Commit
•
4636be7
1
Parent(s):
69d7d48
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: smids_1x_beit_base_adamax_00001_fold1
|
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: 0.9031719532554258
|
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_1x_beit_base_adamax_00001_fold1
|
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: 0.6618
|
36 |
+
- Accuracy: 0.9032
|
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 |
+
| 0.4246 | 1.0 | 76 | 0.3687 | 0.8598 |
|
69 |
+
| 0.2552 | 2.0 | 152 | 0.2999 | 0.8798 |
|
70 |
+
| 0.1978 | 3.0 | 228 | 0.2886 | 0.8731 |
|
71 |
+
| 0.1972 | 4.0 | 304 | 0.2763 | 0.8865 |
|
72 |
+
| 0.1608 | 5.0 | 380 | 0.2799 | 0.8865 |
|
73 |
+
| 0.1346 | 6.0 | 456 | 0.3048 | 0.8815 |
|
74 |
+
| 0.0943 | 7.0 | 532 | 0.3402 | 0.8898 |
|
75 |
+
| 0.0622 | 8.0 | 608 | 0.3287 | 0.8915 |
|
76 |
+
| 0.0613 | 9.0 | 684 | 0.3634 | 0.8865 |
|
77 |
+
| 0.0585 | 10.0 | 760 | 0.3905 | 0.8881 |
|
78 |
+
| 0.0328 | 11.0 | 836 | 0.3830 | 0.8948 |
|
79 |
+
| 0.0344 | 12.0 | 912 | 0.4094 | 0.8915 |
|
80 |
+
| 0.053 | 13.0 | 988 | 0.4103 | 0.8932 |
|
81 |
+
| 0.0261 | 14.0 | 1064 | 0.4498 | 0.8932 |
|
82 |
+
| 0.0261 | 15.0 | 1140 | 0.4936 | 0.8915 |
|
83 |
+
| 0.0343 | 16.0 | 1216 | 0.4859 | 0.8932 |
|
84 |
+
| 0.0153 | 17.0 | 1292 | 0.5143 | 0.8815 |
|
85 |
+
| 0.0038 | 18.0 | 1368 | 0.5271 | 0.8865 |
|
86 |
+
| 0.0046 | 19.0 | 1444 | 0.5417 | 0.8898 |
|
87 |
+
| 0.0282 | 20.0 | 1520 | 0.5283 | 0.8948 |
|
88 |
+
| 0.0048 | 21.0 | 1596 | 0.5421 | 0.8965 |
|
89 |
+
| 0.0018 | 22.0 | 1672 | 0.5503 | 0.8898 |
|
90 |
+
| 0.0064 | 23.0 | 1748 | 0.5860 | 0.8848 |
|
91 |
+
| 0.0241 | 24.0 | 1824 | 0.5762 | 0.8948 |
|
92 |
+
| 0.0207 | 25.0 | 1900 | 0.5869 | 0.8915 |
|
93 |
+
| 0.0293 | 26.0 | 1976 | 0.5842 | 0.8948 |
|
94 |
+
| 0.0029 | 27.0 | 2052 | 0.6141 | 0.8932 |
|
95 |
+
| 0.0198 | 28.0 | 2128 | 0.6046 | 0.8982 |
|
96 |
+
| 0.0329 | 29.0 | 2204 | 0.6286 | 0.8948 |
|
97 |
+
| 0.0036 | 30.0 | 2280 | 0.6053 | 0.8948 |
|
98 |
+
| 0.0339 | 31.0 | 2356 | 0.6159 | 0.8881 |
|
99 |
+
| 0.0211 | 32.0 | 2432 | 0.6253 | 0.8932 |
|
100 |
+
| 0.0315 | 33.0 | 2508 | 0.6357 | 0.8915 |
|
101 |
+
| 0.0135 | 34.0 | 2584 | 0.6365 | 0.8932 |
|
102 |
+
| 0.0361 | 35.0 | 2660 | 0.6309 | 0.8965 |
|
103 |
+
| 0.0313 | 36.0 | 2736 | 0.6365 | 0.8965 |
|
104 |
+
| 0.0198 | 37.0 | 2812 | 0.6348 | 0.8965 |
|
105 |
+
| 0.0132 | 38.0 | 2888 | 0.6243 | 0.8948 |
|
106 |
+
| 0.0085 | 39.0 | 2964 | 0.6351 | 0.8948 |
|
107 |
+
| 0.001 | 40.0 | 3040 | 0.6372 | 0.8948 |
|
108 |
+
| 0.0149 | 41.0 | 3116 | 0.6607 | 0.8998 |
|
109 |
+
| 0.0056 | 42.0 | 3192 | 0.6570 | 0.9065 |
|
110 |
+
| 0.0011 | 43.0 | 3268 | 0.6635 | 0.8998 |
|
111 |
+
| 0.003 | 44.0 | 3344 | 0.6527 | 0.8982 |
|
112 |
+
| 0.041 | 45.0 | 3420 | 0.6537 | 0.8982 |
|
113 |
+
| 0.0011 | 46.0 | 3496 | 0.6576 | 0.8982 |
|
114 |
+
| 0.0196 | 47.0 | 3572 | 0.6599 | 0.8998 |
|
115 |
+
| 0.0117 | 48.0 | 3648 | 0.6620 | 0.9032 |
|
116 |
+
| 0.0018 | 49.0 | 3724 | 0.6617 | 0.9032 |
|
117 |
+
| 0.0144 | 50.0 | 3800 | 0.6618 | 0.9032 |
|
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 343083404
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6a33a347629b2365be6275ff039c71db2a66a60d7c57b3b4723934a91c3ba4b
|
3 |
size 343083404
|
runs/Nov30_16-47-28_f888a2bfcfb9/events.out.tfevents.1701362851.f888a2bfcfb9.842.10
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 sha256:7dc3a83d505218c5a5117ab60360579e407604cc63a77a5f04aa3bd631baa9dd
|
3 |
+
size 81022
|