hkivancoral
commited on
Commit
•
e2e9878
1
Parent(s):
d677f89
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: microsoft/beit-large-patch16-224
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- imagefolder
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: smids_10x_beit_large_adamax_001_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: 0.9016666666666666
|
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_beit_large_adamax_001_fold3
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [microsoft/beit-large-patch16-224](https://huggingface.co/microsoft/beit-large-patch16-224) on the imagefolder dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 1.0324
|
36 |
+
- Accuracy: 0.9017
|
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 |
+
| 0.3438 | 1.0 | 750 | 0.3826 | 0.8517 |
|
69 |
+
| 0.2931 | 2.0 | 1500 | 0.3034 | 0.89 |
|
70 |
+
| 0.2025 | 3.0 | 2250 | 0.3971 | 0.8783 |
|
71 |
+
| 0.2582 | 4.0 | 3000 | 0.3086 | 0.8867 |
|
72 |
+
| 0.2483 | 5.0 | 3750 | 0.3346 | 0.8917 |
|
73 |
+
| 0.1606 | 6.0 | 4500 | 0.3908 | 0.8717 |
|
74 |
+
| 0.1236 | 7.0 | 5250 | 0.4286 | 0.8783 |
|
75 |
+
| 0.1197 | 8.0 | 6000 | 0.3887 | 0.9 |
|
76 |
+
| 0.0412 | 9.0 | 6750 | 0.4924 | 0.885 |
|
77 |
+
| 0.0384 | 10.0 | 7500 | 0.5551 | 0.89 |
|
78 |
+
| 0.0583 | 11.0 | 8250 | 0.4882 | 0.9017 |
|
79 |
+
| 0.0806 | 12.0 | 9000 | 0.5902 | 0.88 |
|
80 |
+
| 0.0489 | 13.0 | 9750 | 0.5212 | 0.88 |
|
81 |
+
| 0.0353 | 14.0 | 10500 | 0.5171 | 0.9 |
|
82 |
+
| 0.0094 | 15.0 | 11250 | 0.6341 | 0.895 |
|
83 |
+
| 0.0154 | 16.0 | 12000 | 0.5409 | 0.9133 |
|
84 |
+
| 0.0118 | 17.0 | 12750 | 0.6110 | 0.8833 |
|
85 |
+
| 0.0159 | 18.0 | 13500 | 0.6873 | 0.9033 |
|
86 |
+
| 0.0026 | 19.0 | 14250 | 0.7871 | 0.8983 |
|
87 |
+
| 0.0163 | 20.0 | 15000 | 0.6341 | 0.895 |
|
88 |
+
| 0.0002 | 21.0 | 15750 | 0.7139 | 0.9017 |
|
89 |
+
| 0.0006 | 22.0 | 16500 | 0.6717 | 0.9033 |
|
90 |
+
| 0.0266 | 23.0 | 17250 | 0.6268 | 0.895 |
|
91 |
+
| 0.0051 | 24.0 | 18000 | 0.6425 | 0.905 |
|
92 |
+
| 0.0 | 25.0 | 18750 | 0.7506 | 0.91 |
|
93 |
+
| 0.0004 | 26.0 | 19500 | 0.6864 | 0.9017 |
|
94 |
+
| 0.0002 | 27.0 | 20250 | 0.6111 | 0.9117 |
|
95 |
+
| 0.0163 | 28.0 | 21000 | 0.6875 | 0.9017 |
|
96 |
+
| 0.0001 | 29.0 | 21750 | 0.8050 | 0.8967 |
|
97 |
+
| 0.0002 | 30.0 | 22500 | 0.7397 | 0.8967 |
|
98 |
+
| 0.0004 | 31.0 | 23250 | 0.8218 | 0.8983 |
|
99 |
+
| 0.0 | 32.0 | 24000 | 0.8725 | 0.8983 |
|
100 |
+
| 0.0 | 33.0 | 24750 | 0.9662 | 0.8967 |
|
101 |
+
| 0.0 | 34.0 | 25500 | 0.9148 | 0.9083 |
|
102 |
+
| 0.0 | 35.0 | 26250 | 0.8492 | 0.9083 |
|
103 |
+
| 0.0001 | 36.0 | 27000 | 0.8264 | 0.9067 |
|
104 |
+
| 0.0 | 37.0 | 27750 | 0.8650 | 0.895 |
|
105 |
+
| 0.0004 | 38.0 | 28500 | 0.9030 | 0.91 |
|
106 |
+
| 0.0 | 39.0 | 29250 | 0.9540 | 0.9 |
|
107 |
+
| 0.0 | 40.0 | 30000 | 1.0292 | 0.8883 |
|
108 |
+
| 0.0 | 41.0 | 30750 | 1.0282 | 0.8917 |
|
109 |
+
| 0.0 | 42.0 | 31500 | 1.0128 | 0.8933 |
|
110 |
+
| 0.0 | 43.0 | 32250 | 1.0147 | 0.8983 |
|
111 |
+
| 0.0 | 44.0 | 33000 | 0.9709 | 0.8983 |
|
112 |
+
| 0.0 | 45.0 | 33750 | 0.9643 | 0.9067 |
|
113 |
+
| 0.0 | 46.0 | 34500 | 0.9770 | 0.9017 |
|
114 |
+
| 0.0 | 47.0 | 35250 | 1.0000 | 0.8983 |
|
115 |
+
| 0.0 | 48.0 | 36000 | 1.0223 | 0.9017 |
|
116 |
+
| 0.0 | 49.0 | 36750 | 1.0291 | 0.9017 |
|
117 |
+
| 0.0 | 50.0 | 37500 | 1.0324 | 0.9017 |
|
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 1213785638
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b91a2ffae1cbd2bee1e8095a33b46e6ab86b0063e0723ddd92a42aec675913d5
|
3 |
size 1213785638
|