End of training
Browse files- README.md +95 -0
- model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: Boya1_Adamax_1-e4_20Epoch_Deit-tiny-patch16_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: 0.5695346320346321
|
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 |
+
# Boya1_Adamax_1-e4_20Epoch_Deit-tiny-patch16_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: 3.5040
|
36 |
+
- Accuracy: 0.5695
|
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: 16
|
57 |
+
- eval_batch_size: 16
|
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: 20
|
63 |
+
|
64 |
+
### Training results
|
65 |
+
|
66 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
67 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
68 |
+
| 1.3705 | 1.0 | 923 | 1.4925 | 0.4968 |
|
69 |
+
| 1.1741 | 2.0 | 1846 | 1.3247 | 0.5411 |
|
70 |
+
| 1.1089 | 3.0 | 2769 | 1.2524 | 0.5777 |
|
71 |
+
| 0.8912 | 4.0 | 3692 | 1.2699 | 0.5712 |
|
72 |
+
| 0.6118 | 5.0 | 4615 | 1.3695 | 0.5725 |
|
73 |
+
| 0.4514 | 6.0 | 5538 | 1.5162 | 0.5690 |
|
74 |
+
| 0.3342 | 7.0 | 6461 | 1.6732 | 0.5641 |
|
75 |
+
| 0.1558 | 8.0 | 7384 | 1.8402 | 0.5668 |
|
76 |
+
| 0.139 | 9.0 | 8307 | 2.0769 | 0.5676 |
|
77 |
+
| 0.0399 | 10.0 | 9230 | 2.4530 | 0.5582 |
|
78 |
+
| 0.0251 | 11.0 | 10153 | 2.6195 | 0.5630 |
|
79 |
+
| 0.0197 | 12.0 | 11076 | 2.8679 | 0.5598 |
|
80 |
+
| 0.0022 | 13.0 | 11999 | 3.0450 | 0.5593 |
|
81 |
+
| 0.0102 | 14.0 | 12922 | 3.1628 | 0.5614 |
|
82 |
+
| 0.0226 | 15.0 | 13845 | 3.2622 | 0.5655 |
|
83 |
+
| 0.0004 | 16.0 | 14768 | 3.3164 | 0.5668 |
|
84 |
+
| 0.0003 | 17.0 | 15691 | 3.3759 | 0.5703 |
|
85 |
+
| 0.0002 | 18.0 | 16614 | 3.4406 | 0.5687 |
|
86 |
+
| 0.0002 | 19.0 | 17537 | 3.4891 | 0.5695 |
|
87 |
+
| 0.0004 | 20.0 | 18460 | 3.5040 | 0.5695 |
|
88 |
+
|
89 |
+
|
90 |
+
### Framework versions
|
91 |
+
|
92 |
+
- Transformers 4.40.1
|
93 |
+
- Pytorch 2.1.0
|
94 |
+
- Datasets 2.19.0
|
95 |
+
- Tokenizers 0.19.1
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 22134280
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4bdfc079524802f3c300ecf33b94544aff0f9f6231f21a7ff38fec07950cc454
|
3 |
size 22134280
|