hkivancoral
commited on
Commit
•
8fb5fd4
1
Parent(s):
e0ca4e4
End of training
Browse files
README.md
ADDED
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: microsoft/beit-base-patch16-224
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- imagefolder
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: hushem_1x_beit_base_adamax_00001_fold2
|
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: 0.6888888888888889
|
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_beit_base_adamax_00001_fold2
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [microsoft/beit-base-patch16-224](https://huggingface.co/microsoft/beit-base-patch16-224) on the imagefolder dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 1.0038
|
36 |
+
- Accuracy: 0.6889
|
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 |
+
| No log | 1.0 | 6 | 1.2765 | 0.4 |
|
69 |
+
| 1.3322 | 2.0 | 12 | 1.2154 | 0.4444 |
|
70 |
+
| 1.3322 | 3.0 | 18 | 1.1631 | 0.4889 |
|
71 |
+
| 0.9388 | 4.0 | 24 | 1.0966 | 0.4889 |
|
72 |
+
| 0.7193 | 5.0 | 30 | 1.0653 | 0.6 |
|
73 |
+
| 0.7193 | 6.0 | 36 | 1.0660 | 0.5556 |
|
74 |
+
| 0.5374 | 7.0 | 42 | 1.0203 | 0.5778 |
|
75 |
+
| 0.5374 | 8.0 | 48 | 1.0147 | 0.6 |
|
76 |
+
| 0.4187 | 9.0 | 54 | 1.0003 | 0.6222 |
|
77 |
+
| 0.3224 | 10.0 | 60 | 0.9783 | 0.6 |
|
78 |
+
| 0.3224 | 11.0 | 66 | 0.9383 | 0.6444 |
|
79 |
+
| 0.2464 | 12.0 | 72 | 0.9513 | 0.6444 |
|
80 |
+
| 0.2464 | 13.0 | 78 | 0.9808 | 0.6444 |
|
81 |
+
| 0.1839 | 14.0 | 84 | 0.9939 | 0.6667 |
|
82 |
+
| 0.1568 | 15.0 | 90 | 1.0128 | 0.6667 |
|
83 |
+
| 0.1568 | 16.0 | 96 | 0.9589 | 0.6889 |
|
84 |
+
| 0.1288 | 17.0 | 102 | 0.9172 | 0.6889 |
|
85 |
+
| 0.1288 | 18.0 | 108 | 0.9617 | 0.6667 |
|
86 |
+
| 0.1076 | 19.0 | 114 | 0.9784 | 0.6889 |
|
87 |
+
| 0.1101 | 20.0 | 120 | 0.9555 | 0.6889 |
|
88 |
+
| 0.1101 | 21.0 | 126 | 0.9639 | 0.6889 |
|
89 |
+
| 0.0715 | 22.0 | 132 | 1.0124 | 0.6667 |
|
90 |
+
| 0.0715 | 23.0 | 138 | 1.0281 | 0.6889 |
|
91 |
+
| 0.0643 | 24.0 | 144 | 0.9837 | 0.6889 |
|
92 |
+
| 0.062 | 25.0 | 150 | 0.9706 | 0.6889 |
|
93 |
+
| 0.062 | 26.0 | 156 | 0.9680 | 0.6889 |
|
94 |
+
| 0.0557 | 27.0 | 162 | 0.9640 | 0.6889 |
|
95 |
+
| 0.0557 | 28.0 | 168 | 0.9912 | 0.6889 |
|
96 |
+
| 0.0524 | 29.0 | 174 | 1.0047 | 0.7111 |
|
97 |
+
| 0.0432 | 30.0 | 180 | 1.0048 | 0.6889 |
|
98 |
+
| 0.0432 | 31.0 | 186 | 1.0092 | 0.6889 |
|
99 |
+
| 0.0454 | 32.0 | 192 | 1.0117 | 0.6889 |
|
100 |
+
| 0.0454 | 33.0 | 198 | 1.0112 | 0.6889 |
|
101 |
+
| 0.0405 | 34.0 | 204 | 0.9915 | 0.6889 |
|
102 |
+
| 0.0406 | 35.0 | 210 | 0.9689 | 0.6889 |
|
103 |
+
| 0.0406 | 36.0 | 216 | 0.9643 | 0.6889 |
|
104 |
+
| 0.0354 | 37.0 | 222 | 0.9716 | 0.6889 |
|
105 |
+
| 0.0354 | 38.0 | 228 | 0.9874 | 0.6889 |
|
106 |
+
| 0.0426 | 39.0 | 234 | 0.9950 | 0.6889 |
|
107 |
+
| 0.0369 | 40.0 | 240 | 0.9999 | 0.6889 |
|
108 |
+
| 0.0369 | 41.0 | 246 | 1.0036 | 0.6889 |
|
109 |
+
| 0.0338 | 42.0 | 252 | 1.0038 | 0.6889 |
|
110 |
+
| 0.0338 | 43.0 | 258 | 1.0038 | 0.6889 |
|
111 |
+
| 0.0349 | 44.0 | 264 | 1.0038 | 0.6889 |
|
112 |
+
| 0.0361 | 45.0 | 270 | 1.0038 | 0.6889 |
|
113 |
+
| 0.0361 | 46.0 | 276 | 1.0038 | 0.6889 |
|
114 |
+
| 0.0398 | 47.0 | 282 | 1.0038 | 0.6889 |
|
115 |
+
| 0.0398 | 48.0 | 288 | 1.0038 | 0.6889 |
|
116 |
+
| 0.0375 | 49.0 | 294 | 1.0038 | 0.6889 |
|
117 |
+
| 0.0265 | 50.0 | 300 | 1.0038 | 0.6889 |
|
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 343086480
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de8f3eb998ab58f2f18032bd64a374c76e2f6202038df977226969ead443a516
|
3 |
size 343086480
|
runs/Nov25_00-47-59_23c9de965386/events.out.tfevents.1700873280.23c9de965386.7636.10
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eeb65e770690b2789ee14e48903a2e7a05b61a43ac55316ed9afd1f17e0370a8
|
3 |
+
size 25995
|