Augusto777
commited on
Commit
•
2970071
1
Parent(s):
f544ee7
Model save
Browse files
README.md
ADDED
@@ -0,0 +1,151 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: beit-base-patch16-224-ve-U13-b-80b
|
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: validation
|
21 |
+
args: default
|
22 |
+
metrics:
|
23 |
+
- name: Accuracy
|
24 |
+
type: accuracy
|
25 |
+
value: 0.782608695652174
|
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 |
+
# beit-base-patch16-224-ve-U13-b-80b
|
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: 0.9549
|
36 |
+
- Accuracy: 0.7826
|
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: 5e-05
|
56 |
+
- train_batch_size: 32
|
57 |
+
- eval_batch_size: 32
|
58 |
+
- seed: 42
|
59 |
+
- gradient_accumulation_steps: 4
|
60 |
+
- total_train_batch_size: 128
|
61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
+
- lr_scheduler_type: linear
|
63 |
+
- lr_scheduler_warmup_ratio: 0.1
|
64 |
+
- num_epochs: 80
|
65 |
+
|
66 |
+
### Training results
|
67 |
+
|
68 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
69 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
70 |
+
| No log | 0.92 | 6 | 1.3182 | 0.4565 |
|
71 |
+
| 1.6182 | 2.0 | 13 | 1.3056 | 0.4565 |
|
72 |
+
| 1.6182 | 2.92 | 19 | 1.2884 | 0.4565 |
|
73 |
+
| 1.592 | 4.0 | 26 | 1.2807 | 0.4565 |
|
74 |
+
| 1.4756 | 4.92 | 32 | 1.2991 | 0.4565 |
|
75 |
+
| 1.4756 | 6.0 | 39 | 1.2451 | 0.5 |
|
76 |
+
| 1.352 | 6.92 | 45 | 1.1845 | 0.5217 |
|
77 |
+
| 1.2143 | 8.0 | 52 | 1.0315 | 0.6087 |
|
78 |
+
| 1.2143 | 8.92 | 58 | 0.9289 | 0.5435 |
|
79 |
+
| 1.0327 | 10.0 | 65 | 0.8925 | 0.5435 |
|
80 |
+
| 0.8878 | 10.92 | 71 | 0.8633 | 0.5652 |
|
81 |
+
| 0.8878 | 12.0 | 78 | 0.7566 | 0.6304 |
|
82 |
+
| 0.7712 | 12.92 | 84 | 0.7669 | 0.7609 |
|
83 |
+
| 0.6808 | 14.0 | 91 | 0.7635 | 0.7609 |
|
84 |
+
| 0.6808 | 14.92 | 97 | 0.8653 | 0.6304 |
|
85 |
+
| 0.5844 | 16.0 | 104 | 0.7193 | 0.7174 |
|
86 |
+
| 0.4332 | 16.92 | 110 | 0.6186 | 0.7826 |
|
87 |
+
| 0.4332 | 18.0 | 117 | 1.0295 | 0.6739 |
|
88 |
+
| 0.3607 | 18.92 | 123 | 0.8007 | 0.7609 |
|
89 |
+
| 0.3134 | 20.0 | 130 | 0.6790 | 0.7826 |
|
90 |
+
| 0.3134 | 20.92 | 136 | 0.8013 | 0.7391 |
|
91 |
+
| 0.2988 | 22.0 | 143 | 0.7481 | 0.7609 |
|
92 |
+
| 0.2988 | 22.92 | 149 | 0.9280 | 0.6739 |
|
93 |
+
| 0.2487 | 24.0 | 156 | 0.6542 | 0.7391 |
|
94 |
+
| 0.1912 | 24.92 | 162 | 0.7134 | 0.7609 |
|
95 |
+
| 0.1912 | 26.0 | 169 | 0.8421 | 0.7609 |
|
96 |
+
| 0.1946 | 26.92 | 175 | 0.7284 | 0.7391 |
|
97 |
+
| 0.1685 | 28.0 | 182 | 0.7507 | 0.8261 |
|
98 |
+
| 0.1685 | 28.92 | 188 | 0.7610 | 0.8043 |
|
99 |
+
| 0.1646 | 30.0 | 195 | 0.8013 | 0.7826 |
|
100 |
+
| 0.166 | 30.92 | 201 | 0.8803 | 0.7826 |
|
101 |
+
| 0.166 | 32.0 | 208 | 0.7895 | 0.7391 |
|
102 |
+
| 0.1372 | 32.92 | 214 | 0.7760 | 0.7174 |
|
103 |
+
| 0.1424 | 34.0 | 221 | 0.9390 | 0.7174 |
|
104 |
+
| 0.1424 | 34.92 | 227 | 0.7839 | 0.8043 |
|
105 |
+
| 0.1399 | 36.0 | 234 | 0.9422 | 0.7609 |
|
106 |
+
| 0.1238 | 36.92 | 240 | 0.8710 | 0.7174 |
|
107 |
+
| 0.1238 | 38.0 | 247 | 0.8684 | 0.7826 |
|
108 |
+
| 0.123 | 38.92 | 253 | 0.8194 | 0.7609 |
|
109 |
+
| 0.1381 | 40.0 | 260 | 0.9698 | 0.7391 |
|
110 |
+
| 0.1381 | 40.92 | 266 | 0.8545 | 0.7609 |
|
111 |
+
| 0.1081 | 42.0 | 273 | 0.9925 | 0.6739 |
|
112 |
+
| 0.1081 | 42.92 | 279 | 0.9320 | 0.8043 |
|
113 |
+
| 0.0929 | 44.0 | 286 | 1.0242 | 0.7609 |
|
114 |
+
| 0.0898 | 44.92 | 292 | 0.9411 | 0.7609 |
|
115 |
+
| 0.0898 | 46.0 | 299 | 0.8995 | 0.7609 |
|
116 |
+
| 0.12 | 46.92 | 305 | 0.7741 | 0.7826 |
|
117 |
+
| 0.1126 | 48.0 | 312 | 0.7122 | 0.8478 |
|
118 |
+
| 0.1126 | 48.92 | 318 | 0.9099 | 0.7826 |
|
119 |
+
| 0.1088 | 50.0 | 325 | 1.1148 | 0.6957 |
|
120 |
+
| 0.0851 | 50.92 | 331 | 0.9297 | 0.8043 |
|
121 |
+
| 0.0851 | 52.0 | 338 | 0.8801 | 0.8043 |
|
122 |
+
| 0.1001 | 52.92 | 344 | 0.8428 | 0.8261 |
|
123 |
+
| 0.0718 | 54.0 | 351 | 0.9721 | 0.7826 |
|
124 |
+
| 0.0718 | 54.92 | 357 | 0.8771 | 0.8043 |
|
125 |
+
| 0.0842 | 56.0 | 364 | 0.9982 | 0.7826 |
|
126 |
+
| 0.1069 | 56.92 | 370 | 1.1083 | 0.7391 |
|
127 |
+
| 0.1069 | 58.0 | 377 | 0.9072 | 0.7826 |
|
128 |
+
| 0.0803 | 58.92 | 383 | 0.7979 | 0.8261 |
|
129 |
+
| 0.0752 | 60.0 | 390 | 0.7489 | 0.8478 |
|
130 |
+
| 0.0752 | 60.92 | 396 | 0.8023 | 0.8261 |
|
131 |
+
| 0.0646 | 62.0 | 403 | 0.8027 | 0.8261 |
|
132 |
+
| 0.0646 | 62.92 | 409 | 0.8275 | 0.7826 |
|
133 |
+
| 0.0829 | 64.0 | 416 | 0.8587 | 0.8043 |
|
134 |
+
| 0.0616 | 64.92 | 422 | 0.8870 | 0.8043 |
|
135 |
+
| 0.0616 | 66.0 | 429 | 0.8928 | 0.8043 |
|
136 |
+
| 0.0693 | 66.92 | 435 | 0.9289 | 0.7826 |
|
137 |
+
| 0.0657 | 68.0 | 442 | 0.9604 | 0.7609 |
|
138 |
+
| 0.0657 | 68.92 | 448 | 0.9560 | 0.7826 |
|
139 |
+
| 0.0588 | 70.0 | 455 | 0.9544 | 0.7609 |
|
140 |
+
| 0.0578 | 70.92 | 461 | 0.9419 | 0.7826 |
|
141 |
+
| 0.0578 | 72.0 | 468 | 0.9474 | 0.7826 |
|
142 |
+
| 0.0638 | 72.92 | 474 | 0.9540 | 0.7826 |
|
143 |
+
| 0.0592 | 73.85 | 480 | 0.9549 | 0.7826 |
|
144 |
+
|
145 |
+
|
146 |
+
### Framework versions
|
147 |
+
|
148 |
+
- Transformers 4.36.2
|
149 |
+
- Pytorch 2.1.2+cu118
|
150 |
+
- Datasets 2.16.1
|
151 |
+
- 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 sha256:2113645b067634dcff972362744fea77ac70332d7945a7a704a6abb968c3b652
|
3 |
size 343086480
|
runs/Jun12_14-27-46_DESKTOP-SKBE9FB/events.out.tfevents.1718224067.DESKTOP-SKBE9FB.14480.0
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 sha256:8e81eea2fa127f783744811f42192b1298ce052a401bc64b91a0dcf6f8a056b1
|
3 |
+
size 36974
|