hkivancoral
commited on
Commit
•
d09392d
1
Parent(s):
d82aa21
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: 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_5x_deit_tiny_sgd_0001_fold5
|
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: 0.3902439024390244
|
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_deit_tiny_sgd_0001_fold5
|
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: 1.4076
|
36 |
+
- Accuracy: 0.3902
|
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: 0.0001
|
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 |
+
| 1.5266 | 1.0 | 28 | 1.7430 | 0.2439 |
|
69 |
+
| 1.4534 | 2.0 | 56 | 1.7173 | 0.2439 |
|
70 |
+
| 1.4589 | 3.0 | 84 | 1.6934 | 0.2439 |
|
71 |
+
| 1.4589 | 4.0 | 112 | 1.6722 | 0.2439 |
|
72 |
+
| 1.4564 | 5.0 | 140 | 1.6529 | 0.2439 |
|
73 |
+
| 1.475 | 6.0 | 168 | 1.6343 | 0.2439 |
|
74 |
+
| 1.4209 | 7.0 | 196 | 1.6174 | 0.2439 |
|
75 |
+
| 1.4499 | 8.0 | 224 | 1.6010 | 0.2439 |
|
76 |
+
| 1.482 | 9.0 | 252 | 1.5863 | 0.2439 |
|
77 |
+
| 1.4359 | 10.0 | 280 | 1.5742 | 0.2439 |
|
78 |
+
| 1.4148 | 11.0 | 308 | 1.5620 | 0.2439 |
|
79 |
+
| 1.4175 | 12.0 | 336 | 1.5508 | 0.2439 |
|
80 |
+
| 1.4309 | 13.0 | 364 | 1.5414 | 0.2439 |
|
81 |
+
| 1.4434 | 14.0 | 392 | 1.5314 | 0.2439 |
|
82 |
+
| 1.4301 | 15.0 | 420 | 1.5227 | 0.2195 |
|
83 |
+
| 1.4116 | 16.0 | 448 | 1.5140 | 0.2439 |
|
84 |
+
| 1.4213 | 17.0 | 476 | 1.5063 | 0.2439 |
|
85 |
+
| 1.4048 | 18.0 | 504 | 1.4983 | 0.2439 |
|
86 |
+
| 1.4279 | 19.0 | 532 | 1.4909 | 0.2439 |
|
87 |
+
| 1.422 | 20.0 | 560 | 1.4842 | 0.2683 |
|
88 |
+
| 1.3928 | 21.0 | 588 | 1.4779 | 0.2683 |
|
89 |
+
| 1.3839 | 22.0 | 616 | 1.4719 | 0.2683 |
|
90 |
+
| 1.393 | 23.0 | 644 | 1.4665 | 0.2683 |
|
91 |
+
| 1.3889 | 24.0 | 672 | 1.4611 | 0.2683 |
|
92 |
+
| 1.3853 | 25.0 | 700 | 1.4568 | 0.2927 |
|
93 |
+
| 1.349 | 26.0 | 728 | 1.4521 | 0.3171 |
|
94 |
+
| 1.3871 | 27.0 | 756 | 1.4479 | 0.3171 |
|
95 |
+
| 1.3753 | 28.0 | 784 | 1.4439 | 0.3415 |
|
96 |
+
| 1.3905 | 29.0 | 812 | 1.4406 | 0.3415 |
|
97 |
+
| 1.3675 | 30.0 | 840 | 1.4371 | 0.3415 |
|
98 |
+
| 1.3814 | 31.0 | 868 | 1.4338 | 0.3415 |
|
99 |
+
| 1.3666 | 32.0 | 896 | 1.4305 | 0.3415 |
|
100 |
+
| 1.3609 | 33.0 | 924 | 1.4275 | 0.3659 |
|
101 |
+
| 1.3514 | 34.0 | 952 | 1.4249 | 0.3902 |
|
102 |
+
| 1.3706 | 35.0 | 980 | 1.4224 | 0.3902 |
|
103 |
+
| 1.3609 | 36.0 | 1008 | 1.4204 | 0.3902 |
|
104 |
+
| 1.3195 | 37.0 | 1036 | 1.4184 | 0.3902 |
|
105 |
+
| 1.3869 | 38.0 | 1064 | 1.4165 | 0.3902 |
|
106 |
+
| 1.3586 | 39.0 | 1092 | 1.4149 | 0.3902 |
|
107 |
+
| 1.3675 | 40.0 | 1120 | 1.4134 | 0.3902 |
|
108 |
+
| 1.3299 | 41.0 | 1148 | 1.4121 | 0.3902 |
|
109 |
+
| 1.3616 | 42.0 | 1176 | 1.4109 | 0.3902 |
|
110 |
+
| 1.3801 | 43.0 | 1204 | 1.4099 | 0.3902 |
|
111 |
+
| 1.3528 | 44.0 | 1232 | 1.4091 | 0.3902 |
|
112 |
+
| 1.3348 | 45.0 | 1260 | 1.4084 | 0.3902 |
|
113 |
+
| 1.353 | 46.0 | 1288 | 1.4080 | 0.3902 |
|
114 |
+
| 1.3488 | 47.0 | 1316 | 1.4077 | 0.3902 |
|
115 |
+
| 1.3749 | 48.0 | 1344 | 1.4076 | 0.3902 |
|
116 |
+
| 1.3556 | 49.0 | 1372 | 1.4076 | 0.3902 |
|
117 |
+
| 1.3606 | 50.0 | 1400 | 1.4076 | 0.3902 |
|
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 22123464
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e15da4ef69e4162debdc98a4c3fad91a20d242ae186f3e0363435108d938f44
|
3 |
size 22123464
|