hkivancoral
commited on
Commit
•
b0f7c74
1
Parent(s):
5347bb1
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: facebook/deit-base-patch16-224
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- imagefolder
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: hushem_40x_deit_base_sgd_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: 0.46511627906976744
|
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_40x_deit_base_sgd_0001_fold3
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [facebook/deit-base-patch16-224](https://huggingface.co/facebook/deit-base-patch16-224) on the imagefolder dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 1.2710
|
36 |
+
- Accuracy: 0.4651
|
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 |
+
| 1.3787 | 1.0 | 217 | 1.4567 | 0.2326 |
|
69 |
+
| 1.3411 | 2.0 | 434 | 1.4476 | 0.2326 |
|
70 |
+
| 1.3346 | 3.0 | 651 | 1.4398 | 0.2326 |
|
71 |
+
| 1.3522 | 4.0 | 868 | 1.4325 | 0.2558 |
|
72 |
+
| 1.295 | 5.0 | 1085 | 1.4257 | 0.2558 |
|
73 |
+
| 1.3027 | 6.0 | 1302 | 1.4192 | 0.2791 |
|
74 |
+
| 1.2908 | 7.0 | 1519 | 1.4129 | 0.3023 |
|
75 |
+
| 1.2684 | 8.0 | 1736 | 1.4068 | 0.3023 |
|
76 |
+
| 1.2597 | 9.0 | 1953 | 1.4007 | 0.3023 |
|
77 |
+
| 1.2504 | 10.0 | 2170 | 1.3948 | 0.3023 |
|
78 |
+
| 1.2181 | 11.0 | 2387 | 1.3891 | 0.3023 |
|
79 |
+
| 1.2286 | 12.0 | 2604 | 1.3834 | 0.3023 |
|
80 |
+
| 1.229 | 13.0 | 2821 | 1.3779 | 0.3023 |
|
81 |
+
| 1.2118 | 14.0 | 3038 | 1.3725 | 0.3256 |
|
82 |
+
| 1.1939 | 15.0 | 3255 | 1.3673 | 0.3256 |
|
83 |
+
| 1.2054 | 16.0 | 3472 | 1.3622 | 0.3488 |
|
84 |
+
| 1.1836 | 17.0 | 3689 | 1.3572 | 0.3721 |
|
85 |
+
| 1.1754 | 18.0 | 3906 | 1.3524 | 0.3721 |
|
86 |
+
| 1.1872 | 19.0 | 4123 | 1.3477 | 0.3721 |
|
87 |
+
| 1.1652 | 20.0 | 4340 | 1.3431 | 0.3721 |
|
88 |
+
| 1.1396 | 21.0 | 4557 | 1.3387 | 0.3721 |
|
89 |
+
| 1.1373 | 22.0 | 4774 | 1.3343 | 0.3953 |
|
90 |
+
| 1.1381 | 23.0 | 4991 | 1.3300 | 0.3953 |
|
91 |
+
| 1.101 | 24.0 | 5208 | 1.3259 | 0.3953 |
|
92 |
+
| 1.1305 | 25.0 | 5425 | 1.3219 | 0.4186 |
|
93 |
+
| 1.1458 | 26.0 | 5642 | 1.3181 | 0.4186 |
|
94 |
+
| 1.0969 | 27.0 | 5859 | 1.3143 | 0.4186 |
|
95 |
+
| 1.092 | 28.0 | 6076 | 1.3106 | 0.4186 |
|
96 |
+
| 1.0422 | 29.0 | 6293 | 1.3071 | 0.4186 |
|
97 |
+
| 1.07 | 30.0 | 6510 | 1.3037 | 0.4419 |
|
98 |
+
| 1.097 | 31.0 | 6727 | 1.3005 | 0.4419 |
|
99 |
+
| 1.1048 | 32.0 | 6944 | 1.2974 | 0.4419 |
|
100 |
+
| 1.0657 | 33.0 | 7161 | 1.2945 | 0.4419 |
|
101 |
+
| 1.0841 | 34.0 | 7378 | 1.2918 | 0.4419 |
|
102 |
+
| 1.0697 | 35.0 | 7595 | 1.2891 | 0.4419 |
|
103 |
+
| 1.0586 | 36.0 | 7812 | 1.2867 | 0.4419 |
|
104 |
+
| 1.0346 | 37.0 | 8029 | 1.2845 | 0.4419 |
|
105 |
+
| 1.0364 | 38.0 | 8246 | 1.2824 | 0.4651 |
|
106 |
+
| 1.055 | 39.0 | 8463 | 1.2804 | 0.4651 |
|
107 |
+
| 1.0391 | 40.0 | 8680 | 1.2787 | 0.4651 |
|
108 |
+
| 1.0408 | 41.0 | 8897 | 1.2771 | 0.4651 |
|
109 |
+
| 1.0911 | 42.0 | 9114 | 1.2757 | 0.4651 |
|
110 |
+
| 1.042 | 43.0 | 9331 | 1.2745 | 0.4651 |
|
111 |
+
| 1.0562 | 44.0 | 9548 | 1.2735 | 0.4651 |
|
112 |
+
| 1.0444 | 45.0 | 9765 | 1.2727 | 0.4651 |
|
113 |
+
| 1.0551 | 46.0 | 9982 | 1.2720 | 0.4651 |
|
114 |
+
| 1.0314 | 47.0 | 10199 | 1.2715 | 0.4651 |
|
115 |
+
| 1.067 | 48.0 | 10416 | 1.2712 | 0.4651 |
|
116 |
+
| 1.0573 | 49.0 | 10633 | 1.2710 | 0.4651 |
|
117 |
+
| 1.0022 | 50.0 | 10850 | 1.2710 | 0.4651 |
|
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 343275306
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aeb66968218afa7338bdca071b8cfdd40fff517ee690462d4fefd2421199a5ce
|
3 |
size 343275306
|