hkivancoral
commited on
Commit
•
23ed954
1
Parent(s):
5195ba1
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_5x_beit_base_adamax_0001_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: 0.8666666666666667
|
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_beit_base_adamax_0001_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: 1.1073
|
36 |
+
- Accuracy: 0.8667
|
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 |
+
| 0.56 | 1.0 | 27 | 0.5803 | 0.8444 |
|
69 |
+
| 0.1296 | 2.0 | 54 | 0.5439 | 0.8444 |
|
70 |
+
| 0.0323 | 3.0 | 81 | 1.1689 | 0.7556 |
|
71 |
+
| 0.051 | 4.0 | 108 | 0.6969 | 0.8444 |
|
72 |
+
| 0.0058 | 5.0 | 135 | 0.7561 | 0.8444 |
|
73 |
+
| 0.0281 | 6.0 | 162 | 0.6767 | 0.8444 |
|
74 |
+
| 0.0031 | 7.0 | 189 | 0.9959 | 0.8 |
|
75 |
+
| 0.006 | 8.0 | 216 | 1.0852 | 0.8222 |
|
76 |
+
| 0.0042 | 9.0 | 243 | 0.9557 | 0.8667 |
|
77 |
+
| 0.0002 | 10.0 | 270 | 0.9792 | 0.8444 |
|
78 |
+
| 0.0001 | 11.0 | 297 | 1.0071 | 0.8667 |
|
79 |
+
| 0.0001 | 12.0 | 324 | 1.1614 | 0.8 |
|
80 |
+
| 0.0001 | 13.0 | 351 | 1.0429 | 0.8667 |
|
81 |
+
| 0.0001 | 14.0 | 378 | 1.0442 | 0.8667 |
|
82 |
+
| 0.0001 | 15.0 | 405 | 1.1430 | 0.8222 |
|
83 |
+
| 0.0001 | 16.0 | 432 | 1.1457 | 0.8222 |
|
84 |
+
| 0.0027 | 17.0 | 459 | 1.3728 | 0.8222 |
|
85 |
+
| 0.0001 | 18.0 | 486 | 1.0448 | 0.8667 |
|
86 |
+
| 0.0001 | 19.0 | 513 | 1.0357 | 0.8667 |
|
87 |
+
| 0.0 | 20.0 | 540 | 1.2604 | 0.8 |
|
88 |
+
| 0.0026 | 21.0 | 567 | 1.0654 | 0.8667 |
|
89 |
+
| 0.0004 | 22.0 | 594 | 1.1414 | 0.8444 |
|
90 |
+
| 0.0001 | 23.0 | 621 | 1.1523 | 0.8444 |
|
91 |
+
| 0.0001 | 24.0 | 648 | 1.1307 | 0.8444 |
|
92 |
+
| 0.0002 | 25.0 | 675 | 1.1816 | 0.8444 |
|
93 |
+
| 0.0 | 26.0 | 702 | 1.1278 | 0.8444 |
|
94 |
+
| 0.0 | 27.0 | 729 | 1.0224 | 0.8667 |
|
95 |
+
| 0.0001 | 28.0 | 756 | 1.4430 | 0.7333 |
|
96 |
+
| 0.0001 | 29.0 | 783 | 1.3228 | 0.7556 |
|
97 |
+
| 0.0 | 30.0 | 810 | 1.2875 | 0.8 |
|
98 |
+
| 0.0001 | 31.0 | 837 | 1.2284 | 0.8222 |
|
99 |
+
| 0.0003 | 32.0 | 864 | 1.3104 | 0.8444 |
|
100 |
+
| 0.0001 | 33.0 | 891 | 1.1798 | 0.8667 |
|
101 |
+
| 0.0001 | 34.0 | 918 | 1.1586 | 0.8667 |
|
102 |
+
| 0.0001 | 35.0 | 945 | 1.1617 | 0.8667 |
|
103 |
+
| 0.0 | 36.0 | 972 | 1.1634 | 0.8667 |
|
104 |
+
| 0.0 | 37.0 | 999 | 1.1712 | 0.8667 |
|
105 |
+
| 0.0 | 38.0 | 1026 | 1.1767 | 0.8667 |
|
106 |
+
| 0.0 | 39.0 | 1053 | 1.1666 | 0.8667 |
|
107 |
+
| 0.0 | 40.0 | 1080 | 1.1693 | 0.8667 |
|
108 |
+
| 0.0 | 41.0 | 1107 | 1.1706 | 0.8667 |
|
109 |
+
| 0.0 | 42.0 | 1134 | 1.0988 | 0.8667 |
|
110 |
+
| 0.001 | 43.0 | 1161 | 1.0945 | 0.8667 |
|
111 |
+
| 0.0 | 44.0 | 1188 | 1.0895 | 0.8667 |
|
112 |
+
| 0.0 | 45.0 | 1215 | 1.0977 | 0.8667 |
|
113 |
+
| 0.0004 | 46.0 | 1242 | 1.0978 | 0.8667 |
|
114 |
+
| 0.0 | 47.0 | 1269 | 1.1013 | 0.8667 |
|
115 |
+
| 0.0001 | 48.0 | 1296 | 1.1072 | 0.8667 |
|
116 |
+
| 0.0001 | 49.0 | 1323 | 1.1073 | 0.8667 |
|
117 |
+
| 0.0 | 50.0 | 1350 | 1.1073 | 0.8667 |
|
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 sha256:56a0194399e7f664e3dbfc499eee8e17cabcf0d1b891c58286474a9cd8facd3d
|
3 |
size 343086480
|
runs/Nov27_22-53-44_0a7ba84d0833/events.out.tfevents.1701125638.0a7ba84d0833.1449.1
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:f2fe5dce62133572715db0e701f7fdb377e72276cb633560488daf9577c458ef
|
3 |
+
size 42580
|