Commit
•
e029920
1
Parent(s):
c6396f9
End of training
Browse files- README.md +125 -0
- model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: microsoft/beit-base-patch16-224
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- imagefolder
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: hushem_5x_beit_base_sgd_001_fold4
|
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: test
|
21 |
+
args: default
|
22 |
+
metrics:
|
23 |
+
- name: Accuracy
|
24 |
+
type: accuracy
|
25 |
+
value: 0.7142857142857143
|
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 |
+
# hushem_5x_beit_base_sgd_001_fold4
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [microsoft/beit-base-patch16-224](https://huggingface.co/microsoft/beit-base-patch16-224) on the imagefolder dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.9066
|
36 |
+
- Accuracy: 0.7143
|
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: 0.001
|
56 |
+
- train_batch_size: 32
|
57 |
+
- eval_batch_size: 32
|
58 |
+
- seed: 42
|
59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
+
- lr_scheduler_type: linear
|
61 |
+
- lr_scheduler_warmup_ratio: 0.1
|
62 |
+
- num_epochs: 50
|
63 |
+
|
64 |
+
### Training results
|
65 |
+
|
66 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
67 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
68 |
+
| 1.529 | 1.0 | 28 | 1.4303 | 0.2857 |
|
69 |
+
| 1.4725 | 2.0 | 56 | 1.3788 | 0.2857 |
|
70 |
+
| 1.3888 | 3.0 | 84 | 1.3402 | 0.3571 |
|
71 |
+
| 1.357 | 4.0 | 112 | 1.3238 | 0.3333 |
|
72 |
+
| 1.2619 | 5.0 | 140 | 1.3109 | 0.3571 |
|
73 |
+
| 1.2354 | 6.0 | 168 | 1.2864 | 0.4286 |
|
74 |
+
| 1.2209 | 7.0 | 196 | 1.2694 | 0.4524 |
|
75 |
+
| 1.2033 | 8.0 | 224 | 1.2439 | 0.4524 |
|
76 |
+
| 1.1737 | 9.0 | 252 | 1.2291 | 0.4762 |
|
77 |
+
| 1.1593 | 10.0 | 280 | 1.2131 | 0.4762 |
|
78 |
+
| 1.1467 | 11.0 | 308 | 1.1977 | 0.4762 |
|
79 |
+
| 1.1374 | 12.0 | 336 | 1.1819 | 0.5 |
|
80 |
+
| 1.1253 | 13.0 | 364 | 1.1622 | 0.4762 |
|
81 |
+
| 1.1026 | 14.0 | 392 | 1.1551 | 0.4762 |
|
82 |
+
| 1.0893 | 15.0 | 420 | 1.1365 | 0.4762 |
|
83 |
+
| 1.0476 | 16.0 | 448 | 1.1177 | 0.4762 |
|
84 |
+
| 1.0789 | 17.0 | 476 | 1.1065 | 0.4762 |
|
85 |
+
| 1.0455 | 18.0 | 504 | 1.0907 | 0.4762 |
|
86 |
+
| 1.0028 | 19.0 | 532 | 1.0816 | 0.4762 |
|
87 |
+
| 1.004 | 20.0 | 560 | 1.0638 | 0.4762 |
|
88 |
+
| 0.967 | 21.0 | 588 | 1.0579 | 0.5 |
|
89 |
+
| 0.9933 | 22.0 | 616 | 1.0403 | 0.5 |
|
90 |
+
| 0.9551 | 23.0 | 644 | 1.0323 | 0.5714 |
|
91 |
+
| 0.9924 | 24.0 | 672 | 1.0183 | 0.5952 |
|
92 |
+
| 0.9236 | 25.0 | 700 | 1.0095 | 0.6190 |
|
93 |
+
| 0.9232 | 26.0 | 728 | 0.9951 | 0.6190 |
|
94 |
+
| 0.9574 | 27.0 | 756 | 1.0017 | 0.6190 |
|
95 |
+
| 0.9076 | 28.0 | 784 | 0.9866 | 0.6429 |
|
96 |
+
| 0.9034 | 29.0 | 812 | 0.9711 | 0.6429 |
|
97 |
+
| 0.8865 | 30.0 | 840 | 0.9696 | 0.6667 |
|
98 |
+
| 0.9168 | 31.0 | 868 | 0.9618 | 0.6667 |
|
99 |
+
| 0.8917 | 32.0 | 896 | 0.9532 | 0.6905 |
|
100 |
+
| 0.901 | 33.0 | 924 | 0.9560 | 0.6667 |
|
101 |
+
| 0.8911 | 34.0 | 952 | 0.9475 | 0.6667 |
|
102 |
+
| 0.9166 | 35.0 | 980 | 0.9435 | 0.7143 |
|
103 |
+
| 0.9177 | 36.0 | 1008 | 0.9323 | 0.7143 |
|
104 |
+
| 0.8498 | 37.0 | 1036 | 0.9279 | 0.7143 |
|
105 |
+
| 0.8848 | 38.0 | 1064 | 0.9240 | 0.7143 |
|
106 |
+
| 0.8498 | 39.0 | 1092 | 0.9206 | 0.7143 |
|
107 |
+
| 0.8193 | 40.0 | 1120 | 0.9192 | 0.7143 |
|
108 |
+
| 0.8443 | 41.0 | 1148 | 0.9102 | 0.7143 |
|
109 |
+
| 0.8576 | 42.0 | 1176 | 0.9108 | 0.7143 |
|
110 |
+
| 0.8916 | 43.0 | 1204 | 0.9094 | 0.7143 |
|
111 |
+
| 0.8299 | 44.0 | 1232 | 0.9082 | 0.7143 |
|
112 |
+
| 0.8298 | 45.0 | 1260 | 0.9062 | 0.7143 |
|
113 |
+
| 0.8683 | 46.0 | 1288 | 0.9063 | 0.7143 |
|
114 |
+
| 0.8298 | 47.0 | 1316 | 0.9065 | 0.7143 |
|
115 |
+
| 0.8412 | 48.0 | 1344 | 0.9065 | 0.7143 |
|
116 |
+
| 0.8333 | 49.0 | 1372 | 0.9066 | 0.7143 |
|
117 |
+
| 0.8603 | 50.0 | 1400 | 0.9066 | 0.7143 |
|
118 |
+
|
119 |
+
|
120 |
+
### Framework versions
|
121 |
+
|
122 |
+
- Transformers 4.35.2
|
123 |
+
- Pytorch 2.1.0+cu118
|
124 |
+
- Datasets 2.15.0
|
125 |
+
- 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 343086480
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:368366057ce8cfed53170704e7001cc51bd724a080bcf9d0b407108dec8c1d91
|
3 |
size 343086480
|