Commit
•
fd991a6
1
Parent(s):
8138e5e
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_sgd_001_fold5
|
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: 0.84
|
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_sgd_001_fold5
|
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: 0.3960
|
36 |
+
- Accuracy: 0.84
|
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 |
+
| 1.0915 | 1.0 | 75 | 1.0482 | 0.46 |
|
69 |
+
| 0.8641 | 2.0 | 150 | 0.8453 | 0.6317 |
|
70 |
+
| 0.8005 | 3.0 | 225 | 0.7497 | 0.67 |
|
71 |
+
| 0.7495 | 4.0 | 300 | 0.6945 | 0.7067 |
|
72 |
+
| 0.7055 | 5.0 | 375 | 0.6553 | 0.7467 |
|
73 |
+
| 0.7202 | 6.0 | 450 | 0.6245 | 0.75 |
|
74 |
+
| 0.6588 | 7.0 | 525 | 0.6019 | 0.7583 |
|
75 |
+
| 0.6049 | 8.0 | 600 | 0.5871 | 0.76 |
|
76 |
+
| 0.6317 | 9.0 | 675 | 0.5605 | 0.7833 |
|
77 |
+
| 0.5775 | 10.0 | 750 | 0.5437 | 0.785 |
|
78 |
+
| 0.5951 | 11.0 | 825 | 0.5303 | 0.7933 |
|
79 |
+
| 0.5297 | 12.0 | 900 | 0.5191 | 0.79 |
|
80 |
+
| 0.5261 | 13.0 | 975 | 0.5051 | 0.7933 |
|
81 |
+
| 0.5545 | 14.0 | 1050 | 0.4974 | 0.7983 |
|
82 |
+
| 0.4597 | 15.0 | 1125 | 0.4949 | 0.805 |
|
83 |
+
| 0.4273 | 16.0 | 1200 | 0.4837 | 0.8017 |
|
84 |
+
| 0.4781 | 17.0 | 1275 | 0.4758 | 0.8067 |
|
85 |
+
| 0.4613 | 18.0 | 1350 | 0.4662 | 0.815 |
|
86 |
+
| 0.4966 | 19.0 | 1425 | 0.4609 | 0.8133 |
|
87 |
+
| 0.5166 | 20.0 | 1500 | 0.4558 | 0.81 |
|
88 |
+
| 0.4529 | 21.0 | 1575 | 0.4548 | 0.8167 |
|
89 |
+
| 0.4333 | 22.0 | 1650 | 0.4478 | 0.8233 |
|
90 |
+
| 0.4673 | 23.0 | 1725 | 0.4422 | 0.8183 |
|
91 |
+
| 0.402 | 24.0 | 1800 | 0.4383 | 0.8283 |
|
92 |
+
| 0.4207 | 25.0 | 1875 | 0.4375 | 0.8283 |
|
93 |
+
| 0.4343 | 26.0 | 1950 | 0.4301 | 0.8267 |
|
94 |
+
| 0.4249 | 27.0 | 2025 | 0.4265 | 0.8283 |
|
95 |
+
| 0.4127 | 28.0 | 2100 | 0.4255 | 0.8267 |
|
96 |
+
| 0.4286 | 29.0 | 2175 | 0.4192 | 0.8367 |
|
97 |
+
| 0.3988 | 30.0 | 2250 | 0.4174 | 0.8367 |
|
98 |
+
| 0.3838 | 31.0 | 2325 | 0.4145 | 0.8383 |
|
99 |
+
| 0.3896 | 32.0 | 2400 | 0.4157 | 0.835 |
|
100 |
+
| 0.4348 | 33.0 | 2475 | 0.4153 | 0.825 |
|
101 |
+
| 0.41 | 34.0 | 2550 | 0.4109 | 0.8367 |
|
102 |
+
| 0.3989 | 35.0 | 2625 | 0.4069 | 0.84 |
|
103 |
+
| 0.3824 | 36.0 | 2700 | 0.4101 | 0.8367 |
|
104 |
+
| 0.3688 | 37.0 | 2775 | 0.4062 | 0.8367 |
|
105 |
+
| 0.4091 | 38.0 | 2850 | 0.4063 | 0.8367 |
|
106 |
+
| 0.3672 | 39.0 | 2925 | 0.4039 | 0.835 |
|
107 |
+
| 0.4219 | 40.0 | 3000 | 0.4009 | 0.8383 |
|
108 |
+
| 0.4047 | 41.0 | 3075 | 0.4024 | 0.8383 |
|
109 |
+
| 0.4168 | 42.0 | 3150 | 0.3989 | 0.835 |
|
110 |
+
| 0.4198 | 43.0 | 3225 | 0.3971 | 0.8417 |
|
111 |
+
| 0.4236 | 44.0 | 3300 | 0.3971 | 0.84 |
|
112 |
+
| 0.3959 | 45.0 | 3375 | 0.3975 | 0.8433 |
|
113 |
+
| 0.3933 | 46.0 | 3450 | 0.3984 | 0.8433 |
|
114 |
+
| 0.3443 | 47.0 | 3525 | 0.3963 | 0.8417 |
|
115 |
+
| 0.3626 | 48.0 | 3600 | 0.3958 | 0.8417 |
|
116 |
+
| 0.38 | 49.0 | 3675 | 0.3960 | 0.8417 |
|
117 |
+
| 0.3733 | 50.0 | 3750 | 0.3960 | 0.84 |
|
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 sha256:346b912c500094fd7997b932f983de607eb041915a49812ebc5d89dbfcfec021
|
3 |
size 343083404
|
runs/Dec13_01-15-40_e9f1c7e988d1/events.out.tfevents.1702430142.e9f1c7e988d1.694.14
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 sha256:6e12a4ef563d9fd6e93991b1def926469de99aefd45e2cca9726d1d8d7d21113
|
3 |
+
size 80222
|