hkivancoral
commited on
Commit
•
6fbcdc8
1
Parent(s):
dbdf7ff
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: smids_10x_deit_tiny_sgd_00001_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: 0.51
|
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_10x_deit_tiny_sgd_00001_fold4
|
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: 0.9601
|
36 |
+
- Accuracy: 0.51
|
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 |
+
| 1.4156 | 1.0 | 750 | 1.2978 | 0.34 |
|
69 |
+
| 1.3315 | 2.0 | 1500 | 1.2425 | 0.3483 |
|
70 |
+
| 1.2993 | 3.0 | 2250 | 1.2021 | 0.37 |
|
71 |
+
| 1.2642 | 4.0 | 3000 | 1.1733 | 0.3717 |
|
72 |
+
| 1.1084 | 5.0 | 3750 | 1.1526 | 0.375 |
|
73 |
+
| 1.1915 | 6.0 | 4500 | 1.1373 | 0.3733 |
|
74 |
+
| 1.1121 | 7.0 | 5250 | 1.1248 | 0.3817 |
|
75 |
+
| 1.1023 | 8.0 | 6000 | 1.1144 | 0.39 |
|
76 |
+
| 1.0611 | 9.0 | 6750 | 1.1051 | 0.3867 |
|
77 |
+
| 1.0698 | 10.0 | 7500 | 1.0965 | 0.39 |
|
78 |
+
| 1.0512 | 11.0 | 8250 | 1.0884 | 0.4017 |
|
79 |
+
| 1.0962 | 12.0 | 9000 | 1.0808 | 0.405 |
|
80 |
+
| 1.0873 | 13.0 | 9750 | 1.0735 | 0.4117 |
|
81 |
+
| 1.0536 | 14.0 | 10500 | 1.0664 | 0.4183 |
|
82 |
+
| 1.0525 | 15.0 | 11250 | 1.0596 | 0.4283 |
|
83 |
+
| 1.026 | 16.0 | 12000 | 1.0532 | 0.4317 |
|
84 |
+
| 1.0131 | 17.0 | 12750 | 1.0470 | 0.44 |
|
85 |
+
| 0.9786 | 18.0 | 13500 | 1.0410 | 0.4433 |
|
86 |
+
| 0.9869 | 19.0 | 14250 | 1.0353 | 0.4467 |
|
87 |
+
| 0.9996 | 20.0 | 15000 | 1.0299 | 0.4517 |
|
88 |
+
| 1.0078 | 21.0 | 15750 | 1.0247 | 0.4533 |
|
89 |
+
| 0.9709 | 22.0 | 16500 | 1.0197 | 0.4617 |
|
90 |
+
| 1.009 | 23.0 | 17250 | 1.0149 | 0.4633 |
|
91 |
+
| 1.0068 | 24.0 | 18000 | 1.0104 | 0.4633 |
|
92 |
+
| 0.9737 | 25.0 | 18750 | 1.0061 | 0.47 |
|
93 |
+
| 0.9634 | 26.0 | 19500 | 1.0021 | 0.4767 |
|
94 |
+
| 0.9648 | 27.0 | 20250 | 0.9982 | 0.4783 |
|
95 |
+
| 0.931 | 28.0 | 21000 | 0.9946 | 0.485 |
|
96 |
+
| 0.993 | 29.0 | 21750 | 0.9911 | 0.4867 |
|
97 |
+
| 0.9852 | 30.0 | 22500 | 0.9879 | 0.49 |
|
98 |
+
| 0.9579 | 31.0 | 23250 | 0.9848 | 0.49 |
|
99 |
+
| 0.9747 | 32.0 | 24000 | 0.9819 | 0.4933 |
|
100 |
+
| 0.9501 | 33.0 | 24750 | 0.9793 | 0.5017 |
|
101 |
+
| 0.9432 | 34.0 | 25500 | 0.9768 | 0.5033 |
|
102 |
+
| 0.9384 | 35.0 | 26250 | 0.9745 | 0.505 |
|
103 |
+
| 0.9356 | 36.0 | 27000 | 0.9724 | 0.505 |
|
104 |
+
| 0.9023 | 37.0 | 27750 | 0.9705 | 0.5067 |
|
105 |
+
| 0.9257 | 38.0 | 28500 | 0.9687 | 0.5083 |
|
106 |
+
| 0.9635 | 39.0 | 29250 | 0.9672 | 0.5083 |
|
107 |
+
| 0.9335 | 40.0 | 30000 | 0.9658 | 0.51 |
|
108 |
+
| 0.8943 | 41.0 | 30750 | 0.9645 | 0.51 |
|
109 |
+
| 0.9485 | 42.0 | 31500 | 0.9635 | 0.51 |
|
110 |
+
| 0.976 | 43.0 | 32250 | 0.9626 | 0.51 |
|
111 |
+
| 0.9386 | 44.0 | 33000 | 0.9619 | 0.51 |
|
112 |
+
| 0.9526 | 45.0 | 33750 | 0.9613 | 0.51 |
|
113 |
+
| 0.9016 | 46.0 | 34500 | 0.9608 | 0.51 |
|
114 |
+
| 0.9008 | 47.0 | 35250 | 0.9605 | 0.51 |
|
115 |
+
| 0.9525 | 48.0 | 36000 | 0.9603 | 0.51 |
|
116 |
+
| 0.8965 | 49.0 | 36750 | 0.9602 | 0.51 |
|
117 |
+
| 0.8897 | 50.0 | 37500 | 0.9601 | 0.51 |
|
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 22167850
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e1586a7247a0e5015305c627ac5f9ff34e619730fe15d8a2992d84da591c07d
|
3 |
size 22167850
|