hkivancoral
commited on
Commit
•
caa89d8
1
Parent(s):
d82c710
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-small-patch16-224
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- imagefolder
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: smids_3x_deit_small_sgd_00001_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: 0.49248747913188645
|
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 |
+
# smids_3x_deit_small_sgd_00001_fold1
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [facebook/deit-small-patch16-224](https://huggingface.co/facebook/deit-small-patch16-224) on the imagefolder dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 1.0200
|
36 |
+
- Accuracy: 0.4925
|
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: 1e-05
|
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 |
+
| 1.0919 | 1.0 | 226 | 1.0743 | 0.4407 |
|
69 |
+
| 1.0742 | 2.0 | 452 | 1.0717 | 0.4391 |
|
70 |
+
| 1.0524 | 3.0 | 678 | 1.0693 | 0.4357 |
|
71 |
+
| 1.0603 | 4.0 | 904 | 1.0670 | 0.4391 |
|
72 |
+
| 1.0627 | 5.0 | 1130 | 1.0647 | 0.4391 |
|
73 |
+
| 1.0778 | 6.0 | 1356 | 1.0625 | 0.4457 |
|
74 |
+
| 1.0591 | 7.0 | 1582 | 1.0603 | 0.4441 |
|
75 |
+
| 1.0519 | 8.0 | 1808 | 1.0582 | 0.4457 |
|
76 |
+
| 1.0538 | 9.0 | 2034 | 1.0562 | 0.4474 |
|
77 |
+
| 1.0527 | 10.0 | 2260 | 1.0542 | 0.4491 |
|
78 |
+
| 1.057 | 11.0 | 2486 | 1.0523 | 0.4491 |
|
79 |
+
| 1.0703 | 12.0 | 2712 | 1.0505 | 0.4491 |
|
80 |
+
| 1.0101 | 13.0 | 2938 | 1.0488 | 0.4474 |
|
81 |
+
| 1.0585 | 14.0 | 3164 | 1.0471 | 0.4491 |
|
82 |
+
| 1.0541 | 15.0 | 3390 | 1.0455 | 0.4541 |
|
83 |
+
| 1.0416 | 16.0 | 3616 | 1.0438 | 0.4591 |
|
84 |
+
| 1.03 | 17.0 | 3842 | 1.0423 | 0.4608 |
|
85 |
+
| 1.0278 | 18.0 | 4068 | 1.0408 | 0.4624 |
|
86 |
+
| 1.0509 | 19.0 | 4294 | 1.0394 | 0.4641 |
|
87 |
+
| 1.0188 | 20.0 | 4520 | 1.0381 | 0.4674 |
|
88 |
+
| 1.0344 | 21.0 | 4746 | 1.0367 | 0.4674 |
|
89 |
+
| 1.0343 | 22.0 | 4972 | 1.0355 | 0.4691 |
|
90 |
+
| 1.0324 | 23.0 | 5198 | 1.0343 | 0.4691 |
|
91 |
+
| 1.0367 | 24.0 | 5424 | 1.0331 | 0.4725 |
|
92 |
+
| 0.9995 | 25.0 | 5650 | 1.0320 | 0.4725 |
|
93 |
+
| 1.0409 | 26.0 | 5876 | 1.0310 | 0.4725 |
|
94 |
+
| 1.0145 | 27.0 | 6102 | 1.0300 | 0.4758 |
|
95 |
+
| 1.0333 | 28.0 | 6328 | 1.0290 | 0.4758 |
|
96 |
+
| 1.0283 | 29.0 | 6554 | 1.0281 | 0.4791 |
|
97 |
+
| 1.0286 | 30.0 | 6780 | 1.0273 | 0.4808 |
|
98 |
+
| 1.0197 | 31.0 | 7006 | 1.0265 | 0.4808 |
|
99 |
+
| 1.0259 | 32.0 | 7232 | 1.0257 | 0.4791 |
|
100 |
+
| 1.0188 | 33.0 | 7458 | 1.0250 | 0.4808 |
|
101 |
+
| 1.0201 | 34.0 | 7684 | 1.0244 | 0.4808 |
|
102 |
+
| 1.0339 | 35.0 | 7910 | 1.0238 | 0.4825 |
|
103 |
+
| 1.0181 | 36.0 | 8136 | 1.0232 | 0.4875 |
|
104 |
+
| 1.0181 | 37.0 | 8362 | 1.0227 | 0.4875 |
|
105 |
+
| 1.0115 | 38.0 | 8588 | 1.0223 | 0.4875 |
|
106 |
+
| 0.9878 | 39.0 | 8814 | 1.0218 | 0.4891 |
|
107 |
+
| 1.0096 | 40.0 | 9040 | 1.0215 | 0.4891 |
|
108 |
+
| 1.024 | 41.0 | 9266 | 1.0212 | 0.4891 |
|
109 |
+
| 1.0376 | 42.0 | 9492 | 1.0209 | 0.4908 |
|
110 |
+
| 1.0233 | 43.0 | 9718 | 1.0206 | 0.4925 |
|
111 |
+
| 1.0195 | 44.0 | 9944 | 1.0204 | 0.4925 |
|
112 |
+
| 1.0135 | 45.0 | 10170 | 1.0203 | 0.4925 |
|
113 |
+
| 1.039 | 46.0 | 10396 | 1.0202 | 0.4925 |
|
114 |
+
| 1.0136 | 47.0 | 10622 | 1.0201 | 0.4925 |
|
115 |
+
| 1.0247 | 48.0 | 10848 | 1.0200 | 0.4925 |
|
116 |
+
| 1.0178 | 49.0 | 11074 | 1.0200 | 0.4925 |
|
117 |
+
| 1.0351 | 50.0 | 11300 | 1.0200 | 0.4925 |
|
118 |
+
|
119 |
+
|
120 |
+
### Framework versions
|
121 |
+
|
122 |
+
- Transformers 4.32.1
|
123 |
+
- Pytorch 2.1.0+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 86735658
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1d8fdb65158b67340b2847b60479ae2a60726fca8f813c98004f300ae8c5b73
|
3 |
size 86735658
|