hkivancoral
commited on
Commit
•
52c4dd6
1
Parent(s):
bf05271
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_1x_deit_tiny_rms_lr001_fold3
|
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: 0.27906976744186046
|
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_1x_deit_tiny_rms_lr001_fold3
|
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: 1.7042
|
36 |
+
- Accuracy: 0.2791
|
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 |
+
| No log | 1.0 | 6 | 3.1061 | 0.2326 |
|
69 |
+
| 4.0184 | 2.0 | 12 | 1.7666 | 0.2558 |
|
70 |
+
| 4.0184 | 3.0 | 18 | 1.6279 | 0.2558 |
|
71 |
+
| 1.7385 | 4.0 | 24 | 1.9636 | 0.2558 |
|
72 |
+
| 1.583 | 5.0 | 30 | 1.6503 | 0.2558 |
|
73 |
+
| 1.583 | 6.0 | 36 | 1.4630 | 0.2326 |
|
74 |
+
| 1.4859 | 7.0 | 42 | 3.2936 | 0.2326 |
|
75 |
+
| 1.4859 | 8.0 | 48 | 2.0073 | 0.2558 |
|
76 |
+
| 2.0303 | 9.0 | 54 | 1.4859 | 0.2326 |
|
77 |
+
| 1.4062 | 10.0 | 60 | 1.6529 | 0.2326 |
|
78 |
+
| 1.4062 | 11.0 | 66 | 1.4259 | 0.2791 |
|
79 |
+
| 1.359 | 12.0 | 72 | 1.3892 | 0.2558 |
|
80 |
+
| 1.359 | 13.0 | 78 | 1.4650 | 0.3023 |
|
81 |
+
| 1.3464 | 14.0 | 84 | 1.4368 | 0.2558 |
|
82 |
+
| 1.262 | 15.0 | 90 | 1.4241 | 0.2558 |
|
83 |
+
| 1.262 | 16.0 | 96 | 1.6562 | 0.3023 |
|
84 |
+
| 1.2521 | 17.0 | 102 | 1.3729 | 0.3023 |
|
85 |
+
| 1.2521 | 18.0 | 108 | 1.5241 | 0.2093 |
|
86 |
+
| 1.2212 | 19.0 | 114 | 1.5032 | 0.3023 |
|
87 |
+
| 1.1882 | 20.0 | 120 | 1.4178 | 0.2558 |
|
88 |
+
| 1.1882 | 21.0 | 126 | 1.8156 | 0.3023 |
|
89 |
+
| 1.1382 | 22.0 | 132 | 1.5280 | 0.2558 |
|
90 |
+
| 1.1382 | 23.0 | 138 | 1.5037 | 0.2326 |
|
91 |
+
| 1.0802 | 24.0 | 144 | 1.5058 | 0.3488 |
|
92 |
+
| 1.1083 | 25.0 | 150 | 1.5421 | 0.2791 |
|
93 |
+
| 1.1083 | 26.0 | 156 | 1.5398 | 0.2558 |
|
94 |
+
| 1.0555 | 27.0 | 162 | 1.8560 | 0.2791 |
|
95 |
+
| 1.0555 | 28.0 | 168 | 1.9193 | 0.2558 |
|
96 |
+
| 1.0051 | 29.0 | 174 | 1.5934 | 0.3256 |
|
97 |
+
| 0.958 | 30.0 | 180 | 1.6481 | 0.2791 |
|
98 |
+
| 0.958 | 31.0 | 186 | 1.5950 | 0.2791 |
|
99 |
+
| 0.9855 | 32.0 | 192 | 1.5539 | 0.2558 |
|
100 |
+
| 0.9855 | 33.0 | 198 | 1.6644 | 0.2791 |
|
101 |
+
| 0.9482 | 34.0 | 204 | 1.6743 | 0.2326 |
|
102 |
+
| 0.9401 | 35.0 | 210 | 1.6352 | 0.3023 |
|
103 |
+
| 0.9401 | 36.0 | 216 | 1.6896 | 0.2791 |
|
104 |
+
| 0.9225 | 37.0 | 222 | 1.7369 | 0.2326 |
|
105 |
+
| 0.9225 | 38.0 | 228 | 1.6916 | 0.2558 |
|
106 |
+
| 0.8891 | 39.0 | 234 | 1.6919 | 0.2791 |
|
107 |
+
| 0.8732 | 40.0 | 240 | 1.7104 | 0.2791 |
|
108 |
+
| 0.8732 | 41.0 | 246 | 1.7028 | 0.2791 |
|
109 |
+
| 0.8715 | 42.0 | 252 | 1.7042 | 0.2791 |
|
110 |
+
| 0.8715 | 43.0 | 258 | 1.7042 | 0.2791 |
|
111 |
+
| 0.8826 | 44.0 | 264 | 1.7042 | 0.2791 |
|
112 |
+
| 0.8986 | 45.0 | 270 | 1.7042 | 0.2791 |
|
113 |
+
| 0.8986 | 46.0 | 276 | 1.7042 | 0.2791 |
|
114 |
+
| 0.8589 | 47.0 | 282 | 1.7042 | 0.2791 |
|
115 |
+
| 0.8589 | 48.0 | 288 | 1.7042 | 0.2791 |
|
116 |
+
| 0.9236 | 49.0 | 294 | 1.7042 | 0.2791 |
|
117 |
+
| 0.8539 | 50.0 | 300 | 1.7042 | 0.2791 |
|
118 |
+
|
119 |
+
|
120 |
+
### Framework versions
|
121 |
+
|
122 |
+
- Transformers 4.35.0
|
123 |
+
- Pytorch 2.1.0+cu118
|
124 |
+
- Datasets 2.14.6
|
125 |
+
- Tokenizers 0.14.1
|
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:f78c75d773ddeb6e2ee9b68ae8864f9a0478efeb0ba718e2decde51c196424ae
|
3 |
size 22123464
|