Augusto777
commited on
Commit
•
f252fd7
1
Parent(s):
0251ea2
Model save
Browse files
README.md
ADDED
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google/vit-base-patch16-224
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: vit-base-patch16-224-dmae-va-U5-42
|
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-base-patch16-224-dmae-va-U5-42
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.9012
|
21 |
+
- Accuracy: 0.7833
|
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: 42
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
54 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
55 |
+
| No log | 0.9 | 7 | 1.2858 | 0.5 |
|
56 |
+
| 1.3455 | 1.94 | 15 | 1.1091 | 0.4833 |
|
57 |
+
| 1.3455 | 2.97 | 23 | 0.8518 | 0.5833 |
|
58 |
+
| 1.0067 | 4.0 | 31 | 0.7317 | 0.7167 |
|
59 |
+
| 0.6085 | 4.9 | 38 | 0.6949 | 0.75 |
|
60 |
+
| 0.6085 | 5.94 | 46 | 0.6633 | 0.75 |
|
61 |
+
| 0.3389 | 6.97 | 54 | 0.6791 | 0.7667 |
|
62 |
+
| 0.1977 | 8.0 | 62 | 0.7010 | 0.7333 |
|
63 |
+
| 0.1977 | 8.9 | 69 | 0.6970 | 0.75 |
|
64 |
+
| 0.1496 | 9.94 | 77 | 0.6984 | 0.8 |
|
65 |
+
| 0.1194 | 10.97 | 85 | 0.9061 | 0.7333 |
|
66 |
+
| 0.1194 | 12.0 | 93 | 0.8720 | 0.75 |
|
67 |
+
| 0.109 | 12.9 | 100 | 0.8439 | 0.7833 |
|
68 |
+
| 0.0902 | 13.94 | 108 | 0.7345 | 0.8333 |
|
69 |
+
| 0.0902 | 14.97 | 116 | 0.8420 | 0.7833 |
|
70 |
+
| 0.0938 | 16.0 | 124 | 0.7994 | 0.75 |
|
71 |
+
| 0.0938 | 16.9 | 131 | 0.8341 | 0.8 |
|
72 |
+
| 0.0862 | 17.94 | 139 | 0.7239 | 0.8 |
|
73 |
+
| 0.0864 | 18.97 | 147 | 0.8485 | 0.7833 |
|
74 |
+
| 0.0864 | 20.0 | 155 | 0.8948 | 0.8 |
|
75 |
+
| 0.065 | 20.9 | 162 | 0.8681 | 0.8167 |
|
76 |
+
| 0.0793 | 21.94 | 170 | 0.8226 | 0.8167 |
|
77 |
+
| 0.0793 | 22.97 | 178 | 0.7495 | 0.8333 |
|
78 |
+
| 0.0629 | 24.0 | 186 | 0.8814 | 0.7667 |
|
79 |
+
| 0.0666 | 24.9 | 193 | 0.7739 | 0.8167 |
|
80 |
+
| 0.0666 | 25.94 | 201 | 0.9246 | 0.7833 |
|
81 |
+
| 0.0571 | 26.97 | 209 | 0.8077 | 0.8333 |
|
82 |
+
| 0.0519 | 28.0 | 217 | 0.8975 | 0.7833 |
|
83 |
+
| 0.0519 | 28.9 | 224 | 0.9199 | 0.7833 |
|
84 |
+
| 0.0523 | 29.94 | 232 | 0.8512 | 0.8 |
|
85 |
+
| 0.0548 | 30.97 | 240 | 0.9377 | 0.8167 |
|
86 |
+
| 0.0548 | 32.0 | 248 | 0.8213 | 0.8167 |
|
87 |
+
| 0.0576 | 32.9 | 255 | 0.8384 | 0.8167 |
|
88 |
+
| 0.0576 | 33.94 | 263 | 0.8664 | 0.8 |
|
89 |
+
| 0.0381 | 34.97 | 271 | 0.8818 | 0.8 |
|
90 |
+
| 0.0338 | 36.0 | 279 | 0.9106 | 0.7833 |
|
91 |
+
| 0.0338 | 36.9 | 286 | 0.9057 | 0.7833 |
|
92 |
+
| 0.0443 | 37.94 | 294 | 0.9012 | 0.7833 |
|
93 |
+
|
94 |
+
|
95 |
+
### Framework versions
|
96 |
+
|
97 |
+
- Transformers 4.38.2
|
98 |
+
- Pytorch 2.2.1+cu121
|
99 |
+
- Datasets 2.18.0
|
100 |
+
- Tokenizers 0.15.2
|
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 sha256:23de107aba85d9fd7ea09a0b71e5f667e43e0f111aef623211088a65b76e2d2b
|
3 |
size 343230128
|
runs/Apr02_01-48-53_6529928adb6f/events.out.tfevents.1712022566.6529928adb6f.1561.0
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 sha256:22ccc0a577d4ea3afcdadfec79341a072a0f006ef13086ac0104794b98297aba
|
3 |
+
size 22269
|