hkivancoral
commited on
Commit
•
2b6aebe
1
Parent(s):
3c82ab1
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_001_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: 0.5777777777777777
|
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_001_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: 6.3078
|
36 |
+
- Accuracy: 0.5778
|
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 |
+
| 1.4226 | 1.0 | 27 | 1.4140 | 0.2667 |
|
69 |
+
| 1.2045 | 2.0 | 54 | 1.6573 | 0.2889 |
|
70 |
+
| 1.2481 | 3.0 | 81 | 1.5730 | 0.2889 |
|
71 |
+
| 1.322 | 4.0 | 108 | 1.5814 | 0.2889 |
|
72 |
+
| 0.9418 | 5.0 | 135 | 1.4941 | 0.4889 |
|
73 |
+
| 0.9982 | 6.0 | 162 | 1.2480 | 0.4222 |
|
74 |
+
| 0.9049 | 7.0 | 189 | 1.2328 | 0.4667 |
|
75 |
+
| 0.7944 | 8.0 | 216 | 1.2343 | 0.4889 |
|
76 |
+
| 0.9595 | 9.0 | 243 | 1.3356 | 0.4667 |
|
77 |
+
| 0.7289 | 10.0 | 270 | 1.3692 | 0.4889 |
|
78 |
+
| 0.696 | 11.0 | 297 | 1.4324 | 0.4444 |
|
79 |
+
| 0.7466 | 12.0 | 324 | 1.4783 | 0.4667 |
|
80 |
+
| 0.7646 | 13.0 | 351 | 1.3725 | 0.4889 |
|
81 |
+
| 0.6451 | 14.0 | 378 | 2.0057 | 0.5333 |
|
82 |
+
| 0.5784 | 15.0 | 405 | 2.4024 | 0.4444 |
|
83 |
+
| 0.5544 | 16.0 | 432 | 2.4151 | 0.5111 |
|
84 |
+
| 0.563 | 17.0 | 459 | 1.9054 | 0.5556 |
|
85 |
+
| 0.5213 | 18.0 | 486 | 3.0169 | 0.5333 |
|
86 |
+
| 0.551 | 19.0 | 513 | 2.4504 | 0.5333 |
|
87 |
+
| 0.613 | 20.0 | 540 | 2.7289 | 0.5333 |
|
88 |
+
| 0.4577 | 21.0 | 567 | 2.8661 | 0.5111 |
|
89 |
+
| 0.3823 | 22.0 | 594 | 2.7689 | 0.4444 |
|
90 |
+
| 0.3921 | 23.0 | 621 | 3.3303 | 0.5556 |
|
91 |
+
| 0.3974 | 24.0 | 648 | 3.5099 | 0.4444 |
|
92 |
+
| 0.3186 | 25.0 | 675 | 2.8023 | 0.5556 |
|
93 |
+
| 0.2983 | 26.0 | 702 | 3.0145 | 0.4889 |
|
94 |
+
| 0.2885 | 27.0 | 729 | 3.6675 | 0.4667 |
|
95 |
+
| 0.1902 | 28.0 | 756 | 3.2605 | 0.5556 |
|
96 |
+
| 0.2253 | 29.0 | 783 | 4.9420 | 0.5111 |
|
97 |
+
| 0.1963 | 30.0 | 810 | 4.0120 | 0.4889 |
|
98 |
+
| 0.1797 | 31.0 | 837 | 4.7762 | 0.5778 |
|
99 |
+
| 0.1892 | 32.0 | 864 | 4.0878 | 0.5333 |
|
100 |
+
| 0.1404 | 33.0 | 891 | 4.6569 | 0.5111 |
|
101 |
+
| 0.0882 | 34.0 | 918 | 4.6823 | 0.5556 |
|
102 |
+
| 0.1578 | 35.0 | 945 | 5.1512 | 0.5111 |
|
103 |
+
| 0.0782 | 36.0 | 972 | 5.2444 | 0.5778 |
|
104 |
+
| 0.0461 | 37.0 | 999 | 5.0650 | 0.5556 |
|
105 |
+
| 0.0253 | 38.0 | 1026 | 5.4464 | 0.5556 |
|
106 |
+
| 0.0617 | 39.0 | 1053 | 5.7436 | 0.5778 |
|
107 |
+
| 0.0131 | 40.0 | 1080 | 6.2467 | 0.5556 |
|
108 |
+
| 0.0373 | 41.0 | 1107 | 6.5043 | 0.5778 |
|
109 |
+
| 0.0018 | 42.0 | 1134 | 6.2715 | 0.5778 |
|
110 |
+
| 0.0403 | 43.0 | 1161 | 6.0713 | 0.5556 |
|
111 |
+
| 0.0098 | 44.0 | 1188 | 6.6508 | 0.5556 |
|
112 |
+
| 0.0159 | 45.0 | 1215 | 6.4236 | 0.5778 |
|
113 |
+
| 0.0031 | 46.0 | 1242 | 6.3525 | 0.5778 |
|
114 |
+
| 0.007 | 47.0 | 1269 | 6.2593 | 0.5778 |
|
115 |
+
| 0.0011 | 48.0 | 1296 | 6.3063 | 0.5778 |
|
116 |
+
| 0.0085 | 49.0 | 1323 | 6.3078 | 0.5778 |
|
117 |
+
| 0.0126 | 50.0 | 1350 | 6.3078 | 0.5778 |
|
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 sha256:9da3565173384505de3a853d7217eefb961a24a5de7f5c442504054c5015e6b4
|
3 |
size 343086480
|
runs/Nov27_04-34-17_4550fdbe7878/events.out.tfevents.1701059658.4550fdbe7878.67538.1
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 sha256:16cea46b3b2b4df418339ddcbf820940e859ec3213a2faa9625ae021e897d2fa
|
3 |
+
size 42576
|