vuongnhathien commited on
Commit
949cb22
1 Parent(s): afb16e9

Model save

Browse files
Files changed (1) hide show
  1. README.md +84 -0
README.md ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/convnextv2-base-22k-384
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: convnext-base-wd1e-8-4e-5-erasing
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: validation
21
+ args: default
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.9502982107355865
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
+ # convnext-base-wd1e-8-4e-5-erasing
32
+
33
+ This model is a fine-tuned version of [facebook/convnextv2-base-22k-384](https://huggingface.co/facebook/convnextv2-base-22k-384) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.2306
36
+ - Accuracy: 0.9503
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: 4e-05
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: cosine
61
+ - num_epochs: 10
62
+
63
+ ### Training results
64
+
65
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
67
+ | 0.6036 | 1.0 | 1099 | 0.3737 | 0.8930 |
68
+ | 0.4997 | 2.0 | 2198 | 0.2730 | 0.9249 |
69
+ | 0.3663 | 3.0 | 3297 | 0.2666 | 0.9260 |
70
+ | 0.3176 | 4.0 | 4396 | 0.2380 | 0.9392 |
71
+ | 0.305 | 5.0 | 5495 | 0.2458 | 0.9372 |
72
+ | 0.2489 | 6.0 | 6594 | 0.2389 | 0.9459 |
73
+ | 0.2356 | 7.0 | 7693 | 0.2424 | 0.9451 |
74
+ | 0.1678 | 8.0 | 8792 | 0.2369 | 0.9439 |
75
+ | 0.1565 | 9.0 | 9891 | 0.2323 | 0.9499 |
76
+ | 0.1643 | 10.0 | 10990 | 0.2306 | 0.9503 |
77
+
78
+
79
+ ### Framework versions
80
+
81
+ - Transformers 4.39.3
82
+ - Pytorch 2.1.2
83
+ - Datasets 2.18.0
84
+ - Tokenizers 0.15.2