hkivancoral
commited on
Commit
•
258a445
1
Parent(s):
169b5e8
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-tiny-patch16-224
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- imagefolder
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: smids_3x_deit_tiny_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: 0.7683333333333333
|
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_3x_deit_tiny_sgd_0001_fold3
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [facebook/deit-tiny-patch16-224](https://huggingface.co/facebook/deit-tiny-patch16-224) on the imagefolder dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.6313
|
36 |
+
- Accuracy: 0.7683
|
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 |
+
| 1.2114 | 1.0 | 225 | 1.2115 | 0.3783 |
|
69 |
+
| 1.0735 | 2.0 | 450 | 1.1384 | 0.3983 |
|
70 |
+
| 1.097 | 3.0 | 675 | 1.1002 | 0.4133 |
|
71 |
+
| 1.0469 | 4.0 | 900 | 1.0702 | 0.4533 |
|
72 |
+
| 1.0229 | 5.0 | 1125 | 1.0448 | 0.48 |
|
73 |
+
| 0.99 | 6.0 | 1350 | 1.0213 | 0.5 |
|
74 |
+
| 0.9781 | 7.0 | 1575 | 0.9993 | 0.5117 |
|
75 |
+
| 0.9907 | 8.0 | 1800 | 0.9784 | 0.54 |
|
76 |
+
| 0.927 | 9.0 | 2025 | 0.9582 | 0.545 |
|
77 |
+
| 0.8847 | 10.0 | 2250 | 0.9391 | 0.5583 |
|
78 |
+
| 0.9329 | 11.0 | 2475 | 0.9207 | 0.5733 |
|
79 |
+
| 0.8984 | 12.0 | 2700 | 0.9031 | 0.59 |
|
80 |
+
| 0.8494 | 13.0 | 2925 | 0.8859 | 0.605 |
|
81 |
+
| 0.8194 | 14.0 | 3150 | 0.8694 | 0.6183 |
|
82 |
+
| 0.7869 | 15.0 | 3375 | 0.8536 | 0.6283 |
|
83 |
+
| 0.8309 | 16.0 | 3600 | 0.8389 | 0.635 |
|
84 |
+
| 0.7966 | 17.0 | 3825 | 0.8246 | 0.64 |
|
85 |
+
| 0.8108 | 18.0 | 4050 | 0.8113 | 0.64 |
|
86 |
+
| 0.801 | 19.0 | 4275 | 0.7985 | 0.6533 |
|
87 |
+
| 0.771 | 20.0 | 4500 | 0.7864 | 0.66 |
|
88 |
+
| 0.7097 | 21.0 | 4725 | 0.7747 | 0.67 |
|
89 |
+
| 0.7109 | 22.0 | 4950 | 0.7636 | 0.6767 |
|
90 |
+
| 0.7079 | 23.0 | 5175 | 0.7529 | 0.6867 |
|
91 |
+
| 0.7294 | 24.0 | 5400 | 0.7431 | 0.69 |
|
92 |
+
| 0.7458 | 25.0 | 5625 | 0.7335 | 0.6883 |
|
93 |
+
| 0.6793 | 26.0 | 5850 | 0.7246 | 0.6917 |
|
94 |
+
| 0.6665 | 27.0 | 6075 | 0.7159 | 0.7017 |
|
95 |
+
| 0.6522 | 28.0 | 6300 | 0.7080 | 0.7083 |
|
96 |
+
| 0.7013 | 29.0 | 6525 | 0.7004 | 0.715 |
|
97 |
+
| 0.6636 | 30.0 | 6750 | 0.6932 | 0.7183 |
|
98 |
+
| 0.6224 | 31.0 | 6975 | 0.6867 | 0.72 |
|
99 |
+
| 0.6822 | 32.0 | 7200 | 0.6803 | 0.725 |
|
100 |
+
| 0.6885 | 33.0 | 7425 | 0.6745 | 0.7283 |
|
101 |
+
| 0.6623 | 34.0 | 7650 | 0.6692 | 0.7333 |
|
102 |
+
| 0.6059 | 35.0 | 7875 | 0.6642 | 0.735 |
|
103 |
+
| 0.6546 | 36.0 | 8100 | 0.6598 | 0.7417 |
|
104 |
+
| 0.6233 | 37.0 | 8325 | 0.6556 | 0.7433 |
|
105 |
+
| 0.6474 | 38.0 | 8550 | 0.6519 | 0.7467 |
|
106 |
+
| 0.606 | 39.0 | 8775 | 0.6483 | 0.75 |
|
107 |
+
| 0.6243 | 40.0 | 9000 | 0.6453 | 0.755 |
|
108 |
+
| 0.6167 | 41.0 | 9225 | 0.6425 | 0.7567 |
|
109 |
+
| 0.6518 | 42.0 | 9450 | 0.6401 | 0.7617 |
|
110 |
+
| 0.5844 | 43.0 | 9675 | 0.6380 | 0.7633 |
|
111 |
+
| 0.6425 | 44.0 | 9900 | 0.6361 | 0.7633 |
|
112 |
+
| 0.6354 | 45.0 | 10125 | 0.6346 | 0.7633 |
|
113 |
+
| 0.5465 | 46.0 | 10350 | 0.6333 | 0.765 |
|
114 |
+
| 0.6036 | 47.0 | 10575 | 0.6324 | 0.7667 |
|
115 |
+
| 0.5553 | 48.0 | 10800 | 0.6318 | 0.7683 |
|
116 |
+
| 0.6342 | 49.0 | 11025 | 0.6314 | 0.7683 |
|
117 |
+
| 0.5635 | 50.0 | 11250 | 0.6313 | 0.7683 |
|
118 |
+
|
119 |
+
|
120 |
+
### Framework versions
|
121 |
+
|
122 |
+
- Transformers 4.32.1
|
123 |
+
- Pytorch 2.1.1+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 22167850
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:999a20108fce1d20621d73edd6ea97c139b6e8d58234fbaf3eff6d64a5dbd80d
|
3 |
size 22167850
|