End of training
Browse files
README.md
ADDED
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: facebook/dinov2-base-imagenet1k-1-layer
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: Foot
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# Foot
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [facebook/dinov2-base-imagenet1k-1-layer](https://huggingface.co/facebook/dinov2-base-imagenet1k-1-layer) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 1.0747
|
21 |
+
- Accuracy: 0.4865
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 5e-05
|
41 |
+
- train_batch_size: 10
|
42 |
+
- eval_batch_size: 1
|
43 |
+
- seed: 42
|
44 |
+
- gradient_accumulation_steps: 2
|
45 |
+
- total_train_batch_size: 20
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: linear
|
48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
49 |
+
- num_epochs: 30
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
54 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
55 |
+
| No log | 1.0 | 2 | 1.2201 | 0.3378 |
|
56 |
+
| No log | 2.0 | 4 | 1.2243 | 0.2568 |
|
57 |
+
| No log | 3.0 | 6 | 1.2672 | 0.2703 |
|
58 |
+
| No log | 4.0 | 8 | 1.2501 | 0.2297 |
|
59 |
+
| 1.2006 | 5.0 | 10 | 1.1975 | 0.2973 |
|
60 |
+
| 1.2006 | 6.0 | 12 | 1.1270 | 0.3919 |
|
61 |
+
| 1.2006 | 7.0 | 14 | 1.0999 | 0.3243 |
|
62 |
+
| 1.2006 | 8.0 | 16 | 1.1497 | 0.3649 |
|
63 |
+
| 1.2006 | 9.0 | 18 | 1.1006 | 0.3108 |
|
64 |
+
| 1.1058 | 10.0 | 20 | 1.1271 | 0.3514 |
|
65 |
+
| 1.1058 | 11.0 | 22 | 1.1273 | 0.3784 |
|
66 |
+
| 1.1058 | 12.0 | 24 | 1.1639 | 0.2838 |
|
67 |
+
| 1.1058 | 13.0 | 26 | 1.1421 | 0.4054 |
|
68 |
+
| 1.1058 | 14.0 | 28 | 1.1190 | 0.3514 |
|
69 |
+
| 1.0489 | 15.0 | 30 | 1.1735 | 0.3243 |
|
70 |
+
| 1.0489 | 16.0 | 32 | 1.1422 | 0.3378 |
|
71 |
+
| 1.0489 | 17.0 | 34 | 1.1414 | 0.3649 |
|
72 |
+
| 1.0489 | 18.0 | 36 | 1.1033 | 0.4189 |
|
73 |
+
| 1.0489 | 19.0 | 38 | 1.0747 | 0.3919 |
|
74 |
+
| 0.9717 | 20.0 | 40 | 1.0952 | 0.3919 |
|
75 |
+
| 0.9717 | 21.0 | 42 | 1.1063 | 0.3784 |
|
76 |
+
| 0.9717 | 22.0 | 44 | 1.0822 | 0.3649 |
|
77 |
+
| 0.9717 | 23.0 | 46 | 1.0768 | 0.3784 |
|
78 |
+
| 0.9717 | 24.0 | 48 | 1.0753 | 0.4595 |
|
79 |
+
| 0.9816 | 25.0 | 50 | 1.0531 | 0.4054 |
|
80 |
+
| 0.9816 | 26.0 | 52 | 1.0624 | 0.4189 |
|
81 |
+
| 0.9816 | 27.0 | 54 | 1.0690 | 0.4459 |
|
82 |
+
| 0.9816 | 28.0 | 56 | 1.1392 | 0.3514 |
|
83 |
+
| 0.9816 | 29.0 | 58 | 1.0696 | 0.4054 |
|
84 |
+
| 0.9576 | 30.0 | 60 | 1.0747 | 0.4865 |
|
85 |
+
|
86 |
+
|
87 |
+
### Framework versions
|
88 |
+
|
89 |
+
- Transformers 4.35.2
|
90 |
+
- Pytorch 2.1.0+cu121
|
91 |
+
- Datasets 2.15.0
|
92 |
+
- Tokenizers 0.15.0
|