Commit
•
89e641c
1
Parent(s):
214f5e1
End of training
Browse files- README.md +125 -0
- pytorch_model.bin +1 -1
README.md
ADDED
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: facebook/deit-tiny-patch16-224
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- imagefolder
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: hushem_40x_deit_tiny_sgd_001_fold1
|
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: 0.7333333333333333
|
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_40x_deit_tiny_sgd_001_fold1
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [facebook/deit-tiny-patch16-224](https://huggingface.co/facebook/deit-tiny-patch16-224) on the imagefolder dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.9268
|
36 |
+
- Accuracy: 0.7333
|
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 |
+
| 1.1534 | 1.0 | 215 | 1.3121 | 0.3778 |
|
69 |
+
| 0.8744 | 2.0 | 430 | 1.2305 | 0.5111 |
|
70 |
+
| 0.7578 | 3.0 | 645 | 1.1023 | 0.5556 |
|
71 |
+
| 0.6354 | 4.0 | 860 | 0.9584 | 0.5778 |
|
72 |
+
| 0.4832 | 5.0 | 1075 | 0.8877 | 0.6444 |
|
73 |
+
| 0.4506 | 6.0 | 1290 | 0.8214 | 0.6889 |
|
74 |
+
| 0.3619 | 7.0 | 1505 | 0.8077 | 0.6889 |
|
75 |
+
| 0.3187 | 8.0 | 1720 | 0.7845 | 0.6667 |
|
76 |
+
| 0.2423 | 9.0 | 1935 | 0.7629 | 0.7111 |
|
77 |
+
| 0.2351 | 10.0 | 2150 | 0.7464 | 0.7333 |
|
78 |
+
| 0.2043 | 11.0 | 2365 | 0.7249 | 0.6889 |
|
79 |
+
| 0.1712 | 12.0 | 2580 | 0.7297 | 0.7111 |
|
80 |
+
| 0.1294 | 13.0 | 2795 | 0.7280 | 0.7333 |
|
81 |
+
| 0.1185 | 14.0 | 3010 | 0.7610 | 0.7333 |
|
82 |
+
| 0.1264 | 15.0 | 3225 | 0.7479 | 0.7333 |
|
83 |
+
| 0.0869 | 16.0 | 3440 | 0.7617 | 0.7333 |
|
84 |
+
| 0.0902 | 17.0 | 3655 | 0.7623 | 0.7333 |
|
85 |
+
| 0.0782 | 18.0 | 3870 | 0.7805 | 0.7333 |
|
86 |
+
| 0.071 | 19.0 | 4085 | 0.7715 | 0.7333 |
|
87 |
+
| 0.063 | 20.0 | 4300 | 0.7777 | 0.7333 |
|
88 |
+
| 0.0587 | 21.0 | 4515 | 0.7497 | 0.7333 |
|
89 |
+
| 0.0675 | 22.0 | 4730 | 0.7998 | 0.7333 |
|
90 |
+
| 0.0426 | 23.0 | 4945 | 0.8200 | 0.7333 |
|
91 |
+
| 0.0373 | 24.0 | 5160 | 0.8281 | 0.7111 |
|
92 |
+
| 0.0441 | 25.0 | 5375 | 0.8317 | 0.7111 |
|
93 |
+
| 0.0323 | 26.0 | 5590 | 0.8133 | 0.7111 |
|
94 |
+
| 0.0359 | 27.0 | 5805 | 0.8214 | 0.7111 |
|
95 |
+
| 0.0291 | 28.0 | 6020 | 0.8265 | 0.7111 |
|
96 |
+
| 0.0287 | 29.0 | 6235 | 0.8490 | 0.7111 |
|
97 |
+
| 0.0271 | 30.0 | 6450 | 0.8534 | 0.7111 |
|
98 |
+
| 0.0256 | 31.0 | 6665 | 0.8626 | 0.7111 |
|
99 |
+
| 0.0212 | 32.0 | 6880 | 0.8791 | 0.7111 |
|
100 |
+
| 0.0155 | 33.0 | 7095 | 0.8740 | 0.7333 |
|
101 |
+
| 0.0144 | 34.0 | 7310 | 0.8433 | 0.7333 |
|
102 |
+
| 0.0132 | 35.0 | 7525 | 0.8680 | 0.7333 |
|
103 |
+
| 0.015 | 36.0 | 7740 | 0.8880 | 0.7333 |
|
104 |
+
| 0.0129 | 37.0 | 7955 | 0.8931 | 0.7333 |
|
105 |
+
| 0.018 | 38.0 | 8170 | 0.8891 | 0.7333 |
|
106 |
+
| 0.0092 | 39.0 | 8385 | 0.9122 | 0.7333 |
|
107 |
+
| 0.0085 | 40.0 | 8600 | 0.9159 | 0.7333 |
|
108 |
+
| 0.0124 | 41.0 | 8815 | 0.9199 | 0.7333 |
|
109 |
+
| 0.0125 | 42.0 | 9030 | 0.9056 | 0.7333 |
|
110 |
+
| 0.0107 | 43.0 | 9245 | 0.9191 | 0.7333 |
|
111 |
+
| 0.0095 | 44.0 | 9460 | 0.9083 | 0.7333 |
|
112 |
+
| 0.0115 | 45.0 | 9675 | 0.9189 | 0.7333 |
|
113 |
+
| 0.0088 | 46.0 | 9890 | 0.9241 | 0.7333 |
|
114 |
+
| 0.0065 | 47.0 | 10105 | 0.9299 | 0.7333 |
|
115 |
+
| 0.007 | 48.0 | 10320 | 0.9257 | 0.7333 |
|
116 |
+
| 0.0129 | 49.0 | 10535 | 0.9260 | 0.7333 |
|
117 |
+
| 0.0229 | 50.0 | 10750 | 0.9268 | 0.7333 |
|
118 |
+
|
119 |
+
|
120 |
+
### Framework versions
|
121 |
+
|
122 |
+
- Transformers 4.32.1
|
123 |
+
- Pytorch 2.1.1+cu121
|
124 |
+
- Datasets 2.12.0
|
125 |
+
- Tokenizers 0.13.2
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 22168618
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9ba14b340677989dbf8c52d59faae49ff21f1b3bd3ab0b1790c8d8a61b80069
|
3 |
size 22168618
|