hkivancoral
commited on
Commit
•
6626728
1
Parent(s):
aca11f1
End of training
Browse files
README.md
ADDED
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: hushem_1x_deit_tiny_adamax_lr00001_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: 0.4634146341463415
|
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_1x_deit_tiny_adamax_lr00001_fold5
|
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: 1.2718
|
36 |
+
- Accuracy: 0.4634
|
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: 1e-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: 50
|
65 |
+
|
66 |
+
### Training results
|
67 |
+
|
68 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
69 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
70 |
+
| No log | 0.67 | 1 | 1.6411 | 0.1220 |
|
71 |
+
| No log | 2.0 | 3 | 1.5318 | 0.1951 |
|
72 |
+
| No log | 2.67 | 4 | 1.5063 | 0.1707 |
|
73 |
+
| No log | 4.0 | 6 | 1.4764 | 0.3171 |
|
74 |
+
| No log | 4.67 | 7 | 1.4625 | 0.3171 |
|
75 |
+
| No log | 6.0 | 9 | 1.4352 | 0.3902 |
|
76 |
+
| 1.379 | 6.67 | 10 | 1.4210 | 0.4390 |
|
77 |
+
| 1.379 | 8.0 | 12 | 1.3993 | 0.4390 |
|
78 |
+
| 1.379 | 8.67 | 13 | 1.3906 | 0.4390 |
|
79 |
+
| 1.379 | 10.0 | 15 | 1.3747 | 0.4146 |
|
80 |
+
| 1.379 | 10.67 | 16 | 1.3676 | 0.4146 |
|
81 |
+
| 1.379 | 12.0 | 18 | 1.3554 | 0.4146 |
|
82 |
+
| 1.379 | 12.67 | 19 | 1.3500 | 0.4146 |
|
83 |
+
| 1.107 | 14.0 | 21 | 1.3389 | 0.4146 |
|
84 |
+
| 1.107 | 14.67 | 22 | 1.3348 | 0.4146 |
|
85 |
+
| 1.107 | 16.0 | 24 | 1.3265 | 0.4390 |
|
86 |
+
| 1.107 | 16.67 | 25 | 1.3236 | 0.4634 |
|
87 |
+
| 1.107 | 18.0 | 27 | 1.3162 | 0.4634 |
|
88 |
+
| 1.107 | 18.67 | 28 | 1.3129 | 0.4390 |
|
89 |
+
| 0.9495 | 20.0 | 30 | 1.3051 | 0.4390 |
|
90 |
+
| 0.9495 | 20.67 | 31 | 1.3019 | 0.4390 |
|
91 |
+
| 0.9495 | 22.0 | 33 | 1.2961 | 0.4390 |
|
92 |
+
| 0.9495 | 22.67 | 34 | 1.2934 | 0.4634 |
|
93 |
+
| 0.9495 | 24.0 | 36 | 1.2879 | 0.4390 |
|
94 |
+
| 0.9495 | 24.67 | 37 | 1.2851 | 0.4390 |
|
95 |
+
| 0.9495 | 26.0 | 39 | 1.2815 | 0.4390 |
|
96 |
+
| 0.8401 | 26.67 | 40 | 1.2802 | 0.4390 |
|
97 |
+
| 0.8401 | 28.0 | 42 | 1.2775 | 0.4390 |
|
98 |
+
| 0.8401 | 28.67 | 43 | 1.2761 | 0.4390 |
|
99 |
+
| 0.8401 | 30.0 | 45 | 1.2740 | 0.4390 |
|
100 |
+
| 0.8401 | 30.67 | 46 | 1.2734 | 0.4390 |
|
101 |
+
| 0.8401 | 32.0 | 48 | 1.2723 | 0.4634 |
|
102 |
+
| 0.8401 | 32.67 | 49 | 1.2719 | 0.4634 |
|
103 |
+
| 0.7816 | 33.33 | 50 | 1.2718 | 0.4634 |
|
104 |
+
|
105 |
+
|
106 |
+
### Framework versions
|
107 |
+
|
108 |
+
- Transformers 4.35.0
|
109 |
+
- Pytorch 2.1.0+cu118
|
110 |
+
- Datasets 2.14.6
|
111 |
+
- Tokenizers 0.14.1
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 22123464
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1ede8f7a7b8e32282f5da3a927e5d5903df1ac88e6c69fe5ddebad277994922
|
3 |
size 22123464
|
runs/Nov10_12-20-53_cc003f633cf7/events.out.tfevents.1699618853.cc003f633cf7.5821.4
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 sha256:84cf1bb66681b328fee666319dd9f50587e0bde6c5b94b5e315c831b53efc0ab
|
3 |
+
size 16301
|