hkivancoral
commited on
Commit
•
02d2fe3
1
Parent(s):
d84927f
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_rms_0001_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: 0.6744186046511628
|
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_rms_0001_fold3
|
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: 2.0271
|
36 |
+
- Accuracy: 0.6744
|
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 |
+
| 1.4187 | 1.0 | 28 | 1.4291 | 0.2558 |
|
69 |
+
| 1.401 | 2.0 | 56 | 1.4569 | 0.2558 |
|
70 |
+
| 1.367 | 3.0 | 84 | 1.2989 | 0.2791 |
|
71 |
+
| 1.3068 | 4.0 | 112 | 1.1706 | 0.5116 |
|
72 |
+
| 1.282 | 5.0 | 140 | 1.1869 | 0.5581 |
|
73 |
+
| 1.1177 | 6.0 | 168 | 0.8916 | 0.7442 |
|
74 |
+
| 0.8904 | 7.0 | 196 | 0.7798 | 0.7209 |
|
75 |
+
| 0.9449 | 8.0 | 224 | 0.6587 | 0.7674 |
|
76 |
+
| 0.8708 | 9.0 | 252 | 1.0524 | 0.5814 |
|
77 |
+
| 0.9352 | 10.0 | 280 | 0.7664 | 0.6744 |
|
78 |
+
| 0.8718 | 11.0 | 308 | 0.6191 | 0.7907 |
|
79 |
+
| 0.7977 | 12.0 | 336 | 1.1991 | 0.6512 |
|
80 |
+
| 0.8081 | 13.0 | 364 | 0.7062 | 0.7674 |
|
81 |
+
| 0.7399 | 14.0 | 392 | 0.7130 | 0.6744 |
|
82 |
+
| 0.8202 | 15.0 | 420 | 0.7484 | 0.6977 |
|
83 |
+
| 0.7069 | 16.0 | 448 | 0.6665 | 0.6977 |
|
84 |
+
| 0.6169 | 17.0 | 476 | 0.7828 | 0.6279 |
|
85 |
+
| 0.6766 | 18.0 | 504 | 0.9849 | 0.5814 |
|
86 |
+
| 0.6876 | 19.0 | 532 | 0.7015 | 0.7442 |
|
87 |
+
| 0.5123 | 20.0 | 560 | 0.9230 | 0.7442 |
|
88 |
+
| 0.4885 | 21.0 | 588 | 0.9671 | 0.6279 |
|
89 |
+
| 0.5212 | 22.0 | 616 | 1.2712 | 0.6744 |
|
90 |
+
| 0.5047 | 23.0 | 644 | 0.7902 | 0.6512 |
|
91 |
+
| 0.4047 | 24.0 | 672 | 1.3996 | 0.7209 |
|
92 |
+
| 0.361 | 25.0 | 700 | 1.1508 | 0.6279 |
|
93 |
+
| 0.362 | 26.0 | 728 | 1.0709 | 0.6279 |
|
94 |
+
| 0.3752 | 27.0 | 756 | 0.9894 | 0.6512 |
|
95 |
+
| 0.2958 | 28.0 | 784 | 1.2219 | 0.6279 |
|
96 |
+
| 0.3016 | 29.0 | 812 | 0.8154 | 0.6977 |
|
97 |
+
| 0.2083 | 30.0 | 840 | 1.2432 | 0.6047 |
|
98 |
+
| 0.2249 | 31.0 | 868 | 1.5401 | 0.6047 |
|
99 |
+
| 0.1443 | 32.0 | 896 | 1.3193 | 0.6279 |
|
100 |
+
| 0.1501 | 33.0 | 924 | 1.1707 | 0.6977 |
|
101 |
+
| 0.1715 | 34.0 | 952 | 1.1677 | 0.7442 |
|
102 |
+
| 0.2795 | 35.0 | 980 | 1.2992 | 0.6744 |
|
103 |
+
| 0.1174 | 36.0 | 1008 | 1.6643 | 0.6744 |
|
104 |
+
| 0.1132 | 37.0 | 1036 | 1.7522 | 0.6279 |
|
105 |
+
| 0.0738 | 38.0 | 1064 | 1.6182 | 0.6744 |
|
106 |
+
| 0.0433 | 39.0 | 1092 | 2.1223 | 0.6512 |
|
107 |
+
| 0.0483 | 40.0 | 1120 | 2.5522 | 0.5814 |
|
108 |
+
| 0.0333 | 41.0 | 1148 | 1.8374 | 0.6977 |
|
109 |
+
| 0.0107 | 42.0 | 1176 | 1.9629 | 0.6744 |
|
110 |
+
| 0.013 | 43.0 | 1204 | 1.6900 | 0.7209 |
|
111 |
+
| 0.0316 | 44.0 | 1232 | 2.1881 | 0.6512 |
|
112 |
+
| 0.0272 | 45.0 | 1260 | 1.8428 | 0.6744 |
|
113 |
+
| 0.0298 | 46.0 | 1288 | 1.7049 | 0.7674 |
|
114 |
+
| 0.0196 | 47.0 | 1316 | 1.9117 | 0.6744 |
|
115 |
+
| 0.0084 | 48.0 | 1344 | 2.0336 | 0.6744 |
|
116 |
+
| 0.0059 | 49.0 | 1372 | 2.0271 | 0.6744 |
|
117 |
+
| 0.0065 | 50.0 | 1400 | 2.0271 | 0.6744 |
|
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 sha256:1b40dc385b830eae3ad3b2016244e759ec4d6987798280e42fe87f4e79581653
|
3 |
size 343086480
|
runs/Nov29_06-49-53_ac8792add2e0/events.out.tfevents.1701240595.ac8792add2e0.2336.20
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 sha256:9f7bd2863954b86e911950ef63fa31adc617def6fb56e5cf48859c2e096c4f73
|
3 |
+
size 43356
|