+
| 0.281 | 4.0 | 154 | 0.8892 | 0.7667 |
|
74 |
+
| 0.1755 | 4.99 | 192 | 0.9072 | 0.7333 |
|
75 |
+
| 0.1035 | 6.0 | 231 | 0.8036 | 0.8167 |
|
76 |
+
| 0.1275 | 6.99 | 269 | 0.8627 | 0.8 |
|
77 |
+
| 0.107 | 8.0 | 308 | 0.8713 | 0.8 |
|
78 |
+
| 0.0984 | 8.99 | 346 | 0.9660 | 0.8 |
|
79 |
+
| 0.0823 | 10.0 | 385 | 1.0704 | 0.7833 |
|
80 |
+
| 0.0771 | 10.99 | 423 | 0.9409 | 0.7667 |
|
81 |
+
| 0.0527 | 12.0 | 462 | 1.0052 | 0.7833 |
|
82 |
+
| 0.0708 | 12.99 | 500 | 0.9578 | 0.8 |
|
83 |
+
| 0.0562 | 14.0 | 539 | 1.0712 | 0.8167 |
|
84 |
+
| 0.0467 | 14.99 | 577 | 1.0586 | 0.8167 |
|
85 |
+
| 0.0445 | 16.0 | 616 | 1.2066 | 0.7667 |
|
86 |
+
| 0.0474 | 16.99 | 654 | 1.1863 | 0.75 |
|
87 |
+
| 0.0263 | 18.0 | 693 | 1.1207 | 0.8167 |
|
88 |
+
| 0.0307 | 18.99 | 731 | 1.1813 | 0.8167 |
|
89 |
+
| 0.0393 | 20.0 | 770 | 1.3761 | 0.75 |
|
90 |
+
| 0.0475 | 20.99 | 808 | 1.3008 | 0.7667 |
|
91 |
+
| 0.0215 | 22.0 | 847 | 1.2625 | 0.7333 |
|
92 |
+
| 0.0311 | 22.99 | 885 | 1.1508 | 0.8 |
|
93 |
+
| 0.027 | 24.0 | 924 | 1.3035 | 0.7667 |
|
94 |
+
| 0.0251 | 24.99 | 962 | 1.2270 | 0.7667 |
|
95 |
+
| 0.0161 | 26.0 | 1001 | 1.1470 | 0.8167 |
|
96 |
+
| 0.0258 | 26.99 | 1039 | 1.1473 | 0.8167 |
|
97 |
+
| 0.0142 | 28.0 | 1078 | 1.2326 | 0.7667 |
|
98 |
+
| 0.0151 | 28.99 | 1116 | 1.3978 | 0.7667 |
|
99 |
+
| 0.021 | 30.0 | 1155 | 1.2003 | 0.8333 |
|
100 |
+
| 0.0158 | 30.99 | 1193 | 1.2488 | 0.7667 |
|
101 |
+
| 0.0163 | 32.0 | 1232 | 1.3232 | 0.75 |
|
102 |
+
| 0.0143 | 32.99 | 1270 | 1.2467 | 0.8 |
|
103 |
+
| 0.02 | 34.0 | 1309 | 1.3176 | 0.7833 |
|
104 |
+
| 0.0128 | 34.99 | 1347 | 1.3083 | 0.7667 |
|
105 |
+
| 0.0144 | 36.0 | 1386 | 1.3080 | 0.7667 |
|
106 |
+
| 0.0109 | 36.99 | 1424 | 1.2999 | 0.8 |
|
107 |
+
| 0.0082 | 38.0 | 1463 | 1.2718 | 0.8 |
|
108 |
+
| 0.0064 | 38.99 | 1501 | 1.2588 | 0.7667 |
|
109 |
+
| 0.0097 | 39.48 | 1520 | 1.2597 | 0.7667 |
|
110 |
+
|
111 |
+
|
112 |
+
### Framework versions
|
113 |
+
|
114 |
+
- Transformers 4.36.2
|
115 |
+
- Pytorch 2.1.2+cu118
|
116 |
+
- Datasets 2.16.1
|
117 |
+
- 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 sha256:2e342cadcd7890758d41cb6b75366a2cca10fd1d5fecfe72c40a3285f82cf694
|
3 |
size 343230128
|
runs/May23_17-20-58_DESKTOP-SKBE9FB/events.out.tfevents.1716506460.DESKTOP-SKBE9FB.4988.0
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 sha256:650a1c52e3de7061747b668435ee9d1c84250ef0366e0f28230c21f10751e5cc
|
3 |
+
size 41573
|